International Journal of Intelligent Engineering and Systems

11

Authors: Hetal Vipul Gandhi, Vahida Zakirhusen Attar

Aspect Based Sentiment Analysis (ABSA) aims to perceive the opinion of the majority of reviewers for each feature (aspect category) of the product. We target both Aspect Term Polarity (ATP) and Aspect Category Polarity (ACP) subtasks of ABSA. We retrieve different word vector-based representations of sentence and augment them with n-gram and sentiment features using novel algorithm. We employ supervised machine learning approaches and propose the ensemble of Logistic Regression, k-Nearest Neighbor, and Support Vector Machine models for these subtasks. We experiment with four major domains from Hindi ABSA Dataset and report increase in performance accuracy by 16% for ATP subtask and 2% to 13% across domains for ACP subtask over results from researchers who released this dataset. Secondly, we also propose a novel WFBOS method to compute the Summary Score [range: 100 to 100] of each category from a particular domain. We make use of frequency of positive, neutral, negative, and conflict sentiment, of each aspect category from among the reviews of a particular domain in Hindi ABSA Dataset to do this computation.

31

Authors: Barlian Henryranu Prasetio, Edita Rosana Widasari, Fitra Abdurrachman Bachtiar

The nonverbal communication processes a critical parcel. In some cases verbal communication is incapable since the speaker does not utilize non-verbal communication well at the same time. Non-verbal communication which falls in unconscious emotion is important in determining in function of cognition, language comprehension, and decision making. However, a little research studied in this area. Many years, researchers are amazed by the reliability of Mel-Frequency Cepstral Coefficients (MFCC) feature extraction technique in recognizing stressed speech. In this paper, we propose a simple feature extraction technique that effective but strong enough to recognize stressed speech. There are the speech energy and frequency. We attempted a basic approach to classify unbiased or stretch on female and male discourse. The highlight extraction is based on control and recurrence. This investigate utilized 10 female and 10 male discourse datasets. There are 5 classification strategies utilized. The classification models are Neural Arrange, k-Nearest Neighbour, Bolster Vector Machine, combination of NN-k-NN and combination of NN-SVM. Test comes about approved utilizing k-fold cross-validation strategy. The tests are assessed utilizing R-index to distinguish whether the highlights contributing to the push discourse acknowledgment. Based on exploratory comes about, the number of inputs impacts the esteem of R-index. In general, combining the Neural Organize and Back Vector Machine is the most excellent classification strategy by appearing stretch acknowledgment rate of 85% precision.

53

Authors: Nischaykumar Hegde, Linganagouda Kulkarni

Mobile sink-based sensor networks deployed in unattended environment are characterized by infrequent sink visits. In these applications, ensuring the survivability and confidentiality of data is important till it is collected by the sink. The data must also be prevented from collection by agents other than sink and leakage by neighbours. Data collection in unattended environment must also be energy efficient to prolong the life time of the network. This work proposes a novel Energy Aware Adaptive Compressive Sensing (EA-ACS) assisted secure data survivability scheme which is able to optimize energy consumption at cost of data accuracy level desired by applications. The solution introduces three novelties: adaptive compressive sensing for reducing the foot print of data and energy consumption during transmission, a novel bi party authentication scheme for secure data collection by sink and low energy overhead piggy bagging for data replication. Through performance in NS2, the proposed solution is found to provide at least 6% higher data survivability and 20% lower energy consumption compared to existing works.

76

Authors: Puppala Ramya, Tumati Jashwanth, Dupaguntla Venkata Sathvik

Technological advancements in block chain (BC)-based frameworks have empowered scientists to create innovative inventions such as e-casting ballots. The traditional agreement models utilized proof-of-work (PoW) in the Bitcoin that affected energy utilization and bargained the adaptability for the ballot framework. The existing works evaluates the trust basically only on the centralized party as it was not feasible because of the dynamic changes in the pervasive social networking (PSN) topology and their characteristics. The present research work proposes a block chain based trust evaluation model for the PSN based BC. The proposed hybrid proof of stake-trust (PST) BC is based on the proof-of trust (PoT) and also the proof of stake (PoS) overcomes the issues that are occurring in the e-vote casting. The trust evaluation is performed for public verification and becomes transparent for each node of PSN. The advantage of the proposed method is that a new block will be designed for trust evaluation during the block generation. The process of sharding erases the workload when the network works fast for the individual nodes provides the sum of their alternative parts. Therefore, the model utilizes the agreements for generating the safe process that guarantee the precision to vote it from the time of the election results. The present research work utilizes the proof of stake-trust based BC resulted in security improvement. The model improves the adaptability and execution of the BC based on the ballot framework provided a secured voting system for the government. The proposed PST-BC model showed better results in terms of latency as 15/s when compared with the existing models merkle hash tree -bloom filter that obtained 107.3/s and performance constraints based electron of 18/s.

97

Authors: Krishna Reddy Gajulapalli, Merlin Sheeba Gnanadhas

The hybrid innovation of Orthogonal Frequency Division Multiplexing (OFDM) through Multiple-Input Multiple-Output (MIMO) delivers a feasible substitute to increase the Quality of Service (QoS) to accomplish better data rate and spectral efficiency for the transmission network. An extraordinary Peak-to-Average Power Ratio (PAPR) and Bit Error Rate (BER) are the important parameters that can be considered in the analysis of the MIMO-OFDM network. Partition Transmit Sequences (PTSs) is one of the capable procedures and direct methods to attain a reasonable PAPR performance. However, it needs a serious restoration process to discover the vital features that produce a computational multi-layered design with sub-blocks. Here, a reduced computational complexity PTS scheme is proposed which is completely depends on the hybrid procedure named as Moth Flame Optimization with Improved Firefly Algorithm (MFO-IFFA). The simulation outcomes demonstrated the capability of the proposed MFO-IFFA approach decreases the PAPR reduction up to 3.6 dB. Similarly, the proposed MFO-IFFA overcomes the significant evolutionary procedures mentioned in the existing works such as Additive Signal Mixing (ASM), Adaptive Simplified Optimized Iterative Clipping and Filtering (ASOICF) and Hybrid Independent Component Analysis (HICA).

116

Authors: Bharathi Ramachandra, T. P. Surekha

Wireless Sensor Network (WSN) is developed as a promising technology for a wide range of applications due to its low installation cost. However, the nodes in the WSN are susceptible to different security threats, because these nodes are located in hostile or harsh environments. The important goal of this paper is to obtain secure data transmission while minimizing energy consumption. In this paper, an Improved Moth Flame Optimization (IMFO) is used for selecting the optimal Cluster Head (CH) from the network. Moreover, the secure routing path is generated using the IMFO where the fitness function considers residual energy, distance, trust and node degree. Therefore, the Secure Clustering and Routing using IMFO (SCRIMFO) provides the resistance against the Distributed Denial-of-Service (DDoS) attack whereas the energy consumption is minimized by identifying the shortest path. The proposed SCRIMFO method is analysed in terms of Average Energy Consumption (AEC), Packet Loss Ratio (PLR), Packet Delivery Ratio (PDR) and routing load. Here, the SCRIMFO method is compared with the Secure Routing Protocol based on Multi-objective Ant-colony-optimization (SRPMA), Ant Colony Conveyance Algorithm (ACCA) and Energy-aware Trust and Opportunity-based Routing (ETOR) approaches. The PDR of the SCRIMFO is 94.64 % for 2 DDoS attacks that is high when compared to the SRPMA, ACCA and ETOR.

142

Authors: Shaymah Akram Yasear, Hayder M. A. Ghanimi

This paper proposes a modified honey badger algorithm (MHBA) for solving the optimal power flow (OPF) problem. This problem is a highly non-linear, non-convex and complex optimization problem with several decision variables and constraints. The original honey badger algorithm (HBA) has the problem of trapping in local optima due to the loss of population diversity, especially in solving complex optimization problems. Therefore, the MHBA aims at sufficient improvement in finding the optimal solution and feasibility. Opposition-based learning strategy (OBL) is integrated with the MHBA to preserve the diversity of the population and enhance the convergence toward the optimal solution. The effectiveness of the MHBA algorithm is evaluated on five objective functions of the OPF problem namely, total generation fuel cost minimization, active power and reactive power transmission losses minimization, voltage deviation and voltage stability enhancement. The performance of the proposed algorithm is tested and validated on the IEEE 30-bus test system. The proposed MHBA is compared with the HBA and other nature-inspired optimization algorithms reported in the literature. The results indicate that the proposed MHBA algorithm has the superiority to jump out of the local optimal and better convergence in solving the OPF problem. This is due to the strategy used in the algorithm which helps in maintaining the population diversity and provides a proper balance between exploration and exploitation.

167

Authors: Ammar Abdul Ameer Rasheed, Ahmed Sabah Al-Araji, Mohammed Najm Abdullah

During the previous years, the number of researchers who discussed the field of path planning algorithms has increased. In this paper, a proposed hybrid technique for path planning based on the benefits of sampling-based algorithms and heuristic path planning algorithms was enhanced. Rapidly-exploring Random Tree star (RRT*) was used to generate the candidate nodes that represent a collision-free path. These candidate nodes were applied to the Particle Swarm Optimization (PSO) algorithm to generate the shortest and the smoothest path planning (the optimal path planning) for the mobile robot. The RRT*PSO algorithm was applied in two scenarios (static and dynamic environments) with a workspace of [500×500] cm using MATLAB 2021a. In the static environment, a workspace full of obstacles was chosen to find the shortest collision-free path. In addition, a reference path equation was found to calculate the reference linear and angular velocities of the mobile robot as well as the linear and angular velocities of the right and left wheels. In this work, the suggested hybrid RRT*PSO algorithm improves path length 34.27% compared to the A* algorithm and the fuzzy analytic hierarchy process (A*–FAHP hybrid) algorithm and 0.35% compared to the Self-adaptive evolutionary game-based particle swarm optimization (SAEGBPSO) algorithm. In the dynamic environment, an algorithm named (contour path down and contour path up) was suggested to avoid collisions with dynamic obstacles. By using this suggested algorithm, the reference linear and angular velocities of the mobile robot as well as the linear and angular velocities of the right and left wheels were calculated to obtain a smooth path followed and free-navigation with dynamic obstacles in an environment.

198

Authors: Najla Akram AL-Saati

In this work, the wild horse optimization (WHO) algorithm, known for its ease of use, efficiency, and fast convergence, is explored in solving the reliability redundancy allocation problem (RRAP) for series-parallel systems. This problem has as of late caught the attention of researchers in this area, especially in today’s rapidly growing field of artificial intelligence. The NP-hard RRAP problem deals with maximizing of reliability under certain constraints. This work uses WHO algorithm to maximize the overall system reliability by determining how many redundant components are to be used along with their reliabilities in each subsystem, such reliability is constrained by cost, volume, and weight. Testing is carried out to show the effectiveness of this algorithm using four known numerical examples, results are to be compared with simplified swarm algorithm (SSO), attraction-repulsion imperialist competitive algorithm (AR-ICA), hybrid salp swarm algorithm and teaching-learning based optimization (HSS-TLBO), particle swarm optimization (PSO), and gradient based optimization (GBO). Computational results show that WHO was able to find better feasible near-optimal solutions effectively and efficiently in terms of population size and number of iterations.

216

Authors: Sritha Sreedharan, Ranjith Nadarajan

Dimensionality reduction is the most prominent process in artificial intelligence and data science because of using a massive amount of high-dimensional information. In recent days, many dimensionality reduction algorithms focused on the harmonic mean-based linear discriminant analysis (HLDA) which was the enhanced version of classical LDA. In particular, two different variants such as HLDA and HLDA pairwise (HLDAp) have been applied to reduce the high-dimensional data by using the harmonic mean between-class distance. However, its computation time complexity was high during the initialization phase since it comprises the matrix Eigen decomposition/inverse. Hence this article proposes the Fast HLDA (FHLDA) and FHLDA pairwise (FHLDAp) algorithms for reducing the high-dimensional data during classification. In this algorithm, a joint diagonalization scheme is introduced instead of Eigen decomposition depending on Taylor expansion for lessening the number of iterations in the initialization step to produce the discriminant. It does not a choice to a sweeping task so that every element of the Eigenvector matrix at every iteration is calculated to minimize the computation time burden. As well, a first-order approximation of the inverse Eigenvector matrix and the complete matrix of Eigenvectors are updated at every iteration. On the contrary, the overlap among the samples of dissimilar classes tends to miscategorization. So, the optimal discriminant vector is discovered to solve this issue by extending the between-class scatter matrices. Finally, the experimental outcomes show that the FHLDA and FHLDAp algorithms achieve 10 % higher average accuracy than LDA, ALDA, WLDA, G2DLDA, HLDA, and HLDAp algorithms.

237

Authors: Abdul Azeez, Suraiya Tarannum

In wireless communication systems, Multiple-Input Multiple-Out (MIMO) and Orthogonal Frequency Division Multiplexing (OFDM) were widely used technology. Spectrum utilization efficiency is needed to improve in OFDM technology for effective performance. A Nested Particle Swarm Optimization and Grey Wolf Optimization (HPSO-GWO) is proposed with the Low-Density Parity-Check (LDPC) coding scheme for minimizing the errors that occurred while transmitting the data bits over the MIMO-OFDM. The Nested PSO-GWO process involves in update the velocity of PSO using GWO method that helps to increases the convergence rate and balance the trade-off between exploration-exploitation process. The optimal velocity update in the PSO helps to escape from local optima trap in the search process and improve the efficiency of the model. Generally, the linear error-correcting codes are applied in Low-Density Parity-Check (LDPC) that is used to transmit the message in a noisy channel. Fast Fourier Transform (FFT), CP removal, and the Serial to Parallel (S/P) are accomplished as well as the received data bits are demodulated to obtain the output bits on the receiver side. The proposed method has 10-2 CCDF in 5.6 PAPR and the existing method requires more than 6 PAPR to achieve 10-2 CCDF.

257

Authors: Ahmed H. Aliwy, Ayad R. Abbas, Mustafa J. Hadi

Sentiment analysis (SA) is one of the most important tasks in the natural language processing (NLP) field. Many researchers have been trying to build an efficient SA system for many applications such as detection of terrorist activities, customer support management, analyzing customer feedback, market research, competitive research, and many others. Almost all these researches deal with a classification task, and they tried to solve one or two of the challenges that face this task. In this research, a complete SA system was constructed for processing five main challenges in SA and studying the effect of each one on the system. These challenges are the processing of negation, multi-polarity of words, text multi-polarity, semantically ambiguous words (exact meaning), and sarcasm. Some solutions were introduced for these challenges for getting high accuracy. It is the first work for studying the effect of these five challenges collectively with novel solutions to some of them. For aspect-based SA, three different classifiers were used; support vector machine (SVM), maximum entropy (MaxEnt), and long short-term memory (LSTM). The best results for f-measure were 0.833, 0.852, and 0.875 using the LSTM method on Foursquare ABSA, SemEval2014 (laptop and restaurant) datasets, respectively. We induced the most effective negation processing on the SA system from many test scenarios, followed by multi-polarity of words, semantically ambiguous words, text multi-polarity, and sarcasm, respectively. Also, the proposed sarcasm processing technique was evaluated on two annotated corpora with sarcasm, iSarcasm, and Rillof datasets, before applying it on SA.

279

Authors: Chada Sampath Reddy, G. Narsimha

Wireless sensor networking (WSN) is an important subject among the researchers in recent years and it is recognized as a familiar approach for upcoming applications like traffic monitoring in real time, battlefield, and eco-systems for surveillance. The network has receptive data and it is essential that the networks secure the several types of attacks like eavesdropping, capturing the node, rejection of service. Various sensor networks routing approach has been proposed to secure the networks. This work offers a secure routing scheme in WSN with deep learning approaches. Initially, trust verification is performed to select the non-malicious node, which is carried out through long short-term memory (LSTM), where the malicious nodes are removed. Secondly, data transmission is done through encrypting the data using elliptic curve cryptography (ECC) algorithm. This encrypted data is forwarded to the secured shortest paths, in which the secure shortest path is selected by dragonfly algorithm (DA) through solving the multi-objective function by incorporating the measures like distance, energy, delay, throughput, and trust. Evaluation of cost function of the proposed DA-LSTM model is correspondingly secured 22 %, 27 %, 31 %, and 18 % enriched performance than the PSO-LSTM, GWO-LSTM, WOA-LSTM, and CSA-LSTM at iteration 10th. Finally, the numerical simulations show that the suggested secure routing and data transmission in WSN is validated with other optimization algorithms and shows an advanced performance based on analysis with various performance measures by concerning with the number of sensor nodes and the maximum number of iterations.

303

Authors: Jatinder Pal Singh, Anuj Kumar Gupta

Wireless sensor networks (WSNs) have become a dominant technology in recent years due to their vast range of applications. However, the creation of energy-efficient WSN remains elusive. Clustering methods have long been employed in WSNs to reduce energy consumption and extend network lifetime, but efficient cluster head (CH) selection and competent routing always pose a major obstacle. This paper, proposes a new routing technique in which CH selection is performed using whale based tunicate swarm algorithm (WTSA) and routing between CHs is implemented using aquila optimizer (AO). In the proposed technique WTSA is used to identify efficient CHs from the WSN network, and remaining nodes join these CHs by assessing the cost function value. CHs residual energy, node degree, distance from base station (BS) and intra-cluster distance are being used to derive this cost function. AO is used for inter-clustering routing between CHs that are far from the BS. With the help of a fitness function, AO is used to cultivate optimal routes between CHs and to weed out ineffective routes. The performance of the proposed technique WTSA-AO is compared with state-of-the-art techniques BOA, PSO-GSA, BERA, WTSA, and LEACH in terms of delay, number of alive nodes, throughput and average energy consumption. The results show that the proposed technique improves the performance of wireless sensor networks by reducing average energy consumption by 8.3 % compared to WTSA and striving to achieve a delay of 0.121 seconds for 200 nodes.

329

Authors: Srinivasarao Thumati, S Vadivel, M Venu Gopala Rao

Several studies in the literature have focused the use of optimum network reconfiguration (ONR) and/or optimal allocation of renewable energy (RE) based distributed generation (DG) methodologies to improve performance in electrical distribution networks (EDNs). However, a few studies have only focused at simultaneous ONR and DG allocation in the context of demand increase, network loading unpredictability, or RE power. Furthermore, there is no much focus on the influence of emerging electric vehicle (EV) load penetration on EDN performance. This study proposes a novel meta-heuristic strategy for solving the simultaneous optimal ONR and RE-based DGs allocation problem for minimising distribution losses, improving voltage profile, and lowering greenhouse gas (GHG) emissions while considering the load penetration of electric vehicles (EVs). For solving the complexity inherent in the multi-objective optimization problem with numerous constraints and multi-type variables, a new and efficient honey badger algorithm (HBA) is proposed. On the IEEE 33-bus EDN, simulations are run with various EV load penetration levels. In terms of fitness function, HBA is observed to be superior to COA, TLBO, CSA, and PSO. As observed in the results, for 50% EV load penetration, the losses, AVD, and GHG emissions are increased to 1571.676 kW, 0.02658 p.u., and 25780.05 103 (lb/h), respectively. However, by having DGs optimally and with ONR, the losses, AVD, and GHG emissions are decreased to 77.08 kW, 0.00038 p.u., and 2175.01103 (lb/h), respectively. This indicates that the performance of EDN is improved significantly by having simultaneous DGs allocation and ONR solution irrespective of EV load penetration level. This also indicates the suitability of the proposed methodology for practical applications.

352

Authors: Harmandeep Singh, Vipul Sharma, Damanpreet Singh

Recently, breast cancer has achieved top position in terms of cause of mortality among women of all age groups by surpassing the lung cancer. To improve the survival rate, timely assessments are essential. Mammography is the best modality among the most widely used timely detection modalities. The radiologists’ manual reading may have an impact on the accuracy of the diagnosis. As a result, the computer-aided diagnosis (CAD) systems are being developed as tools to reduce the false alarms and to increase the diagnosis accuracy. In this study, an attempt has been made to improve the diagnosis performance of the CAD systems by incorporating recently developed marine predators algorithm (MPA) in conjunction with three different neural network classifiers including feedforward neural network (FFNN), cascade forward neural network (CFNN), and recurrent neural network (RNN). Unlike other existing studies, fully digital mammogram images from INbreast dataset have been employed for testing of the system proposed in this study. Experimental results reveal that the best classification performance [Accuracy 97.34%, Sensitivity: 98.40%, Specificity: 100.00%] is obtained when MPA is used in conjunction with RNN classifier. To demonstrate the usefulness of the proposed system, the obtained results are compared with the results obtained using already invented CAD systems in previously published studies using the same dataset. The findings suggest that the proposed system is acceptable for real-time clinical applications.

382

Authors: Suwito Suwito, Mochamad Ashari, Muhammad Rivai, M. Anis Mustaghfirin

This paper presents a multisector drip irrigation system (DIS) powered by solar photovoltaic (PV). A binary particle swarm optimization (BPSO) method possibly determines irrigation in multisector, depending on the power availability of the solar PV. The power from solar PV in this study was optimized through maximum power point tracking (MPPT) using an incremental conductance (INC) method. A prototype was built using a PV emulator in 10 controlled irrigation sectors. Three operating modes applied include control of all sectors with BPSO, partly sectors with a combination of linear programming, and all sectors with bypassed without BPSO. Simulations and tests showed very similar results, indicating that the BPSO method provides an optimal and accurate irrigation system with 0.7 psi of an average irrigation operating pressure (IOP) error, 4.01 % of water volume error, and 96.55 % of the uniformity coefficient of water volume.

406

Authors: Sudha Rani Chikkalwar, Yugandhar Garapati

An intrusion detection system monitors the networks and identifies the malware or suspicious activity in the network. Machine learning techniques were applied in the Intrusion detection system to improve its efficiency in the identifications. Imbalance data problem in intrusion detection affects the performance of identification and deep learning methods have overfitting problems. The autoencoder – support vector machine – grasshopper optimization (AE-SVM-GO) model is proposed to overcome the limitation of the overfitting problem in intrusion detection. The hybrid technique of AE-SVM-GO is applied to solve imbalance data problem and overfitting problem in intrusion detection. The autoencoder model is applied to generate the instances of minority classes to balance the dataset. The Grasshopper optimization performance hyper-parameter optimization in the SVM model to learn the features to adaptively set the parameter in classification. Four datasets such as UNSW-NB15, CICIDS2017, NSL-KDD, and Kyoto 2006+ dataset were used to test the proposed AE-SVM-GO model. The proposed AE-SVM-GO model has 95.3 % accuracy, whereas the existing convolutional recurrent neural network (CRNN) and SVM-naïve bayes model has 76.82 %, and 93.75 % accuracy respectively.

425

Authors: Ravi Mohan Sharma, Chaitanya P Agrawal

With the fast advancement of smartphone technology, the smartphone has emerged as the most prevailing instrument for accessing the Internet and obtaining a wide range of services with a click. Increased use of smartphones for online payments has attracted fraudsters, adding to an increase in malware outbreaks. Mobile application vulnerabilities and malware are the origins of various types of fraud and numerous cyber-attacks. Large datasets are frequently used for malware analysis; however, large datasets may contain many redundant, inappropriate, and noisy features, resulting in misclassification and low detection rates. This paper presents a hybrid approach to Android malware detection that reduces the dimensionality of datasets to reduce resource-intensive computation while preserving critical information. We present a novel hybrid approach for detecting Android malware based on a meta-heuristic (modified Intelligent Water Drop Algorithm (IWD)) and Deep Learning (DL) techniques. The studies show that the proposed approach efficiently removes irrelevant attributes and attains significant detection performance with an F1-Score of 93.7%, a precision of 95.35, an accuracy of 99.12%, and a recall rate of 96.68%.

447

Authors: Kavitha Muruganantham, Subbaiah Shanmugasundaram

Online digital marketing achieves their revenue according to their advertisements or sales assignment when companies have the profitable attention for recommending their products to customers via ranking them. Online customers are not able to guarantee that the items delivered through the recommendation by big data are either comprehensive or applicable to their essentials. In the past few years, recommendation frameworks were broadly applied to analyze the massive amount of data. Among those, a Distributed Predictive model with Matrix factorization and random Forest (DPMF) has achieved high efficiency to predict the item ratings. However, it accounts only for user preferences and opinions whereas the other contextual data are necessary for enhancing the efficiency of rating prediction. In this article, a Distributed Improved Predictive model with a Matrix factorization and random Forest (DIPMF) framework is proposed that considers the elements of social context and the dynamic characteristic of every user for every item to enhance the quality of prediction. The primary aim is to combine the information from the preferences, opinions and social context of each user. The social context of users is multiple features of the context such as differences in the current opinion with earlier opinion, behavior, relationship and interaction. Since each user is connected through relations and interactions. At first, the training dataset is split into an optimal amount of splits for accelerating the parallel and distributed training process. Then, the training process is carried out by the DPMF with the Distributed Improved Predictive model with Matrix factorization-Improved variant (DIPMI) to create the representation of every user's preferences, opinions and social contexts in the training set. Further, the prediction of rating is formulated as a regression challenge and solved via the Random Forest (RF) algorithm that predicts the customer’s rating behavior with their opinions and social context for every product. Finally, the experiments are conducted on trip advisor and Amazon datasets to evaluate the efficiency of DIPMI and DIPMF compared to the state-of-the-art recommendation frameworks. The findings exhibit that the DIPMF on the trip advisor dataset achieves an average of 0.6826 Root Mean Square Error (RMSE), 0.5925 Mean Absolute Error (MAE), 0.8369 recommendation quality and 0.0023 Confidence Range (CR) 95% compared to the other frameworks. Similarly, the DIPMF on Amazon dataset achieves an average of 0.7591 RMSE, 0.5704 MAE, 0.8298 recommendation quality and 0.0032 CR 95% compared to the other frameworks.

468

Authors: Binuja Philomina Marydasan, Ranjith Nadarajan

In mobile adhoc networks (MANETs), the most essential problem is to ensure the quality-of-service (QoS) during data transmission via multiple paths from a source to the destination node. To tackle this problem, a topological change adaptive adhoc on-demand multipath distance vector (TA-AOMDV) routing protocol was developed, which ensures QoS according to the different parameters for high-speed node mobility. But, it did not consider the path stability related to the node density, which also affects the routing efficiency. Hence, this paper develops a reliable and stable TA-AOMDV (RSTA-AOMDV) routing protocol that applies a new forwarding strategy to enhance the path reliability and stability for data transmission. In this protocol, every origin node relays data packets to the target in a hop-by-hop manner depending on local information gathered from its one-hop adjacent during the forwarding phase. Also, two different metrics are considered: (i) destination region selection (DRS) and (ii) weighted closeness and connectivity (WCC) to find the stable path from the source to the destination node. During the adjacent finding phase, a forwarding node self-selection mechanism is introduced to reduce the communication overhead due to the high node density and severe congestion. Finally, this protocol is simulated for 2 different cases: (1) a varying node mobility and (2) varying number of nodes. In the case of high-speed node mobility, i.e. 50m/s, the RSTA-AOMDV protocol achieves a 50.7 % packet delivery ratio (PDR), 109.4ms end-to-end delay (E2E-D), 158.51Kbps throughput, 73.4 % normalized routing overhead (NRO) and 11J mean energy consumption (MEC) compared to other existing protocols. Similarly, in the case of high node densities, i.e. when the number of nodes is 100, the RSTA-AOMDV protocol achieves a 66.5 % PDR, 1485.74ms mean E2E-D, 639.7Kbps throughput, 15 % NRO and 22.7J MEC compared to the existing protocols.

489

Authors: Valarmathi Srinivasan, Vijayabhanu Rajagopal

Diabetic Retinopathy (DR) is a common complication of Diabetes Mellitus (DM) that produces retinal abnormalities and can lead to blindness if not diagnosed and treated on time. To address this concern, an adaptive Convolutional Neural Network (CNN) model with Gradient Boosting (GB) called ResNetGB has been used from the literature where a Principal Component Analysis (PCA) based Fully Connected (FC) layer is used to capture the discriminative characteristics from the Retinal Fundus (RF) samples. It is essential to extract more effective features to categorize the DR grades. Hence, in this article, the Multi-Scale Attention (MSA) strategy is incorporated into the ResNetGB model for effective DR grade classification. First, the encoder network is used to embed the RF image in a high-level interpretational space in which the mixture of mid and high-level characteristics is considered to enhance the representation. Then, a Multi-Scale Feature Pyramid (MSFP) is added to define the retinal pattern in various localities and the MSA strategy is applied to the high-level interpretation. Moreover, the entire MSA-ResNetGB framework is trained by the cross-entropy loss to categorize the patients with respective DR grades. Finally, the experimental analysis exhibit that the MSA-ResNetGB model achieves the 94.40% and 94.17% accuracy on two benchmark datasets: Kaggle-APTOS and IDRiD, respectively compared to the cutting-edge models.

509

Authors: Muhammad Kaleem, Ismail Fauzi Bin Isnin

Due to technology scaling, network-on-chip (NoC) become the viable solution for on-chip many-core systems. The most critical concern of NoC is congestion management caused due to heavy communication traffic between nodes. Without an appropriate congestion resolution strategy for reducing heavy in-network traffic, the efficiency of the entire network is damaged severely. In this paper, an interval based record-keeping mechanism is presented to reduce network traffic and congestion by maintaining a history table and previous packet transaction records at each node. Proposed method performs certain validity checks before allowing using previous transaction record from history table. The performance of the technique is investigated in terms of average delay and compared to the state-of-the-art routing algorithms using the Access Noxim simulator. The simulation results demonstrate that the proposed method has outperformed in terms of global average delay, with 8-12% improvement, the average number of hits is 26-61% greater than misses under different synthetic traffic. The proposed algorithm has been tested under various topological configurations for efficiency evaluations.

533

Authors: Muhammad Aidiel Rachman Putra, Tohari Ahmad, Dandy Pramana Hostiadi

Botnets are a severe threat to a computer network, affecting various aspects of security systems, including spreading malicious programs, phishing, sending spam messages, and click fraud. Because of their negative consequences, botnets must be identified early. Nevertheless, their different characteristics have made them challenging to detect. This research proposes a bot patterns communication detection from traffic flows analysis consisting of three main activities: bot detection, extraction, and communication behavior analysis phases. This proposed model aims to obtain a specific behavior of bot attacks, which can be used as an early warning bots attack system. The process of bot patterns communication detection depends on the accuracy of bot detection, so the model improves the pre-processing phase and uses multi-model classification. Improvement in the pre-processing phase is carried out in the feature engineering section using the concept of one-hot encoding. Several machine learning classification models are used to obtain the best detection accuracy: Decision tree, Random forest, Logistic regression, k-NN, and Naïve Bayes. Furthermore, the model has been tested on two different datasets, namely the NCC and CTU-13. The experimental results show that the proposed model is optimal and recognizes bot activities well. The accuracy detection is obtained at 99.99%. Besides, the model can also identify the bot’s attack activity scenario and communication behavior in three types: centralized, distributed, and spread.

555

Authors: Salma El bakkal1* Abdellah Lakhouili1 El Hassan Essoufi

Intelligent traffic controller leads to manage traffic at intersection in order to minimize traffic congestion and has been intensively researched for a several decades. Multi-intersection cooperative traffic signal control (CTSC) is an efficient system that has received a great deal of attention and development in recent years. One problem with multi-intersection CTSC is that controller’s actions are based only on the traffic state or on the decisions taken at previous time step (t-1) at adjacent intersection. To address this problem, in this work a Double Deep Q Network Cooperative Traffic Signal Controller (CTSC-DDQN) is proposed. The CTSC-DDQN algorithm is a reinforcement learning agent that, depending on current traffic conditions, changes the traffic phase distribution order for n-intersection simultaneously. Experimental results under real scenarios show that the proposed approach outperforms other static approach which fixe the time length and the phase order despite the traffic situation and actuated controllers which change the traffic light properties based on the queue length in term of average Q-length and average waiting which eventually leads to mitigate traffic congestion. The results show that our could minimize the average waiting time by up to 79% and the average queue length by up to 80%.

575

Authors: Sai Ram Inkollu, G.V. Prasanna Anjaneyulu, Kotaiah NC, Nagaraja Kumari.CH

Currently global warming is increasing significantly around the world and become one of the typical issues for sustainability. In this connection, many sectors are transforming towards sustainable solutions. Integration of renewable energy (RE) is one such adaption in electrical power systems, by which the burden on conventional plants as well as their greenhouse gas (GHG) emission can be reduced significantly. However, due to radial structure, electrical distribution networks (EDNs) may not support for RE integration inappropriately. There are numerous methods have been introduced on optimal allocation of RE sources in radial distribution networks (RDNs), but not highly focused on maximizing their RE hosting capacity (HC). In this paper, a recent and efficient meta-heuristic algorithm, hunter-prey optimization (HPO) is introduced for finding the optimal locations and sizes of photovoltaic (PV) systems in RDNs. In addition to the loss minimization and voltage profile improvement, maximization of PV hosting capacity (HC) is focused as a major objective. Simulation results are done on IEEE 33-bus RDNs for different scenarios. The computational efficiency of proposed HPO is compared with other recent algorithms and it is observed that the results of HPO are better than other compared methods in terms of global optima. In addition, the enhanced HC of PV systems in RDNs is ensured improved performance in terms of reduced grid-dependency, GHG emission and distribution losses along with improved voltage profile.

599

Authors: Shatha Abdulhadi Muthana, Ku Ruhana Ku-Mahamud

This study presents a comparison between multi-objective optimization methods used to obtain solution for generator maintenance scheduling (GMS) problem. The GMS problem with three objectives which include the total operation cost minimization, system’s reliability (gross reserve) maximization and convenience is considered in this study. Convenience objective is represented by the minimization of the violation in the number of units’ maintenance outage constraint. To solve the problem of GMS, there is a need for GMS model to represent the requirements of electrical power system and optimization method to implement the model and obtain solution for the GMS. The proposed Pareto ant colony system (PACS) algorithm is based on ant colony system algorithm and Pareto approach. Pareto approach is used to make trade-off between the obtained solutions based on the three objectives. In this study comparison is made based on the results of experiments using the IEEE RTS 32- and 36-unit systems while the demand for the 32- and 36-unit systems is based on IEEE RTS demand systems. In addition, four common multi-objective algorithms based on Pareto approach i.e., the Non-dominated Sorting Genetic Algorithm II, Strength Pareto Evolutionary Algorithm 2, Multi-objective Simulated Annealing, and Multi-objective Particle Swarm Optimization are used in the evaluation of the proposed PACS algorithm. The multi-objective GMS model is implemented by all the algorithms and five performance metrics i.e., the grey relational grade (GRG), coverage, distance to Pareto front, overall Pareto spread and the number of non-dominated solutions are used in the evaluation. The Friedman test is also used to evaluate the algorithms’ performance statically, which is made based on GRG metric. The experimental results showed that the proposed PACS algorithm was able to obtain a robust solution by considering different initial operational hours of the units. In term of GRG metric, the PACS algorithm was able to obtain the best results for the 32-unit systems in all the maintenance windows. However, for the 36-unit system, the PACS algorithm secured the second-best results at the early stages of the operation time but outperformed other algorithms during other operation times. For other metrics, overall the PACS algorithm has the best performance in terms of coverage, distance to Pareto front and overall Pareto spread metrics while the NSGAII has the best result in terms of the number of obtained non-dominated solutions. Friedman test implies that the PACS algorithm is significantly better than the other comparative algorithms.

627

Authors: Saka Uma Maheswara Rao, K Venkata Rao, Prasad Reddy PVGD

The medical and health service has become advanced and the smart health care platform has made the diagnosis more robust for the treatment. The accurate analysis of medical data is dependent on early disease detection and the value of accuracy is reduced when the medical data quality is poor. However, the existing approaches failed to deploy the learning model to handle the heterogeneous medical data. The present research work has used the machine learning algorithm effectively for the chronic disease prediction such as heart disease, cancer, diabetes, stroke, and arthritis for the frequent communities and the medical data are available from the disparate sources including a wide variety of information has made difficult to analyse and retrieve. The detailed information about the attributes is required to be known as it is significant in analyzing the medical data. The process of selecting the attributes plays an important role in decision-making for medical disease analysis. The proposed model was tested for its effectiveness and was validated with various benchmark data which was collected from distinct domains. The present research work utilizes Spark Streaming layers for data streaming to diagnose further based on Long Short Term Memory (LSTM) Co-learning with whale optimization approach is from the heterogeneous medical data. The results obtained by the proposed method analysed the disease abnormality better. The existing model obtained SVM-RBF of 81.30 %, k-fold cross-validation and hyperparameters tuning with Random Forest of 94.9%, CNN of 90%, and the proposed LSTM based Co-learning model with Whale optimization approach obtained 98.6 % which is better compared to the existing models.

12

Authors: Ravikumar Mugadhanam, Eranna Uppara

The development of high-performance Radio Frequency (RF) receivers requires an innovative RF front-end design to ensure the best performance out of good technology. Recently, in the industry of wireless technology, the production of receiver designs with better efficiency and performance is increased. A Low Noise Amplifier (LNA) plays a vital role in the performance of an RF receiver. LNA is most commonly designed with the increased number of stages which renders high gain by conquering the noise in the subsequent stages. The previous LNA design topologies (single-stage and two-stage) offer minimum Noise Figure (NF) and high voltage gain with increased power consumption and dissipation. The standalone parameter ‘linearity’ is indirectly dependent on power and it is clear that to achieve high linearity more quantity of power is required. In this research work, an improved three-Stage LNA with Cascode Topology (3S-LNA-CT) is designed with efficiency by satisfying the requirements like minimum NF, improved linearity, low power and high voltage gain. The proposed LNA architecture is realized using three stages in cascade connection because, in the receiver design, low noise and improved performance are the prior design constraints. Cadence Virtuoso software is used to implement the proposed three stage LNA design in 45nm Complimentary Metal Oxide Semiconductor (CMOS) technology. At end of the simulation, the 3S-LNA-CT design achieved 0.33 dB of NF, 7.92µW of power consumption, S11 and S22 values are evaluated -11.36dB and -17.54 dB respectively. The simulation performances of the 3S-LNA-CT is improved compared to the conventional LNA design such as Noise Cancelation Technique (NCT) LNA, Ultra-Wide Band (UWB) LNA, and Particle Swam Optimization (PSO) LNA.

36

Authors: Umasankar Loganathan, Charles Rajeswaran, Harindrakumar Jayaraj, Manoj Magesh

In the present scenario, the DC-DC converter becomes the most significant device and it is used in various applications such as Electric vehicles, fuel cells, sustainable systems, etc. A bidirectional converter used in the above-mentioned applications should be lesser in magnitude and lighter in weight. In case, if the magnitude of the traditional bidirectional DC-DC converter is more, the substituting consistency has been amplified that results in more switching losses. Because of this switching loss, the magnitude of the structure is minimized. To overcome the losses during the process, a novel topology of dc-dc converters is designed with Falcon Optimization Algorithm (FOA) to increase the efficiency of converters. This research proposes the design of Bidirectional DC-DC converter (BDDCDC) for C and π Filter through Fractional Order Proportional Integral Derivative (FOPID) which is tuned by FOA. This proposed controller synthesis considers both robustness and closed-loop performance to ensure a fast and stable regulation characteristic. A simple tuning method provides the appropriate gains to meet design requirements. The outcomes of proposed FOA-FOPID is simulated in MATLAB Simulink which represent the transient performances such as steady state error (1.1 V), rise time (0.21 sec), settling time (0.33 sec) and peak time (0.24 sec) is much better than existing PID and Adaptive Neuro Fuzzy Inference System (ANFIS) control.

59

Authors: Abdelhakim Idir, Khatir Khettab, Yassine Bensafia

The goal of this research is to develop a high-performance fractionalized proportional–integral–derivative (FPID) controller based on Henry Gas Solubility Optimization (HGSO) for controlling the speed of a direct current (DC) motor. The suggested HGSOA-based Fractionalized PID technique with Matsuda approximation method was used to obtain the optimal FPID controller by minimising the integral of time multiplied absolute error (ITAE) as the objective function. Index of performance and disturbance rejection analyses, as well as transient and frequency responses, were all employed to validate the suggested approach's effectiveness. The proposed HGSO-FPID controller with Matsuda approximation was then compared not only to the original HGSO algorithm-tuned PID controller, but also to other controllers tuned by cutting-edge meta-heuristic algorithms such as Atom Search Optimization algorithm (ASO), Grey Wolf Optimization algorithm (GWO), Particle Swarm Optimisation (PSO), Invasive Weed Optimisation (IWO), and stochastic fractal search (SFS). The results showed that the proposed HGSOA-FPID controller has better performance with lower settling time, Ts which 0.1003 s, with lower rise time, Tr which is 0.0579 s, negligible overshoot, D which is 0.0052% and strong output disturbance rejection when compared to the performance of the other controllers.

80

Authors: Velusamy Murugesan, Ponnunaicker Balamurugan

Breast cancer classification through Gene expression analysis is very challenging due to the large variations and missing values problem. However, the traditional normalization and missing value imputation (MVI) methods perform poorly in the occurrence of significant batch effects, heterogeneity, artefacts, and low resolution. Therefore, an efficient pre-processing technique is presented in this paper using Weighted Fuzzy Score (WFS) and Bayesian Independent Principal Component Analysis (BIPCA) for upholding the quality of the expression analysis. In this proposed WFS-BIPCA technique, the large variations are reduced through sustainable transformations by WFS. BIPCA impute replaces the missing expression values without degrading the quality, consistency, and coherence of the output results without repeating all microarray experiments. The proposed WFS-BIPCA technique is evaluated with different classifiers over breast cancer gene expression datasets from Mendeley Data. Results showed that WFS-BIPCA with Support Vector Machine (SVM) classifier achieved high accuracy of 92.36%, 91.86%, 90.02% and 93.89% for BC-TCGA, GSE2034, GSE25066 and Simulation Datasets, respectively. Similarly, it achieved 91.66%, 96.15%, 89.32%, and 95.36% precision, 93.94%, 92.22%, 86.25%, and 97.48% recall, 92.79%, 94.14%, 87.76%, and 96.41% f-measure values and low processing time of 1.98, 0.96, 3.56 and 0.55 seconds for BC-TCGA, GSE2034, GSE25066 and Simulation Datasets, respectively.

103

Authors: Hadeel I. Abdulameer, Mohamed J. Mohamed

In this paper, we present four control structures for the Fractional/Integer Order Fuzzy Proportional Integral Derivative controllers that are used for a 2-link rigid robot manipulator. The manipulator is dealing with the trajectory tracking problem. A metaheuristic optimization technique, namely the most valuable player algorithm, is presented to optimize the controller's parameters while minimizing the integral of time square error. Furthermore, the proposed controllers’ robustness is examined for changing the initial condition, exterior disturbances, and parameter variations. MATLAB code outcomes show that the Fractional Order Fuzzy Proportional Integral Derivative controllers ensure the best trajectory tracking and also improve the system's robustness to change the initial condition, external disturbances, and parameter variations. The best structure is the Fractional Order Fuzzy Proportional Derivative -Fractional Order Proportional Integral Derivative controller among all structures with the minimum integral of time square error that is equal to 7.7481×10-5 for trajectory tracking, 2.4334×10-5 for changing of the initial position, 2.1893×10-4 for disturbances rejection and 2.4990×10-6 for parameter variation. The result showed also that the response of the trajectory tracking for theta1 and theta2 without overshoot and it has minimum settling time in the case of Fractional Order Fuzzy Proportional Derivative -Fractional Order Proportional Integral Derivative controller.

127

Authors: Wiwik Anggraeni, Eko Mulyanto Yuniarno, Reza Fuad Rachmadi, Pujiadi, Mauridhi Hery Purnomo

Climate and geography factors significantly influence the spread of dengue fever. It's critical to figure out the specifics of climatic and geographic conditions and the relationships between current patients. For further preventive measures, it is also necessary to identify the transmission source patients. This study aims to improve the understanding of dengue fever patients spreading under climate and geographic locations. Patients are clustered based on climatic and geographical variables, and influential patients are found in the established network using Fuzzy C-Means and Social Network Analysis. The scenario of cluster numbers' alteration and degree of fuzziness with Fuzzy C-Means made the three groups of patient clusters. A total of 52% of the patients are included in the lowland cluster, based on climate conditions and altitude. The patients grouped better with this approach than with the other compared methods. The Calinski Harabasz score has an average difference of 1644.105. The following relationship in the network is constructed once the cluster has been formed. It is given a fuzzy rule representing the distance of residence and the period of illness between patients. According to the Social Network Analysis approach applied to the region and month scenario, the three areas sensitive to the spreading center are Dau, Kepanjen, and Karangploso. The most significant patient data distribution occurred during the rainy season, peaking in January-February. The centrality algorithm shows that patients with male characteristics and the age range of children and adults could be the source of the disease's spread every month. Kepanjen area is the site of residence with the most significant impact with a proportion of 62.5 % in a year, and the initial illness is the fever related to dengue. Analysis results of this study can use by the Public Health Office to plan and manage resources to prevent extensive spread.

161

Authors: Zainab E. Kanoon, Ahmed Sabah Al-Araji, Mohammed Najm Abdullah

Due to the widespread use of autonomous mobile robots, the path planning of mobile robots take great importance in the research field. This paper aims at developing a path planning method that provides the shortest path with collision avoidance between the starting and the target points in a static robot environment. This paper proposes an intelligent hybrid optimization method that combines two algorithms; the first algorithm is called the Quarter Orbits (QO) algorithm, which tries to enhance the behavior of the cell decomposition path planning algorithm in terms of reducing the path length required to reach the target by steering the mobile robot toward the target using the quarter orbits cells instead of the grid cells and the vertical lines' cells. The second algorithm uses the Particle Swarm Optimization (PSO) algorithm to get a more efficient, smoother, and shorter path for the mobile robot to reach the target in a complex environment. The generated hybrid method is called the Quarter Orbits Particle Swarm Optimization (QOPSO). All simulation results clearly show that the proposed hybrid algorithm provided the shortest path with collision avoidance compared to the results of the Vertical Cell Decomposition (VCD) algorithm and the Radial Cell Decomposition (RCD) algorithm. The proposed hybrid QOPSO algorithm achieves enhancement on the path length equals 29.42% compared to the VCD algorithm and 24.25% compared to the RCD algorithm for different maps using MATLAB 2021a.

193

Authors: Marwa Jaleel Mohsin, Ibrahim A. Murdas

To overcome the RF spectrum crunch in the wireless communication networks and perform high-speed transmission with increased channel capacity, Light fidelity (Li-Fi) was presented by Harald Haas as a promising technology for the fifth generation and beyond. A high-speed Li-Fi system based on all-optical orthogonal frequency division multiplexing (AO-OFDM) was proposed and simulated in this paper. The optical signal was transmitted through a Free-space optical channel link making the proposed system suitable for outdoor application. All-optical OFDM architecture was improved the overall system performance. The 8 and 16 subcarriers were multiplexed demultiplexed through optical inverse fast Fourier transform/fast Fourier transform (OIFFT/OFFT) for the purpose of orthogonality. Optical IFFT was implemented at the transmitter side based on an optical frequency comb generator (OFCG) and dense wavelength division multiplexing (DWDM), while at the receiver side, Optical FFT was implemented based on multi-Mode interferometers (MMI) and time delays. The system was simulated by the VPI photonic design suite and analysed in terms of BER, Constellation diagram, and received power with different FSO path links from 1 to 100Km. Our system achieved a well-received power with high data rate reaches 1.2Tbps and low BER about 1×10-12.

215

Authors: Hatma Suryotrisongko, Yasuo Musashi

We explored the potentials of the quantum machine learning (ML) approach for cybersecurity domain generation algorithm (DGA) detection applications employing two quantum ML approaches: hybrid quantum-classical deep learning (DL) and variational quantum classifier (VQC) models. We implemented quantum noise models and benchmarked the hybrid quantum-classical DL with the VQC-based one. Our datasets include statistical analysis (entropy, relative entropy, information radius, and reputation score) of 1,000,000 Alexa and 803,333 DGA domain names. Qiskit and Pennylane were utilized for the quantum simulations in our experiments. We found that our proposed hybrid quantum DL outperforms the VQC-based model (94.9% maximum accuracy). Investigating the combinations of 12 types of optimizer algorithms, four feature maps, and four variational form circuits reveal that feature maps and variational forms are critical for the VQC algorithm. We show the usefulness of a quantum circuit architecture consisting of Angle Embedding and Random Layers for a hybrid quantum DL model.

233

Authors: Agus Tri Haryono, Riyanarto Sarno, Rachmad Abdullah

Financial headlines and microblogs usually have sentiment of finance and research further about aspect of sentiment analysis still needed. From dataset FiQA 2018 challenges 4 aspect represent about financial, which is corporate, economy, stock and market. This research proposes method to determine financial headlines and microblogs to financial aspect. A sentence form dataset pre-processed into keyword. Aspect categorization using semantic similarity calculate similarity measurement on word vector of sentence with term list of each aspect, the highest similarity value determines the aspect. Neural network is used for sentiment classification of headlines and microblogs, the method used word embedding and bidirectional long short-term memory (BLSTM). The sentiment classification results are combined with the aspect categorization results to determine which aspects have the highest positive sentiment. The highest aspect categorization performance is obtained combined semantic similarity and bidirectional long short-term memory which reach 88.1% and semantic classification accuracy reach 77.0%. The stock aspect has received more positive sentiment compared to the sentiment of other aspect, this can be used for started investment in stock.

253

Authors: Robert Marco, Sharifah Sakinah Syed Ahmad, Sabrina Ahmad

Missing data in software attributes as a common occurrence that can lead to incorrect estimates and poor predictability. For this reason, the imputation approach was used in our study. We model incomplete data using an Autoencoder (AE) approach for missing value imputation, which substantially minimizes the complexity of data modeling when dealing with small data in regression situations. In this study, we introduce the imputation approach through Stacked Denoising Autoencoder (SDAE) with dropout regularization and perform hyperparameter tuning. The scenario presented in this research is built up by eliminating data intervals from the whole dataset at various missing rates (10 percent - 80 percent missing rate). Experimental findings from 11 datasets support the efficacy of the suggested technique (on Promise and ISBSG10). The proposed method's performance is compared to that of other techniques (such as: Generative Adversarial Imputation Networks (GAIN), k-Nearest Neighbor imputation (kNNI), Multiple Imputation by Chained Equations (MICE), and Random Forest Imputation (MissForest)), demonstrating that our method outperforms others even with an 80% data missing rate, with producing the best value (low) on mean absolute error (MAE: 0.0839) and root mean square error (RMSE: 0.1061).

281

Authors: Asmaa A.Ghany, Ahmed A. Zaki Diab, Abo‐Hashima M. Elsayed, Yahia S. Mohamed, E. G. Shehata

Nowadays, great attention has been paid to wind energy conversion systems (WECS), particularly high-power stations equipped with high-power electronic converters. Direct-driven permanent magnet synchronous generator (PMSG) with three-level converters is the preferred type for such wind energy systems. To regulate the operation of the generation system, a finite control set model predictive control (FCS-MPC) has a superior performance for power converters control techniques due to tight control dynamics, simple design, multi-variables control, no modulation control stage, and only a discrete-time model is needed. But on the contrary, variable switching frequency output waveforms is the main drawback. The main objective of the paper is to design a controller of a three-level neutral point clamped (3L-NPC) converter with a novel fixed switching frequency for regulating the stator current of PMSG and ensure the balance of the DC-link capacitors voltages. In addition, a low voltage ride-through (LVRT) control technique is provided for the grid side converter of the wind power system to improve the wind turbine system performance throughout the grid fault. The futured system has been demonstrated via simulation work under steady states, transient conditions, and different types of grid voltage faults. The comparative results between MMPC and classical FCS-MPC show the effectiveness of the proposed MMPC in enhancing the results and reducing the simulation execution time and the computational effort associated with the calculation of the duty cycle of the converters also the total harmonic distortion (THD) has reduced by 31.34% lower than classical FCS-MPC and obtaining a constant switching frequency with a reduction in execution time by 51.17%. In addition, the comparative results of WECS during symmetrical and asymmetrical grid faults with and without LVRT controller show the effectiveness of LVRT controller in supporting the grid during faults and preventing the dc capacitor overvoltage.

304

Authors: Andi Kurniawan Nugroho, Dinar Mutiara Kusumo Nugraheni, Terawan Agus Putranto, I Ketut Eddy Purnama, Mauridhi Hery Purnomo

Stroke is a condition in which the blood supply to the brain is cut off. This occurs due to the rupture of a blood vessel. In addition, this can lead to fatal conditions for the patient where causes damages in several areas of the patients’ brain. The examination by health workers is generally carried out to receive an image of the part of the patient’s brain that has a stroke disorder. Commonly, stroke detection is done using magnetic resonance imaging (MRI). The purpose of this study is to use convolutional neural network (CNN) as a method for classifying MRI stroke images. The data used in this study is the DWI stroke MRI image dataset 5,226 images. The data consisted with 1,742 normal images, 1,742 intra cerebral hemorrhage (ICH) images, and 1,742 acute ischemic images, which are grouped into 3 parts, training, validation, and testing. The images produced by the MRI are labeled manually by the doctor to obtain certain types of strokes. This study employed the multi optimizer which is Root Mean Squared Propagation (RMSprop), adaptive moment estimation (Adam), and stochastic gradient descent (SGD). This study compared between the scenario original CNN model and the scenario hepta convolution layer neural network (HCL-NN) which proposed by this study. Both of the scenario of CNN tested using magnetic resonance –diffusion weighted (MR-DWI) images. Transfer learning in the CNN model (inside the CNN library) was tested with the author's data for performance testing. Then, the results of the performance trials that have been carried out earlier are compared with the results of the original CNN and HCL-NN. The experiment shows by using scenario HCL-NN display data training accuracy value 99.23 percent and data testing accuracy 97.40 percent. The both values are achieved with using RMSprop optimizer. Furthermore, this study also tested the values of precision, Recall and F1-scores. The scores for testing the HCL-NN scenario 97.43, 97.40 and 97.40 are higher compare to the other scenarios (original CNN) and other transfer learning (RESNET, VGG19 and mobilenet V2). As a summary of this study, the proposed HCL-NN performed better than other CNN scenarios for classifying strokes for MR-DWI images.

343

Authors: Ledya Novamizanti, Andriyan Bayu Suksmono, Donny Danudirdjo, Gelar Budiman

In medical applications, the slightest distortion in the patient's medical image cannot be tolerated, as such distortion can lead to misdiagnoses and misleading conclusions. The robust reversible watermarking technique has received considerable attention, as it allows the complete extraction of the embedded watermark signal and the comprehensive reconstruction of the masking signal. This paper proposes a robust reversible watermarking (RRW) scheme based on Stationary Wavelet Transform (SWT) and Multibit Spread Spectrum (MSS). The host image is broken down into several subbands using SWT. Then, the watermark is embedded into the subband diagonal detail coefficient of the host image using MSS. Finally, the watermarked subband is combined with other subbands using inverse SWT (ISWT) into a watermarked image. The embedded watermark is extracted on the receiving side, and the original medical image is precisely reconstructed without involving auxilary information. By the experimental results, the proposed robust reversible watermarking technique can restore the watermark and rebuild the host medical image perfectly without any attack. The watermarked images produced by the proposed reversible data hiding technique have better visual quality with a peak signal-to-noise ratio above 41 dB. In addition, the proposed RRW scheme is robust to various attacks such as compression, noise addition, sharpening, and image enhancement.

366

Authors: Robert Marco, Sharifah Sakinah Syed Ahmad, Sabrina Ahmad

The fundamental challenge in developing a prediction model for software effort estimation (SEE) is related to the availability of inadequate public data or the small amount of information contained in the data. As a result, because the information contained in the data is small, it can be challenging to make accurate estimates with insufficient SEE data. Data augmentation techniques, and synthetic data have been used successfully to overcome problems with limited data sets. In this study, conditional variational autoencoder (CVAE) and an inverse normalization transformation (INT) were investigated as methods for data augmentation and synthetic data generation. Eleven data sets in the field of software engineering (such as the PROMISE repository and ISBSG) that will be used as case studies. Overall, the CVAE-INT model was used for the augmented data set (synthetic data). Based on the Mann-Whitney test, it shows that our method provides a significant level with a mean p-value greater than 0.90 in the data set. Our model yields lower mean absolute error (MAE) and root mean squared error (RMSE) values. Increased mean error for the datasets Albercht (0.0269; 0.0842), China (0.0444; 0.1079), Cocomo81 (0.0544; 0.1155), Desharnais (0.0702; 0.1258), IFPUG (0.0225; 0.0448), ISBSG10 (0.0996; 0.1836), Kemerer (0.0776; 0.1457), Kitchenham (0.0001; 0.0010), Maxwell (0.0746; 0.1230), Nasa93 (0.0980; 0.1488), and UCP (0.0427; 0.0899). Furthermore, we assessed the influence of synthetic data using five machine learning prediction approaches (such as CART, k-nearest neighbors (kNN), Support Vector Regression (SVR), MultiLayer Perceptron (MLP), and Random Forest (RF)). The results show that our method can provide data augmentation techniques for the transformation of variance data that can produce synthetic data that has the same distribution as real data. In addition, this study shows that the synthetic data produced has a significant effect on increasing the accuracy of the five predictor methods in the machine method.

397

Authors: Anggun Fitrian Isnawati, Mas Aly Afandi

The development of wireless technology, especially small cell communication systems, is now very flexible to be developed. As a form of network densification to improve the performance of the macrocell network, the combination with smallcell, in this case the femtocell network, forms a heterogeneous networks (Hetnets). However, with many networks running concurrently, a combination network between macrocell and smallcell networks, interference is unavoidable. To overcome this problem, it can be solved by applying the power control technique independently by the user. One of the independent power control methods is using a game theory approach. The use of game theory in power control or Game-Theoretical Power Control is often also referred to as Power Control Game (PCG). By determining the appropriate utility function, optimal power is obtained each time using the power update iteration process. The study addresses the issue of achieving the target SINR for both femto and macro users on heterogeneous networks by proposing a PCG that is capable of exceeding the target SINR upon convergence, implying improved communication quality. Based on the results of the feasibility and convergence tests, the proposed system has been proven to meet the requirements for existence and uniqueness, which are the requirements for meeting the feasibility and convergence of the system. The results of the performance comparison also show that when reaching convergence, both femtocell and macrocell users using the Proposed PCG method are able to exceed the specified target of signal to interference and noise ratio (SINR) in each network type. Meanwhile, using the Koskie Gajic (KG) and Al Gumaei (AG) methods, both femtocell and macrocell users could not reach the target SINR. So it can be concluded that in terms of achieving the target SINR, the Proposed PCG method is better than the other two methods.

416

Authors: Putra Yudha Pranata, Wahyono

Illegal parking is a violation that often occurs in urban areas. Supervision is conducted in places where parking is prohibited to overcome this problem. Manual monitoring requires high staff performance and costs. Therefore, a video-based illegal parking detection is proposed. Previous studies have several weaknesses in video-based illegal parking detection, especially those that use background modeling techniques. Examples of drawbacks include changes in illumination and imperfect segmentation caused by noise, leading to false-positive errors. This study aims to overcome the problem of frequently occurring false-positive errors by using the improved visual background extractor (I-ViBe). This method develops the ViBe approach to detect illegal parking by modifying the background model update mechanism with the static region extraction and vehicle verification processes and integrating tracking processes. Experimental results show that the values of precision, recall, and f-measure are 100%, 60%, and 75% respectively, which means that the proposed system has overcome all false-positive problems.

441

Authors: Najib Ababssi, El alami Semma, Azeddine Loulijat

Voltage instability and voltage collapse are the serious problems that can occur due to reactive power deficits caused by increased load or contingencies. Detecting potential voltage collapse in power systems is essential to maintain voltage stability during high demand. The stability of power systems is an important issue in the planning and operation of these systems. This paper determined the optimal location and size of a FACT STATCOM device for improving the static voltage stability margin of a transmission system. The study network is the IEE New-England transmission network. The problem has been formulated as a multi-criteria optimisation with the objectives of maximising load margin, minimising power losses and minimising voltage deviation. The objective function of the problem is adjusted using the analysis and optimisation method (CPF). The appropriate values and placement for STATCOMs are found using the CPF method based on the objectives below. The proposed method is verified using a simulation test on the IEEE-100 kV network which is part of the IEEE- 39 bus New England power system. The simulation results showed the efficiency of the CPF for the nominal values and the optimal location of the STATCOM. The results showed that the improvement of the voltage stability margin, the voltage profile of IEEE-100 kV is increased and the power losses are reduced. Finally, STATCOM ensures the overall stability of the transport network.

467

Authors: Shaik Imam Saheb, Khaleel Ur Rahman Khan, C. Shoba Bindu

In the dense sensing environment, deployment of multiple sensor nodes is included in the WSNs. Based on the sensor deployment scheme, the WSNs’ effectiveness has been provided up to the extent that relied on the network coverage. Some of the major objectives relevant to the sensor nodes' deployment that are required to be satisfied are the network connectivity, number of deployed sensors, lifetime, overall consumption of energy, and area coverage. The deployment of sensor nodes has been carried out based on a constrained problem of multi-objective (MO) that includes the objective of determining the sensor node arrangement for improving the coverage area, decreasing the energy consumption, improving the network lifetime, and network connectivity between SINK and node for accurate data transmission. Based on Bat Algorithm (BA), the node deployment with the proposed technique is discussed for improving the sensor nodes’ coverage rate. However, each bat is determined the solution based on the sensor nodes’ deployment. Further, the bat algorithm (BA) has been improved to enhance the sensor nodes' coverage rate. According to the value of fitness function, the bat movement is chosen in the enhanced bat algorithm. The node deployment using the improved bat algorithm have been compared with RSSI based node deployment method, called as hybrid DP-HOP and particle swarm optimization approach CPSO. Compared with Hybrid DP-Hop & CPSO techniques, the proposed node deployment technique achieved 60% throughput gain, improves PDR by 30% and reduce the end to end delay by 40% and optimized energy consumption.

488

Authors: Firas Muneam Bachay, Mohammed Hasan Abdulameer

Palmprint authentication has received a lot of attention as one of the most prevalent biometric methods. A palmprint is a portion of the palm’s surface that has special characteristics that could be used for authentication. Getting the most valuable features out of a palmprint, on the other hand, is a major challenge. Another challenge is coming up with an efficient strategy to authentication that uses fewer images, especially with approaches that require a high number of images in the training phase, which is a major issue. The majority of recently developed approaches rely on primary lines, wrinkles, and creases, which in some situations are insufficient to separate two people due to resemblance. Deep learning methods have recently been viewed as a critical component for extracting deep features such as texture features in these types of tasks. We concentrated on the palmprint authentication challenge in this work by creating a hybrid model called AE+CNN, which is based on the autoencoder (AE) model and a convolutional neural network (CNN) model. The proposed model comprises three phases: pre-processing, region of interest extraction (ROI), and feature extraction and matching using hybrid AE+CNN. The experiments used the COEP palmprint database, which has a limited number of palmprint images, posing a significant challenge for deep learning models that require a large number of images for training. The F1-score and the accuracy metric were both employed in the evaluation. with a score of 97.85 % for accuracy and 96.81 % for F1-score. Gradient-weighted class activation mapping (Grad-CAM) was also applied to figure out which parts of the palmprint are the most discriminative for class classification.

514

Authors: Moch Deny Pratama, Riyanarto Sarno, Rachmad Abdullah

The Hotel website always provide sentiment reviews of the service, then users can easily choose the desired facility according to the best advice results from the previous user. In this study, the sentiment of the reviews are determined based on five hotel aspects, those are: food, service, location, comfort and cleanliness. Every data hotel reviews is pre-processed to produce a term list. Extract related hidden topics using Latent Dirichlet Allocation (LDA). The extracted documents are categorized by matching for similarity to determine the term documents into five hotel aspects. Each term document is expanded using synonyms to increase the similarity value to LDA with 100% expanded document using Cosine Similarity produces the highest performance value of 0.856. Labeling the sentiment of each review based on the aspect and sentiment classification using the Support Vector Machine method gets an average value of 0.940 for all fifth aspects. The ranking of the most important aspects shows that users talk a lot about the cleanliness aspect, having the highest positive sentiment value of 39.450 and having a negative sentiment of 3.861, indicating that each review sentiment is influenced by certain aspects.

536

Authors: Rajeswarappa Govardanagiri, Vasundra Sanjeevulu

In wireless senor networks (WSNs), the process of handling the sensor nodes’ restricted energy resources from the dimensions of data routing, collection and aggregation is highly challenging. These potential challenges of WSNs demand efficient energy stabilization in the network for prolonged lifetime that attributes towards improved rate of reliable data dissemination. The maximization of network lifetime is essential for attaining success in data delivery, energy conservation and scalability. Clustering schemes provide low overhead and efficiently allocates the resources for ultimate improvement in energy consumptions and minimize interfaces among the sensor nodes. Swarm intelligent meta-heuristic clustering schemes provide optimal solution for this non-deterministic polynomial (NP)-complete problem of clustering. In this paper, Hybrid grasshopper and improved bat optimization algorithm (HGIBOA)-based cluster head selection scheme is proposed for enhancing lifetime expectancy by sustaining energy stability in WSNs. This HGIBOA utilized variable coefficient-based Levy flight for enhancing the exploration potentialities of GOA. It inherited the local searching operation of bat algorithm for establishing the balance between exploitation and exploration. It further included a random strategy for employing it over high quality population with the objective of improving the capability of exploitation. It also included the fitness function evaluation based on residual energy, distance between cluster head and base station, and distance between cluster head and cluster member nodes. The simulation results confirmed that this proposed HGIBOA with different number of sensor nodes sustained residual energy by 18.21%, improved throughput by 21.84%, prolonged network lifetime by 17.92% and maintained stability of 16.28%, better than the benchmarked Cuckoo search and PSO-based QoS-aware multipath routing protocol (CSPSO), clustering scheme using firefly and modified ABC (FMABCCS) and integrated GWO and WOA-based clustering strategy (GWWOA) approaches used for investigation.

554

Authors: Bethelli Pavani, Lavadya Nirmala Devi

Sensors in an internet of things (IoT) network are energy-consuming devices and they operate on batteries that have limited energy capacity. This issue impacts the network lifetime. One of the promising solutions for this problem is simultaneous wireless information and power transfer (SWIPT). In SWIPT, a receiver node harvest the energy by itself based on the quantity of RF signal. When the transmitted RF signal becomes weak, the receiver node not able to forward the information to the next node due to not sufficient harvested energy. It can reduce network performance. Here, we propose a new SWIPT mechanism called as hybrid SWIPT (H-SWIPT) to enhance the harvesting energy at which the receiver node not only depends upon the previous node's RF signal but also depends on the neighbor node's RF signal, sink broadcast energy, and co-channel interference. Furthermore, to minimize the total energy consumption of the path a new routing metric is introduced. Based on this, it will select the minimized energy cost path from source to destination. The network performance is evaluated in terms of energy cost and aggregative energy cost and compared with existing schemes: information transmission (IT) & power splitting protocol based SWIPT (SWIPT-PS). From the results, for varying node count, the average energy cost is observed as 5.9mW, 5.433mW, and 4.7mW for IT, SWIPT-PS &H-SWIPT respectively.

576

Authors: Thaair Ameen, Ali Adil Ali

To provide more accurate, diverse, and interpretable recommendations, one must go beyond modeling user-movie interactions and consider user social correlation graphs and movie-movie correlation graphs. However, most previous research has only considered correlations between user preferences and social correlations, while ignoring the correlation between movies. In this paper, we describe a model for movie recommendations that include a representation of the user's preference in movies based on graph attention networks and multi correlations as in the following graphs. 1) user-movie graphs, which include user-movie interactions, as well as users’ opinions on movies, 2) user social correlation graphs, which contain social correlations among users, and 3) movie-movie correlated graphs, which contain the correlation among the movies themselves. Extensive experiments are conducted on two real-world (Netflix and Movie Lens) datasets to verify the efficiency and stability of the proposed model.

601

Authors: Aicha El filali, Aissam Jadli, El Habib Ben Lahmer, Sanaa El filali

Demand forecasting is an indispensable key to planning and achieving objectives, as it feeds all the processes in the company’s supply chain. Forecasting is a difficult task that requires a lot of analysis using powerful complex mathematical equations to build a model capable of predicting customer behavior according to the market variability involved. Therefore, the objective of this paper is to build a new hybrid deep learning method named (LSTM-GRU) based on sequential learning using long short term memory (LSTM) and gated recurrent units (GRU). The proposed method builds automatically the best prediction model by considering various combinations of LSTM and GRU hyperparameters using the gridsearch technique. It can predict highly fluctuating demand data while taking into consideration the non-linear characteristics of time series. The new method’s performance was compared to several deep learning models, namely single layer LSTM, single layer GRU, stacked LSTM, and stacked GRU, using real electrical product data from an industrial Moroccan company. The evaluation of the experimental results with mean absolute error (MAE) and root mean squared error (RMSE) methods reveal that the predictions produced with the new model are the most accurate with the lowest error rates MAE= 237682.56 and RMSE= 366633.28 respectively.

12

Authors: Mahesh Boddu, Soumitra Kumar Mandal

This article presents an efficient hardware architecture of lossless image compression mechanism using colour filter array (CFA) for wireless camera networks. Recently, Quantum-dot cellular automata (QCA) technology has been widely using in the field of VLSI, thus the proposed compressor is developed using QCA technology to mitigate the area, and power as compared to standard CMOS technology. In addition, an improved and extended Golomb-Rice entropy coder (IEGREC) is proposed to reduce the memory requirement, and computational complexity. The IEGREC approach eliminates the requirement of context module, which is a major component in lossless image compressor architectures and its memory to lessen the hardware resource utilization. Further, to maintain the pixel connectivity and higher compression ratio (CR), the proposed architecture utilizes the adaptive Golomb-Rice (GR) parameter prediction and control module. Finally, packer module is used to maintain the flow of output compressed bit stream. The extensive simulation results show that proposed QCA-IEGREC method performs superior as compared to state-of-art approaches in terms of lesser area as 3700 gate count, and reduced power of 1.02 mW, and even image quality statistics such as 18.78dB of peak signal-to-noise ratio (PSNR), 152.3 of figure-of-merit (FOM), and 29.3 of CR.

36

Authors: Omar Abdullah Murshed Farhan Alnaggar, Basavaraj Ningappa Jagadale, Swaroopa Hebbar Narayan

Early detection of the brain tumors can help in providing sufficient treatment to completely cure the disease. Machine Learning (ML) and Deep Learning (DL) algorithms are utilized predominantly in recent years for the tumor detection process from the brain Magnetic Resonance Imaging (MRI). In this paper, an effective tumor detection framework is proposed by utilizing a hybrid segmentation algorithm and a new hyper-parameter optimized Convolutional Neural Networks (CNN) based classifier using Chimp Optimization Algorithm (COA). The framework includes pre-processing, segmentation, feature extraction and classification stages. The pre-processing stage performs the denoising using wavelet filter and image enhancement using adaptive histogram equalization. Then the Boosted Crossbred Random Forests (BCRF) is used to segment the regions of interest to identify skull, tumor and lesions. The features are extracted using the Grey-Level Co-occurrence Matrix (GLCM) and Gabor filter. Finally, the tumor classification is achieved using the COA-CNN. The COA-CNN is developed by utilizing the COA to tune the hyper-parameters of CNN to obtain optimal CNN architecture. Experimental evaluation was performed on a dataset of 3264 MRI brain images containing normal and tumor images. No tumor, Glioma, Meningioma, and Pituitary tumor are classes of the MRI images which are correctly classified by the proposed BCRF and COA-CNN based detection model with a testing accuracy of 95.18% and reduced processing time. The results indicate the efficacy of the proposed method in classifying brain tumors for assisting physicians in early tumor diagnosis and treatments.

57

Authors: Fikri Budiman, Pulung Nurtantio Andono, De Rosal Ignatius Moses Setiadi

This research proposes an encryption method for images based on dual chaos systems and dual hash functions. SHA-256 and SHA-512 are hash functions chosen to process plain images and private keys. The purpose of using hash functions on plain and key images is to increase encryption resistance against differential attacks and perform local encryption in each image zone. The proposed method consists of two stages of encryption, the first involves dual hash functions and confusion with a chaotic system by performing encryption based on zoning and rotation of the image. The second stage is a diffuse process using a logistic map. The proposed method is proven to be strong against various attacks that have been tested with various measuring tools such as entropy, histogram analysis, chi-square, number of changing pixel rate (NPCR), unified averaged changed intensity (UACI), and the avalanche effect (AE). This method also proved to work better than the state-of-the-art method in this research, significantly based on entropy, UACI, and NPCR.

79

Authors: Nataraj Kalaivani, Raman Beena

Heterogeneous Cross-Project Defect Prediction (HCPDP) predicts the defects by incorporating the project datasets with different distribution and metrics. However, the class imbalance problem and shallow feature learning of classifiers reduce the overall performance. This paper presents an HCPDP using Improved Synthetic Minority Oversampling Technique (ISMOTE) and hybrid deep learning classifier of Golden Eagle Optimized Siamese Neural Networks (GEO-SNN). Initially, Peters filter removes irrelevant instances in source-target dataset based on heterogeneous metrics. ISMOTE, enhanced through fuzzy mutual information based KNN attribute weights assignment, is applied solve the class imbalance problem. Features are scaled using Z-Score standardization and metric matching by Spearman's Rank Correlation (SRC). Finally, GEO-SNN, developed by SNN parameter optimization using GEO, performs deep semantic feature learning for defect prediction. Experiments using benchmark datasets showed that the proposed ISMOTE and GEO-SNN based HCPDP technique has provided 99% defect prediction accuracy and reduced processing time by 20%than the state-of-the-art methods.

99

Authors: Sudhakar Karna Narayana, Naveen Thimmahanumaiah Hosur

Wireless Mesh Networks (WMNs) are considered as an important structure for the next generation wireless networks that have numerous nodes organized in the mesh topology. In WMN, the data packets are forwarded through the multi-hop model. Nowadays, the combination of mesh clients with the Internet of Things (IoT) is gaining substantial importance for connecting numerous machines and it is used to acquire faster coverage. Moreover, the nodes in the WMN are susceptible to the malicious nodes which transmit the compromised and manipulated data to the destination. In this research, the Priority based Trust Efficient Routing using Ant Colony Optimization (PTER-ACO) is proposed to achieve data privacy and reliable routing over the WMN. Subsequently, Advanced Encryption Standard (AES) and Rivest Cipher 6 (RC6) are used to provide added security to the data. The PTER-ACO is analyzed by means of energy efficiency, network throughput, Packet Loss Rate (PLR), computational overhead, and latency. The existing methods such as Improved version of the Dijkstra Algorithm (IDA), Round Trip Time (RTT) based detection and Robust and Trusted Scheme (RTS) are used to evaluate the PTER-ACO, against these methods. The PLR of the PTER-ACO method is 21 % for 10 malicious nodes, which is less when compared to the IDA, RTT and RTS.

116

Authors: Madha Bramarambika

The MRI is assisted by doctors to evaluate the tumors that help them for planning the required treatment. The physicians are dependent on the medical MRI diagnosis but that required lots of effort in finding out the tumor regions. The existing models speed up the scanning process using the MRI technique that reduced the burdens from radiologists but showed abnormality due to the presence of outliers when extracting hyperparameters. The proposed Hybrid GLCM-LDTP-Le-Net Feature extraction technique is developed by combining the Grey level covariance Matrix (GLCM), Local Direction Ternary Pattern (LDTP) and Le-Net features. The feature extraction technique results with hybrid parameters, which are applied to the Bidirectional Long Short Term Memory (Bi-LSTM) model to classify the brain MRI as a Malignant or Benign. The proposed hybrid feature extraction increases the accuracy of learned models by extracting the combined features from the input data. The proposed hybrid feature extraction obtained an accuracy of 97.88 %, better when compared with the existing CNN-based models' methods that obtained accuracy of 91%.

135

Authors: Agus Subhan Akbar, Chastine Fatichah, Nanik Suciati

Many studies have been carried out to segmentation brain tumors on 3D Magnetic Resonance Imaging (MRI) images with 3D or 2D approaches. The 3D approach pays attention to the interrelationships between slices in a 3D image. However, this requires high resources, while the 2D approach requires lower resources but ignores the voxel relationship in 3D space. The 2.5D approach seeks to combine the lightness of the 2D approach and the voxel interconnection of the 3D approach. This article proposes SDA-UNet2.5D, a shallow UNet 2.5D architecture that pays attention to the interconnectedness of 3D images by involving five slices to get one slice of segmentation prediction results. The architecture is trained using the Brain Tumor Segmentation (BraTS) 2018, 2019, and 2020 datasets. Compared to other architectures, this proposed architecture has a high segmentation speed with 4.05-4.24 seconds to segment one patient data. Online validation resulted in superior average dice performance of 75.70, 88.82, 77.33 for the BraTS 2018, 71.29, 88.00, 76.55 for the BraTS 2019, and 70.80, 87.95, 75.89 for the BraTS 2020 validation datasets in the areas of Enhanced Tumor (ET), Whole Tumor (WT), and Tumor Core (TC).

163

Authors: Arun Prasath Govindan, Annapurani Kumarappan

Hand gestures and voice inputs have been measured as the vital communication component for the past few decades. Here, deep learning-based Reversible Convolutional Neural Network (Rev-CNN) is explicitly modelled to predict gesture-based sign language. Similarly, this work concentrates on modelling a reversible model to identify the voice gesture into sign language. It shows reversible representation by attaining superior accuracy with a lesser amount of model parameters and various CNN architecture. Here, the efficiency of the reversible model is evaluated with the prevailing G-CNN, VGG-11/16 model over the testing and training environment. Here, two diverse datasets like ROBITA Indian Sign Language Gesture Database and the standard voice-input dataset, is considered for evaluation purpose. The highest prediction accuracy of 94.38 % and 97.89 % is attained using the proposed reversible CNN model over the other approaches like GCNN, VGG-11 and VGG-16 model. The experimental outcomes and metrics like loss function, error rate and execution time are measured and compared with different methods like GCNN, VGG-11/16. Additionally, other efficiency metrics are utilized to determine the efficiency of the anticipated model. The model outperforms the existing approaches by categorizing the gestures with reduced error rate. The prediction accuracy of the reversible CNN (dataset 1) is 95.38 % and for dataset 2 is 96.69%. Similarly, the execution time is 5.5 minutes.

190

Authors: Santhosh Kumar Gorva, Latha Channagiri Anandachar

In recent decades, the rapid growth of cloud computing has led to increasing concerns about the security and energy requirement of cloud data centers. To overcome the concerns of load balancing and data security, a new hybrid model is proposed in this article. Firstly, a Modified Particle Swarm Optimization (MPSO) technique is proposed for balancing the tasks between heavy-loaded Virtual Machine (VMs) and light-loaded VMs. An effective load balancing improves the performance and availability of website, database, application and other computing resources. In the MPSO, a linear decreasing inertia weight is included to achieve optimal solutions in both VM migrations and load balancing. Secondly, an Enhanced Elliptic Curve Cryptography (EECC) algorithm is proposed for effective data security. In the proposed EECC algorithm, a new pseudo-random key is combined with a public key to improve the security of cloud data centers. In this work, the effectiveness of the proposed MPSO-EECC model is validated in terms of Service Level Agreement (SLA), execution time, energy consumption, energy SLA violation, encryption, and decryption comparison time. As represented in the experimental section, the proposed MPSO technique almost reduced 30%-70% of energy consumption compared to the existing optimization techniques. Similarly, the proposed EECC algorithm reduced 10ms to 30ms of decryption comparison time related to the comparative cryptography algorithms.

213

Authors: Kawther Dawood Salman, Ekhlas Kadhum Hamza

Due to the rapid growth in mobile data traffic, academia and industry are considering Li-Fi (Light Fidelity) as an alternative to Wi-Fi (Wireless Fidelity). Li-Fi is a high-speed, two-way wireless network system that has several advantages over traditional radio frequency systems. To fully exploit the potential of Li-Fi systems, users must be provided with a seamless connection, which must be achieved by carefully studying user mobility. Nowadays, most wireless Li-Fi network applications focus their design on solving some unspecific user-location problems that may fully achieve some preferred results in the domain they serve. For example, locating an unknown user in an indoor environment is considered a kind of solution for maintaining the QoS (Quality of Service) and delivering the signal to the user without distraction. Where the main research problem lies in the signal interference, loss, and scattering in the Li-Fi network, it is a big problem because it reduces the network performance and coverage. Therefore, to solve this problem, this research investigates the locating of the mobile user within the Li-Fi equipped room to obtain the best possible coverage of the user's service. The aim of the research was divided into two stages. In the first stage, the method used in our work was presented by showing the triangulation method in simulating user location data (sensor simulation), the first stage was not affected by noise, as it serves as proof of the correctness of our work and depends in the second stage when it is under the influence the noise. In the second stage, the method of RSS - triangulation (Receiving Signal Strength -Triangulation) was adopted to simulate the user’s location data (a simulation of the sensor) and under the influence of noise and implemented on a deep learning algorithm to determine the accuracy of the user’s location and how to deal with noise. In the simulation results for the data in the first stage, our work was validated using the triangulation method in data simulation. The average error for the X-Axis was 2.17344 〖× 10〗^(-14) cm; Y-Axis was 6.44762 〖× 10〗^(-14) cm and Z-Axis 4.65690 〖× 10〗^(-11) cm the results obtained from the triangulation simulation were close to the real results. In the second stage, when adopting the RSS-Triangulation method under effect the noise, the average error was achieved on the X-axis 2.05612 〖×10〗^(-3 )cm, Y-Axis was 4.56249〖 ×10〗^(-3 )cm, and Z-Axis 5.10474 〖×10〗^(-3 )cm where The DNN (Deep Neural Network) showed how to deal with noise, the highest error was obtained on the X-axis 2.51535 cm, the Y-axis 2.25903 cm, and the Z-axis 4.22898 cm for an indoor environment of 5m x 5m x 3m.

243

Authors: Nirmala John, Varaprasad Janamala, Joseph Rodrigues

Due to numerous operational restrictions and economic purposes, optimal load management for energy balance in the smart grid (SG) is one of the compensating responsibilities. This research provides a novel multi-objective optimization technique for attaining energy balance in SG, with the goal of avoiding fines due to excessive upstream network power extraction beyond contractual demand. Due to a lack of capacity to create the whole optimization towards the global optimum after each run, optimal load control (OLC) is a prevalent challenge. Adaptive-TLBO, the most recent variation of Teaching Learning Based Optimization (TLBO), comprises both alterations during the exploitation and exploration phases (ATLBO). Because the ATLBO is used on a modified IEEE 33-bus system, the results obtained in this mode are extraordinary. The energy balance has improved in addition to the enhancement of the voltage profile and the reduction of distribution losses. As evidenced by comparisons with PSO, basic TLBO, backtracking search algorithm (BSA), and cuckoo search algorithms, the suggested ATLBO algorithm has precedence over any other proposed algorithm (CSA).

260

Authors: Anthony Anggrawan, Mayadi, Christofer Satria, Lalu Ganda Rady Putra

Providing scholarships to students is an important action in helping students succeed in their studies. The scholarship recipients are students who meet the specified criteria. However, it is not easy to decide which scholarship recipients are genuinely eligible to receive scholarships, especially if the selection process for prospective scholarship recipients is done manually. Many prospective scholarship recipients must be selected, and more than one criterion is required. That is why it is not surprising that awarding scholarships to selected candidates takes a long time and the accuracy of the results is dubious. It means there needs to be a system that can assist in choosing prospective students who meet the criteria for the best requirements as scholarship recipients. Therefore, the purpose of this research is to build an application system that can provide recommendations for eligible candidates for scholarship recipients based on consideration of the criteria possessed by prospective scholarship recipients. This research method is an experimental study using a combination of the Analytical Hierarchy Process (AHP) and the Multi-Objective Optimization Method by Ratio Analysis (Moora) method to rank scholarship recipients. The study results indicate that using an application system integrated into the database in recommending prospective scholarship recipients according to the desired conditions is more accurate using a combination of AHP and Moora methods (up to 94.07%) than using only one Moora method (which is only 89.62%). This means that the selection of scholarship recipients according to the desired qualifications using the AHP method for weighting and the Moora method for ranking is a combination of methods that have relatively more reliable accuracy.

287

Authors: Salwa Khalid Abdulateef

The image vectorization based on geometrical contour representation is an active research topic. It involves approximating the contour of the objects inside the image using geometrical definition or estimation. Typical approach of estimating the parameters of the geometrical model is fitting-based estimation. However, the noise that exists in the image causes degradation in the performance. In order to overcome this degradation, we propose integrating evolutionary based optimization. In this article, the design of the operators of the genetic optimization for improving the contour detection results of segments-based estimation of the contour is proposed. The operator includes both crossover and mutation. The evaluation shows that Structural Similarity Index Metrics (SSIM) measure has increased after applying it from 0.64 to 0.77 on UEC Food 100 Dataset and from 0.54 to 0.66 after applying it to UEC Food 256 Dataset.

307

Authors: Mays D. AL-Bayati, Duraid Y. Mohammed, Mohammad Sarfraz

Arrhythmia identification using electrocardiograms (ECGs) is a critical component of biomedical signal processing and pattern recognition. The classification of ECG arrhythmias is presented in this article using features extracted from the Extreme Value distributor of the probability density function (PDF), also training model built using the Alexnet architecture of a conventional neural network (CNN). A continuous wavelet transform (CWT) was used to convert the features space to a two- dimensional image. Additionally, a comparison of the two approaches was conducted. In the first case, we used CWT to convert ECG data to two-dimensional images. In the second case, features were extracted from PDF files and converted to the image domain using a CWT. With a learning rate of 0.001 and batch size of 250, the accuracy of tests was 98.67 %. The results indicated that the proposed method is more accurate than the conventional method when it comes to feature extraction.

329

Authors: Korawitch Kaiyawong, Keerati Chayakulkheeree

This paper proposes a mixed-integer particle swarm optimization (MIPSO) for coordinated optimal placement of energy storage system (ESS) and capacitor bank (CB). In the propose method, optimal ESS scheduling (OESSS) is solved by particle swarm optimization (PSO), as a subproblem, the optimal coordinated placement (COP) for ESS and CB, simultaneously. The distribution system annual loss minimization (DSALM) is used as the objectives of COP problem. The proposed method was tested with the IEEE 33-bus radial distribution test system. The results demonstrated that the proposed method is successful and robust in minimizing system losses, which loss saving of 35.12% when compare to the based case, which is the best solution among other existing methods.

348

Authors: Hayder M. A. Ghanimi, Shaymah Akram Yasear

The global pandemic (Covid-2019) has severely affected all aspects of our life and even changed the way we live and work. As the pandemic outspread, healthcare professionals need urgent interventions to control the harmful consequences. Encountering such a crisis makes them more prone to negative psychological ramifications in their work environment, making them unable to provide the proper support. Burnout is the most negative feeling increased among healthcare professionals while compacting the virus. One essential move to remedy the impacts of burnout is understanding its determinants and their causal relationships. This paper addresses the design of a computational (cognitive) agent model of burnout for healthcare professionals using a temporal-causal network model. Several determinants of burnout with their causal relationships were identified from the literature and formalised to construct the proposed cognitive agent model. In addition, different simulation experiments were implemented to obtain a clear insight into the causal relationships among burnout determinants and those experiments are exhibited similar behaviours to exiting literature. Furthermore, the developed model was evaluated using two different methods: mathematical analysis to prove its implementation was achieved right and automated logical verification to check several properties as shown in the literature to confirm that the suitable model was built. The obtained cognitive agent model could be helpful to develop a covid-19-aware analytics software agent that can monitor healthcare professionals' mental health.

371

Authors: Tossapol Kiatcharoenpol, Sakon Klongboonjit

A reliable and sensitive technique for predicting quality of a plastic work-piece produced in injection molding process is essential help for practicing engineers. A system based on the process parameters that can estimate both two prime characteristics, %volume shrinkage and warpage of work-piece before it produced is significantly beneficial. In this paper, a fast feed forward network, Hybrid Neural Network (HNN), is proposed to construct the predictive model for those two quality characteristics. The unique algorithm of HNN based on the optimization of the weights of each layer is changed to a linear problem by linearization of the sigmoid functions. As iteration procedure used in Backpropagation algorithm is eliminated, the network training time is significant reduced. With this fast convergence of using HNN, the intelligent predictive model for injection molding process that can learn online is possible for further study. To entitle the network to cater for various process parameter conditions, a knowledge base as training and testing data have to be generated on the experimental data in a comprehensive working range of a plastic injection molding process. Consequently, the experiments were performed in 256 conditions based on the combination of nine basic process parameters. The neural networks were trained and the architecture of networks was appropriately selected by benchmarking the Root Mean Square error (RMS). The results of the novel network, HNN, have shown the ability to accurately predict the percentage of volume shrinkage with the 1.02% and 4.87% error at training and testing stages, respectively and for warpage with the 3.76% and 2.47% error at training and testing stages, respectively. These accuracy results are similar to those of backpropagation neural network (BPNN), but HNN has shown the superior fast converging about 38.5% and 66.7% over than those of BPNN.

394

Authors: Malikhah Malikhah, Riyanarto Sarno, Sozo Inoue, M. Syauqi Hanif Ardani, Doni Putra Purbawa, Shoffi Izza Sabilla, Kelly Rossa Sungkono, Chastine Fatichah, Dwi Sunaryono, Arief Bakhtiar, Libriansyah, Cita RS. Prakoeswa, Damayanti Tinduh, Yetti Hernaningsih

Viral respiratory infections are the most common diseases suffered by all age groups worldwide. The gold standard for diagnosing viral respiratory infection is through the molecular method, but this diagnosis is expensive, requires sophisticated equipment, can only be performed by well-trained medical staff, and is painful. Volatile Organic Compounds (VOCs) are compounds released from the human body that can be a marker of disease and based on numerous studies it also contains VOCs. An electronic nose (E-nose) is a device that can be used to identify disease. This study proposes a new approach for the detection of viral respiratory infections through sweat from the armpit using an E-nose consisting of 5 semiconductor gases and a single-board computer. Several statistical parameters are used to obtain features and the detection algorithm used is Fully Connected Deep Network (FCDN). Several sizes of hidden layers were tested to obtain the best FCDN model. This study also proposes the selection of the best FCDN model which is a trade-off between complexity and accuracy, so that the model stored in E-nose is a model that not only has good accuracy but is also not too complex. The experimental results show that using 29 statistical parameters and 2 hidden layers generate the highest accuracy of 0.940 for the detection of 2 classes, namely positive and negative, with sensitivity and specificity of 0.967 and 0.915, respectively, where the best FCDN model has a total of 90,561 parameters.

414

Authors: Ravindar Mogili, G. Narsimha

Abnormal behaviour of the heart called arrhythmia can be recorded as an electrocardiogram (ECG) signal. ECG plays a vital role in the diagnosis of heart disease. Advances in machine learning allow the development of computer-aided diagnostic models to identify heart disease type. We have proposed a hybrid model with Convolution Neural Network (CNN) to auto extract features from ECG and use XGBoost to assess the type of arrhythmia. We tested our model to diagnosis eleven kinds of arrhythmia beats from the MIT-BIH arrhythmia database and obtained overall sensitivity of 92.61%, specificity of 99.85%, positive predictive value of 95.99% and accuracy of 99.84%. The robustness of the proposed model is further confirmed by classifying the arrhythmia beats into 5 classes according to the AAMI standard and comparing the results with the state-of-the-art methods. Attained overall Sensitivity of 94.36%, specificity of 99.44%, positive predicative value of 96.40% and Accuracy of 99.69% for 5 AAMI Classes. The results demonstrated that the proposed model could be used in the diagnosis of arrhythmia.

441

Authors: Rahmad Hidayat, Agus Harjoko, Aina Musdholifah

An image retrieval system is required to provide high accuracy in a short time. Combining various features will usually increase accuracy but also increase retrieval time. This study developed a CBIR (Content-Based Image Retrieval) method based on hierarchical clustering on low-level features. Low-level features consisting of color, texture, and shape are extracted and then clustered hierarchically. The resulting clusters are then validated to obtain their optimal number. In the retrieval process, the query image features are extracted and compared with the cluster centroid on each feature. The scores of query results on each feature are normalized, and then the normalized scores are weighted to get the total score. The experiment was carried out using three datasets, namely DIKE20, Corel-1k, and Corel-10k. Based on the experimental result, the proposed method shows better performance compared to the existing state-of-the-art method. On the Corel-1k and Corel-10k datasets, the proposed method obtained precision scores of 0.81 and 0.62, respectively.

464

Authors: Aicha El Filali, El Habib Ben Lahmer, Sanaa El Filali, Mohammed Kasbouya, Mohammed Amine Ajouary, Saadia Akantous

The covid 19 has caused a strong health and economic crisis, where the business environment is turning into a great uncertainty and customer demand has become more and more fluctuating. As a result, demand forecasting as well as the task of predictive analysis, holds a great attention in the supply chain, in order to meet the needs of customers, avoid any out of stock, and at the same time avoid a waste of resources. In this paper, we propose a deep learning method based on long-term memory multilayer networks (LSTM) for demand forecasting. Using the grid search method, our method has the ability to automatically select the most optimal forecasting model, considering different combinations of LSTM hyperparameters of a time series. The proposed model has shown strength in capturing the existing nonlinear features in time series data compared to some known time series forecasting methods derived from statistical and machine learning approaches, using historical sales data of a Moroccan pharmaceutical manufacturing company. These methods include exponential smoothing (ETS), autoregressive integrated moving average (ARIMA), recurrent neural network (RNN). The evaluation of the proposed method and the comparison methods was performed using the root mean square error (RMSE) and Symmetric mean absolute percentage error (SMAPE). The comparison of the test results showed that the proposed method is the best performing with RMSE of 4487.32 and SMAPE of 0.026 much better than those obtained by the other models.

494

Authors: Asha Kethaganahalli Hanumanthaiah, Manjunathswamy Byranahalli Eraiah

Multimodal biometric systems are a natural evolution of traditional biometric authentication systems with use of multiple biometric to enhance the security level. Presentation attacks in form of photos and replay videos are becoming a threat to the biometric authentication systems and it becomes necessary to prevent from these attacks for an enhanced security level. This work proposes a challenge response based multi modal biometric authentication resilient to presentation attack. The proposed system is designed for multi modal biometric involving face and iris biometrics with challenge in form of arbitrary emotion invoking image at a random position on the screen. The changes in region of interest around the Facial landmarks and distance of iris to Facial landmarks are captured as response. The response is then matched with expected response derived based on the position of arbitrary emotion invoking image on screen to detect presentation attacks. In addition the work also proposes a hybrid deep feature which provides an addition security in recognition process to ensure authentication failure for fake samples. The error rate in leakage of spoofs is very low in proposed solution (less than 1%) in different environments compared to existing works. The recognition accuracy of face is atleast 1% higher and atleast 2% higher for IRIS in proposed solution compared to existing works.

521

Authors: Arjun Singh Saud, Subarna Shakya

Although some studies employed technical indicators as input to machine learning models to forecast stock trading signals, there was a noticeable gap between how technical analysts and machine learning professionals used technical indicators. Based on this finding, this study suggested a know sure thing based machine learning (KST-ML) technique for anticipating stock trading signals and compared its results to KST-based trading and Buy-Hold strategies. The main idea behind the KST-ML strategy is to learn and then predict stock trading signals from the relationship between KST indicators such that more accurate predictions can be made. The strategies were assessed based on their annual rate of return (ARR), Sharpe ratio (SR), and percentage of profitable trades executed. In addition, the proposed strategy's performance was compared to that of several intelligent stock trading strategies proposed in the literature. The proposed method clearly outperformed the other two strategies in terms of all three evaluation measures. With a 5.6 SR value, the strategy generated a 67.73% ARR and made 79.38% profitable trades. The results were much better than the results from the KST-based and the Buy-Hold strategies. Furthermore, we found that the annual returns generated by the KST-ML approach were significantly higher than those generated by other intelligent techniques reported in the literature.

543

Authors: Ahmed H. Mohammed, Ahmed Kareem Shibeeb, Mohammed Hussein Ahmed

Recently, the proliferation of the Internet of Things (IoT) services and applications has prompted several governments to deploy many cameras in critical sites, such as embassies, military institutions, and ministries. The images must be encrypted to protect data shared between IoT sensors/devices and embedded subsystems. Often, IoT devices are smaller and less powerful. A lot of traditional encryption methods are computationally inefficient. They require many rounds of coding, which takes up much space on a device. Despite this, this paper has developed a lightweight encryption algorithm based on chaos theory suitable for IoT devices with limited processing power. The confusion-diffusion structure is often divided into two independent components in chaotic image cryptosystems. However, it reduces the security of the cryptosystem since the independent design may be subjected to cryptanalysis individually. This paper presents an efficient chaotic image encryption algorithm based on a plaintext-associated approach. It incorporates confusion-diffusion operation to increase encryption reliability. The Zaslavsky map initial values are determined by the values and locations of an input image and random values to resist chosen-plaintext cryptanalysis. Furthermore, the proposed method uses a simultaneous confusion-diffusion process to resist any separate attack. The simulation and experimental analysis demonstrate that the proposed encryption algorithm has 0.3927 seconds as a fast encryption time. Moreover, it provides a high performance compared to several other chaotic-based image cryptosystems. as measured by the ‎histogram, entropy (‎7.9972‎‎3), ‎ pixel change rate (‎99.7194‎), unified average changing intensity (‎33.4635‎) within the critical interval, pixel ‎correlation, global and local entropy, CDR (ciphertext difference rate), and gray difference degree (GDD). It also has ‎higher security than other chaotic-based image cryptosystems.

563

Authors: Kiattisin Kanjanawanishkul

Eri silkworm pupae are well known as an alternative for a protein food source. At present, they are sold as canned food for long-term preservation. Therefore, good quality and size consistency are essential. To evaluate quality and size, an image-based grading method was proposed. The image of pupae was captured and then shape features (i.e., solidity, aspect ratio, and extent) and color features based on three color models (i.e., RGB, HSV, and L*a*b*) were extracted. Two neural networks with 10-fold cross validation were separately developed for shape evaluation and color evaluation. After misshapen and discolored pupae were identified by neural networks, remaining pupae were graded into five size numbers according to their length: very small, small, medium, large, very large. Experimental results showed that the average accuracies for shape evaluation and color evaluation were 99.64% and 99.58%, respectively. The accuracy for size evaluation was 94%. Therefore, the proposed grading method reduces sorting time and increases sorting accuracy.

584

Authors: Umar Umar, Faanzir Faanzir, Firdaus Firdaus, Indri Suryawati, Muhira Dzar Faraby, Adi Soeprijanto, Ontoseno Penangsang

The interconnection of single-phase households DG into the existing grid requires appropriate anticipation to ensure the quality and reliability of the existing system. This paper deals with the optimal placement and sizing of multi single-phase DG in unbalanced distribution systems for power loss reduction and voltage improvement while maintaining voltage unbalance and harmonic are in the acceptable limit. Optimal location and sizing of DG are determined simultaneously using the improvement version of Symbiotic Organisms Search (SOS), called Dual-Phase Parasitism SOS (DPP-SOS) with a crossover operator. DPP-SOS consists of original parasitism (OP) and random weight parasitism (RWP). DPP-SOS was programmed using MATLAB software and validated using 26 benchmark functions. To demonstrate the effectiveness of this method in reducing losses, the DPP-SOS is also tested using 7, and 25 bus test systems. Result show that DPP-SOS with a crossover operator has been successful in determining the location and rating of single-phase and three-phases DG simultaneously. DPP-SOS has an average convergence speed of 24.08% faster than the basic SOS. The simulation result also shows that multi single-phase DG is effective in reducing power loss, increasing voltage, and reducing voltage unbalance in the distribution system.

11

Authors: Widi Aribowo

The improvement of the economy country along with developments in each sector will be followed by technological progress. This has led to an increase in electricity demand in Indonesia every year. Electricity load forecasting has an important role in the energy management system. The purpose of electricity load forecasting is as an effort to balance between electricity demand and electricity supply. Power system management can be said to be good if the planning carried out will make a major contribution to the development of electric power systems. In this study, the Feed Forward Backpropagation Neural Network method (FFBNN) is optimized using the Teaching-Learning-Based Optimization Algorithm (TLBO) to predict long-term electricity load. The results were measured and validated using the Mean Absolute Percentage Error (MAPE) method. The performance of the proposed method will be compared with the actual data, feed forward backpropagation neural network (FFBNN) and cascade forward backpropagation neural network (CFBNN). It was found that the TLBO-FFBNN method had an average MAPE value of 0.00004936%. The Comparison results show the effectiveness of the proposed method. The proposed method shows that is adapted and has a good MAPE value.

33

Authors: Ahmad Alwarid, Agus Sihabuddin

Fuzzy Time Series models have been developed in various ways, one of which is determining the intervals. Several methods were applied to determine the intervals, but the performances are still not optimal. This paper proposes a new approach that uses a combination of Absolute Differences and K-means Clustering in the Fuzzy Time Series Markov Chain model. K-means Clustering made the interval more flexible and compact based on the data it clustered. In addition, Absolute Differences was used as the based method to define how many intervals to be made. This study used Taiwan Capitalization Weighted Stock Index (TAIEX) as benchmark data to evaluate the proposed method, which produced an average Mean Absolute Percentage Error (MAPE) value of 0.42, and an average Root Mean Squared Error (RMSE) value of 51.09 for the test data. The proposed method outperformed other compared researches at the end of this paper in terms of prediction accuracy.

55

Authors: Fathima Ghouse, Kavitha Paranjothi, Revathi Vaithiyanathan

Dysgraphia is a handwriting disorder and the classification of dysgraphia in children's handwritten images helps to identify the dysgraphia patient effectively and also prevents low self-esteem. Traditional methods of dysgraphia classification based on experts manually classify the dysgraphia that requires more cost and time. Few researches apply the machine learning and deep learning techniques for the classification of dysgraphia and existing models have the limitations of overfitting problems in the training process. In this research, the Non-Discrimination Regularization in Rotational Region Convolutional Neural Network (NDR-R2CNN) is proposed to improve the efficiency of dysgraphia classification. The balancing parameters are introduced in the loss function to balance the class in the training and eliminate the features to reduce the overfitting problem. The collected children's handwriting data were used to evaluate the performance of the proposed NDR-R2CNN model. The proposed NDR-R2CNN model has the advantages of effective feature analysis and non-discrimination word analysis. The NDR-R2CNN model has the accuracy of 98.2 % and the SMOTE+SVM method has 90.2 % accuracy in Dysgraphia classification. The result shows that the NDR-R2CNN model has 98.2 % accuracy and the existing CNN has the accuracy of 94.2 %.

75

Authors: Nagaratna Parameshwar Hegde, Sireesha Vikkurty, Gnyanee Kandukuri, Sriya Musunuru, Ganapatikrishna Parameshwar Hegde

The COVID-19 pandemic has essentially transformed the way of leading a life for millions of people across the world. As offices remained closed for months, employees expressed conflicting sentimental analysis on the work-from-home culture. People worldwide use social media platforms such as Twitter to talk about their daily lives made a trend in the online platform. This research study aims to gauge the public's sentiment on working from home/ remote locations during the COVID-19 pandemic by tracking their opinions on Twitter. The existing random forest model trained the data faster but failed to predict the results faster. Therefore, an ensemble model is proposed to predict an outcome using a distinct modeling algorithm. An ensemble classifier has been used for enhancing the performances using the base learning classifiers such as Naive Bayes (NB), Random Forest (RF), Support Vector Machine (SVM), Logistic Regression (LR) form an Ensemble classifier. The proposed ensemble model aggregates each base model for the prediction and results for the unseen data. These tokens are then passed to the Ensemble classifier that classifies the sentiments and assigns a polarity (positive, negative, neutral) to every tweet. The proposed Ensemble method improve the average prediction performance over any contributing member in the ensemble. The results obtained by the proposed Ensemble model reached accuracy of 97.47 % when compared to the existing models such as Deep LSTM, SVM model that obtained accuracy of 83 %, 84.46 %.

95

Authors: Lukman Hakim, Huipeng Zheng, Takio Kurita

The neighboring relationship of the pixels is fundamental information in the image. Utilizing neighboring pixel information provides an advantage over using only pixel-to-pixel information. This study presents a regularization term based on the differences of neighboring pixels. We define the differences of neighboring pixels by using the Graph Theory approach. We then propose an effective graph Laplacian regularization to enforce the differences between pixels as the nodes and differences between nodes as edges. In our scheme, Graph Laplacian constructs from the output of the convolutional neural network and ground-truth image. The generated differences matrices from the output and ground-truth are combined as a Laplacian regularization term used as the deep convolutional neural network's new objective function. Experiments show that our scheme successfully captures pixel neighbor relations and improves the performance of the convolutional neural network better than the baseline without a regularization term. Qualitative and quantitative results show that our developed regularizer proved to enhance the boundary structure on image super-resolution and image segmentation tasks, which is achieved Structural Similarity Index (SSIM) of 0.9604 and 0.8263 on Cartoon set and Manga109 datasets and area under the curve (AUC) of 0.9740 and 0.9561 on DRIVE and STARE datasets, respectively.

117

Authors: Jirasak Ponchua, Suchada Sitjongsataporn

Explosive growth and usage of internet while COVID-19 pandemic demands an access technology in our lifestyle that means the Internet of Things (IoT) and Passive Optical Networks (PONs) are increasingly being used in order to support the digital lifestyle. Mobile Internet allows us firstly to exchange the content of information and multimedia while on the move. Then, IoT makes it possible to connect the smart devices with the low latency. PONs have been suggested for providing the ultra-low latency for Quality of Service (QoS) applications such as the Tactile Internet (TI) that is the next evolution to enable real-time control of IoT. A one-millisecond round-trip delay is required to support the tactile internet. As stated on the improving bandwidth allocation for PONs and Passive Optical LAN (POLAN), we propose the FiWi-Dynamic Wavelength and Bandwidth Allocation (F-DWBA) algorithm to reduce the round-trip delay at lower than one-millisecond, which the proposed F-DWBA algorithm based on the PONs and WLAN 802.11b should have a maximum performance. The lowest round-trip delay will make the Fiber-Wireless (FiWi) system can work efficiently and support TI applications. Simulation setup are tested on the latency budget of communication for the TI system starting from the Mobile Unit (MU) through the access point (AP) connected to the Optical Network Unit (ONU) including with the Optical Line Terminal (OLT) to the server. Performance analysis is focused on three periods of the latency time at the optical access network, radio interface and MU interface. Simulation results show that the proposed F-DWBA algorithm has a better round-trip delay than the Gigabit-Passive Optical Network (G-PON) standard about 40 percentage and better than the conventional Dynamic Wavelength and Bandwidth Allocation (DWBA) algorithm about 33 percentage at the full working of the tactile internet system.

141

Authors: Gemilang Santiyuda, Retantyo Wardoyo, Afiahayati

The adaptive Lévy flower pollination algorithm (ALFPA) is a recent addition to variants of flower pollination algorithm (FPA). Despite its excellent performance on single objective problem instances, it has shown inefficiency in the number of function evaluation (FE). Inspired by this, this paper proposed two algorithms extending ALFPA to solve multiple objective problem while also improving FE efficiency. The first algorithm proposed is ALFPA with non-dominated sorting denoted as MO-ALFPA alongside two variants which are proposed to improve its FE efficiency denoted as MO-ALFPAT and MO-ALFPAB. The second proposed algorithm, MOEA/D-ALFPA, uses decomposition strategy instead of non-dominated sorting on MO-ALFPA. The empirical study on two benchmark suits shows that MO-ALFPAT and MOEA/D-ALFPA performed better than other methods. Furthermore, MO-ALFPAT and MOEA/D-ALFPA produced the best results in three benchmark instances, based on inverted generational distance indicator, and two and three best results based on the hypervolume indicator, respectively.

167

Authors: Alek Nur Fatman, Tohari Ahmad

Information has been crucial in supporting daily activities. Many tasks must be accomplished by transferring not only public but also private information. This situation has brought the necessity for protecting it during transmission. Some mechanisms introduced, like data hiding, are still challenging, considering the quality of the data and the secret size can be protected. This research presents a reversible data hiding method for digital video based on prediction error and histogram shifting to approach those problems. There are six kinds of prediction errors used, three are created from two adjacent frames, and three are from a single frame. The selection of the shift location is determined by the histogram location, which has the highest peak point. The histogram is obtained by calculating the frequency of the subtraction of each value from its predicted value. The PSNR calculated from the stego and the original videos has an average of 73.45 dB. This value demonstrates that the proposed method outperforms the previous research.

188

Authors: Ravi Kumar Sanapala, Sreenivasa Rao Duggirala

Wireless Sensor Networks (WSNs) contain thousands of small and inexpensive sensor nodes distributed in the specific area for collecting the desired information from the environment. However, the sensor nodes have restricted battery energy, hence the random deployment of sensors creates issues while managing the resources for effective data delivery over the network. Therefore, this research aims to develop an energy-efficient cluster-based WSN to minimize the energy consumption of the nodes. In this paper, the Low-Energy Adaptive Clustering Hierarchy (LEACH) algorithm is used for selecting the optimal Cluster Heads (CHs) from the network. Subsequently, the Improved Spider Monkey Optimization (ISMO) is used for creating the optimal routing through the CHs to the Base Station (BS) where the multiple fitness functions such as residual energy, distance, and routing traffic are considered to optimize the ISMO. Hence, the data communication between the intermediate CHs in hierarchical cluster-based architecture helps to minimize the energy consumption of the nodes. The performance of the proposed LEACH-ISMO method is analyzed using network lifetime, total energy consumption, normalized overhead, throughput, End-to-End Delay (EED) and Packet Delivery Ratio (PDR). The existing methods namely Fuzzy C-Means (FCM) with Artificial Bee Colony (ABC), Meta-Heuristic Ant Colony Optimization based Unequal Clustering (MHACO-UC) and Optimized Quality of Service-based Clustering and Multipath Routing Protocol (OQoS-CMRP) are used to evaluate the LEACH-ISMO method. The PDR of the LEACH-ISMO method is 96.7 % for 200s, which is high when compared to the FCM-ABC, MHACO-UC and OQoS-CMRP.

214

Authors: Gouramma Halidoddi, Rubini Pandu

Wireless Sensor Networks (WSNs) have gained huge attention in different areas due to their self-configurability, easy maintenance and scalability features. WSN is configured with more nodes to transfer the data inside the network. The sensor networks are usually classified by low bandwidth, limited energy, limited power supplies and small size memory which leads to a very demanding environment to provide security. In recent years, accomplishing the network security objective with low energy utilization is a major issue in WSN. In this paper, two-level security is proposed to secure data transmission over the WSN. First, the secure clustering and routing operation are performed by using the Multi-Objective Trust-based Bat Optimization Algorithm (MOTBOA). Second, the data security of the netw¬ork is improved by the Enhanced Homomorphic Cryptosystem (EHC). This paper aims to offer secure communication in WSN. It is achieved by using the EHC method for the operation of encryption and decryption over the data during communication among the nodes. The performance of the proposed MOTBOA-EHC method is evaluated in terms of detection rate, delay, throughput, routing load and Packet Delivery Ratio (PDR). The existing methods namely Trust based Dynamic Source Routing (TDSR), Monarch-Cat Swarm Optimization-based routing protocol and Secured Quality of Service aware Energy Efficient Routing (SQEER) are used to evaluate the performances of the MOTBOA-EHC method. The PDR of the MOTBOA-EHC method is 92% at 100 rounds that are high when compared to the TDSR, MCSO and SQEER.

235

Authors: Jeny Varghese, Jagannatha Sreenivasaiah

Multiple cloud computing services are collectively managed as federated cloud. The growth of users into this federated cloud for accessing a variety of services has introduced challenges on resource utilization and load imbalance that consumes larger waiting time of users. To address these two issues, this paper proposes data center (DC) clustering, virtual machine (VM) clustering, resource mapping and task scheduling. Initially the DCs are clustered using region based fuzzy possibilistic C-means clustering (R-FPCM) algorithm. DC clustering is performed by gathering the information of data dependency, million instructions per second (MIPS), latency, storage, bandwidth and counts of VM. Depending on DC clustering, the VMs are clustered by multi-objective density-based spatial clustering based on the estimated capacity and bandwidth. In order to balance load, Markov chain is applied to predict future load and balance accordingly. An intermediate broker is employed to monitor the VM resources and map based on the user’s task requirement. Service level agreement (SLA) is satisfied for every user by the broker and then fast 1 to N resource mapping algorithm is involved for mapping resources. This is followed by entropy-based monotonic scheduling algorithm that arranges user tasks in an order that is determined from task type, task size, task arrival time and deadline. The dynamic computation of entropy enables to improve scheduling with the current status of the system. The extended simulations of this proposed system are simulated in Cloudsim and the results are evaluated in terms of execution time, latency, resource utilization and response time and compared with the performance of Capacity based VM clustering algorithm. These simulation results show that the performance of the proposed system is much better than the existing approach.

262

Authors: Pulung Nurtantio Andono, Guruh Fajar Shidik, Dwi Puji Prabowo, Dewi Pergiwati, Ricardus Anggi Pramunendar

Indonesia is rich in flora and fauna diversity, but it is experiencing an increasing number of endangered populations. The public can prevent the expanding population threatened with extinction by knowing the types of fauna, especially birds threatened with extinction. This study proposes an automatic grouping method to recognize bird sound patterns in an open environment. This experiment used bird data from a public dataset and obtained bird sound patterns by recording from a distance far enough to make sounds without feeling disturbed freely. However, the sound of birds may contain noise and need data processing using YAMME to be carried out the noise, and birds’ voices can be separated. After that, the data was extracted using the combination of Mel Frequency Cepstral Coefficients (MFCC) and Gammatone Cepstral Coefficients (GTCC) methods also reduced the dimensions of the feature before completing the identification. The bird identification obtained provides an accuracy performance that reaches 78.11%, and these results are higher than other feature extraction methods that also apply dimensional reduction.

282

Authors: Yunifa Miftachul Arif, Hani Nurhayati, Supeno Mardi Susiki Nugroho, Mochamad Hariadi

Halal tourism is one of the tourism products that have the prospect of contributing to economic growth in Indonesia. Therefore, the government needs to increase promotions to increase tourist interest in halal tourism destinations in Indonesia. Game is one of the alternative promotional media that can also function as an educational medium for choosing halal tourism that is fun for potential tourists. This study proposes a recommendation system to support knowledge sources in the Indonesian halal tourism game. We use destinations ratings-based multi-criteria recommender system (MCRS) to generate recommendation rankings as a reference for visualizing halal travel for players as potential tourists. This method improves the ability of the conventional tourism recommendation system, which is generally based on a single criterion. In this study, we use eight destinations rating criteria as a reference for calculating the recommender system in the halal tourism game. Each of these criteria is a reference for tourists' assessment of halal tourist destinations in Indonesia. Next, we integrate the cosine-based similarity technique in MCRS to measure the level of similarity between players and previous tourist data sets. This research's testing phase uses the theme of halal tourism destinations in the Batu City area. The test results show that the number and composition of the tourism destinations item rating as input of the recommender system affect the accuracy, precision, recall, and F1 scores. Based on 40 experiments with different tourism destination item rating input configurations, it shows that the average value of accuracy = 0.60, precision = 0.67, recall = 0.64 and F1 score = 0.65.

305

Authors: Priyanka Rajanikanth, Kalli Satyanarayan Reddy

The Last decade the demand for wireless communication has increased massively. Wireless Sensor Networks (WSN) have turned out as a potential solution for various real-time applications namely environmental monitoring, health and military applications. These networks follow the random placement strategy hence, identifying the location of sensor nodes is a tedious task. Moreover, these networks suffer from various issues such as limited power resources. This work, focusses on the sensor node localization and network lifetime enhancement of Wireless Sensor Networks (WSN). In localization, security is an important issue, so a trust-based model to secure localization is investigated in this work. Further, energy aware clustering and Cluster Head (CH) selection has been undertaken to prolong the lifetime of the network. Finally, a data aggregation model which decreases the network energy depletion by discarding the redundant data is presented. The outcome of the model which is proposed has been assessed and expressed in the form of localization error, energy depletion and alive node. The comparative analysis shows that the localization error for varied anchor nodes is obtained as 1.51, 2.28, 2.52 and 1.25 using existing techniques DMA (Distance Mapping Algorithm), MDS-Map (Multidimensional Scaling), DV-Hop (Distance Vector-Hop) and Proposed Approach, respectively. Similarly, the average energy consumption is obtained as 1.02, 1.67, 1.90 and 0.82 using DMA (Distance Mapping Algorithm), MDS-Map (Multidimensional Scaling), DV-Hop (Distance Vector-Hop) and Proposed Hybrid Approach. The comparative analysis shows that proposed hybrid approach of localization, CH (Cluster Head) formation and aggregation attains better performance when compared with existing techniques in WSN(Wireless Sensor Networks).

329

Authors: Cucun Very Angkoso, Hapsari Peni Agustin Tjahyaningtijas, I Ketut Eddy Purnama, Mauridhi Hery Purnomo

One of the objectives of medical imaging research is to develop an effective and reliable clinical support tool for the early detection of various neurological conditions in patients such as Alzheimer's Disease (AD). Classification based on three-dimensional (3D) MRI (Magnetic-Resonance-Imaging) images have shown a good performance. However, solving 3D object classification as a 3D object using classical machine learning or deep learning is computationally high. 3D images from MRI can be reconstructed into three depth directions: axial, coronal, and sagittal. However, the multi-view-based method cannot explore the content of each image slice for all planes in 3D-MRI. Our study proposes a multiplane method by using three two-dimensional (2D) CNNs to capture discriminatory information on all available planes. Our method is a new fusion strategy to deal with the disadvantages of shape-based multi-view techniques. Our framework selects three slices: the three largest 3-planes to represent whole 3D-MRI objects as multi-2DCNN inputs. Extensive experiments have shown that the proposed method can outperform the 2DCNN method, which uses only one plane. More importantly, by taking full advantage of 2DCNN, we offer a new method for identifying 3D objects that is both easy and efficient. We called this new architecture Multiplane Convolutional Neural Network (Mp-CNN) since it used multiple inputs in its design. We evaluated the proposed method using T1-weighted structural MRI data consisting of 500 AD, 500 Mild Cognitive Impairment (MCI), and 500 Normal Cognition (NC) subjects collected from the MRI database of Alzheimer's Disease Neuroimaging Initiative (ADNI). From the performed experiments, the proposed method achieves 93% accuracy for multiclass AD-MCI-NC and good precision AD 93%, MCI 91%, and NC 95%, respectively. Our study also demonstrates that the proposed multiplane approach outperforms the single-plane approach.

350

Authors: Muhammad Abdillah, Ronald Cornelius Batubara, Nita Indriani Pertiwi, Herlambang Setiadi

Maximum Power Point Tracking (MPPT) is a technique developed to obtain maximum power transfer on solar panels. Various MPPT methods developed can overcome various conditions that affect the power transfer of solar panels, such as irradiation fluctuations and an increase in the solar panels surface temperature. To handle the problem fuzzy logic controller (FLC) is employed as the MPPT method. The input of FLC utilizes the error (E) and delta error (∆E) which is obtained from solar panel or photovoltaic (PV) output including voltage Vpv and active power Ppv. Then, the output of FLC is to determine the appropriate duty cycle (D) of the single-ended primary inductor converter (SEPIC) converter. This proposed scheme is to get better performance in terms of stable voltage output produced by SEPIC converter. The novelty of this paper is the combination of MPPT based on FLC or MPPT FLC that have less ripple and SEPIC that can produce stable voltage output. Hence, the ripple out the load can be reduced significantly by using this proposed method. From the simulation results, it is found that when irradiation conditions and temperatures vary, MPPT FLC can change the operating point of the solar panels close to MPP to obtain maximum power transfer. In terms of power ripple, MPPT FLC can reduce ripple (the total ripple is around 4.9 W) compared to conventional MPPT such as perturb and observer (P&O) (the total ripple is around 9.2 W). Ripple reduction occurs in both irradiation and temperature variations.

370

Authors: Shaymaa Mahmood Mahdi, Safanah Mudheher Raafat

In this paper, the design and application of robust interactive PID control for a medical robot system is presented. The aim is to solve the problem of precise position tracking required for human walking, using a simple type of control while taking into account the interactions of the systems’ input and outputs. The medical robot system can be interpreted as pendulum links to obtain a complete motion of all muscles. Two control actions are required to be applied for the two joints. The interactions of this multivariable system have been examined using the relative gain array (RGA). In this work, PID and Fuzzy PID controllers are implemented with interactions effects. In addition, two other non-conventional types of PID control structures have been considered for comparison, where the RGA cannot be applied. These are the two-degree PID (2DoFPID) and nonlinear PID (NPID) controllers. Simulation results show that in the case of not considering the interaction effects, the Fuzzy PID controller can provide an improvement of 44% as compared with conventional PID controller. While this improvement has been increased to 70% with the consideration of interaction effects. Meanwhile, NPID controller shows higher rise and settling times (almost more than 2 seconds for the settling time). While 2DoFPID controller shows difficulty in implementation due to its highly chattered control signals with higher overshoots in the transient response as compared with the results of the interactive Fuzzy PID controller. Finally, robustness against disturbances and system uncertainties has been tested with all the developed controllers. It has been concluded that the interactive Fuzzy PID controller achieves better performance in terms of less ISE, settling time, rise time, and overshoot.

396

Authors: Ahmed Aldhahab, Ibrahim Murdas

Conventional logic gates failed to process data at a high bit rate. Therefore, researchers began to study the design of these gates with optical technology, which is characterized by high bit rate data processing. The non-linear behavior is a drawback in semiconductor optical amplifier (SOA). This nonlinearity property of the SOA is used in this paper to implement the OR optical gates. Mach–Zander interferometer (MZI)-based structures are among the numerous of structures that are available to transform a modulation of phase into a modulation of intensity. These are widely used by electro-optic (EO), or thermo-optic (TO) impacts to create various applications like optical modulators, splitters, switches, etc. In this paper, the MZI is used as switches and the SOA is employed with cross-gain modulation (XGM) to implement the optical logic gate OR at a high bit rate of 250 Gbps. Several experimental results were performed on the proposed design of the OR gate until the optimum value of the injection current, which is 0.08 A, was obtained. This optimum value led to achieve the lowest BER, highest Quality factor, and lowest power consumption, which are 0, 60.7989, and 31.13×10-3, respectively. The experimental results of the proposed design outperformed those results obtained by other state-of-the-art designs.

414

Authors: Andi Kurniawan Nugroho, Terawan Agus Putranto, I Ketut Eddy Purnama, Mauridhi Hery Purnomo

Commonly, clinicans have problems for recognising brain stroke injury images. However, with the advantages of Information technology it is expected that will be a new method that can support the clinicans’ opinion for recognising the brain stroke injury for type of stroke (hemorrhagic, ischemic, and normal). Therefore, this study aim is to discovery a new model to classify hemorrhagic, ischemic and normal based on Diffusion Weighted (DW)- Magnetic Resonance (MR) images. This study argues by using Qual Convolutional Layers (QCL-CNN) which applied in CNN can classified type of stroke. For this study experiment, this research conducted two experiment to asses the performance of QCL-CNN. The first experiments partitioned the MR image dataset into 20 percent testing and 80 percent training sets. Then, the second testing performed ten-fold cross-validation on the image dataset. The result from the first experiment of the classification accuracies obtained 93.90 percent (1st dataset) and 94.96 percent (2nd dataset). As for the second experiment, the results shows that the classification accuracies obtained 95.91 percent ( 1st data set) and 97.31 percent ( 2nd data set). The data source for this study gained from Indonesian hospital and the web sources dataset public from Ischemic Stroke Lesion Segmentation (ISLES). This study also compared, the QCL-CNN model with other architecture model such as AlexNet, ResNet50, and VGG16. The result of the comparison experiment shows that QCL-CNN architectures model has excellent performance than the others model.

441

Authors: Annisa Kesy Garside, Ikhlasul Amallynda

This paper considers the permutation flow shop scheduling problem to minimize total earliness and tardiness. We initiated a metaheuristic algorithm, namely a crossbreed discrete artificial bee colony. We modifications to the essential artificial bee colony and propose two versions of the crossbreed discrete artificial bee colony. Taguchi experimental design is used to test the performance of this. Several computational experiments using Vallada’s benchmark instances have been carried out to prove the performance of the proposed algorithms. The statistical test results show that the proposed algorithms have the largest negative mean of BRE’s value, each of -0.1959 for CDABC_ver1 and -0.1954 for CDABC_ver2. It means that the proposed algorithms perform significantly better than other algorithms. The results of the Kruskal Wallis H test show that the proposed algorithm has better performance than some dispatching rules and heuristic algorithms. Furthermore, the proposed algorithms can deliver better results in less time than mathematical model solution.

464

Authors: Lubna A. Alnabi, Abbas K. Dhaher, Mohammed B. Essa

The power loss in electrical networks is considered unavoidable, because of its inherent resistance, for effective and economical operation; network loss should be reduced to maximum extent. There are two goals for this study, the first one is extracting the optimal size and location of distribution generators (DG) and the optimal reconfiguration with the aim of decreasing power loss and enhance voltage profile, while the second objective is to prove the success of the methods of Newton Raphson (NR) and guess sidle(GS) in the study and analysis of radial distribution networks. In order to reduce power loss, the genetic algorithm (GA) is used to address the network distribution problem. Software package MATPOWER-7 and MATLAB are utilized to simulate a 33-bus testing system for achieving four cases of various Distribution generator (DG) numbers. A comparison with another previous studies done and the conclusion indicated a positive impact on the efficiency of the system, this work support loss reduction and voltage improvement with the lowest Distribution generator (DG) size and prove that the increase of Distribution generator (DG) number not always can give better result though system cost increase, maintenance, along with the units’ distance for gas supplying increases. There are 4 cases with distinctive Distribution generator (DG) number applied in this paper and a compassion is done of power losses and voltage profile with references where case4 show better result with voltage profile 0.96 and power losses 59.09. As load flow method the Gauss-Seidel (GS) method used because it is a simple iterative method for solving n number of load flow equations by using iterative method. Where partial derivatives not require. And a Newton-Raphson (NR) method used where it is based on Taylor’s series and partial derivatives. The Newton-Raphson (NR) method advantages are less number of iterations needs to reach convergence, takes less computer time when computation cost is less and the convergence is definite. Also it is more accurate, and is insensitive to factors like slack bus selection, regulating transformers. and the number of iterations required in this method is almost independent of the system size. Genetic algorithm (GA) has a good ability to making a global search and explore the search space using their different kind of crossover. Also you can combine it with local search method to increase the exploitation search of the Genetic algorithm. In this paper the introduction part introduced where it is the general part of the paper then the research method proposed in section 3 with details then a Genetic algorithm proposed finally the result with conclusions are proposed.

490

Authors: Nam-Soo Kim

Recently, the non-orthogonal multiple access (NOMA) technique, which transmits multiple users in the same time-frequency block, has been focused on for future cellular networks. Conventional NOMA-based aerial cellular networks consider an unmanned aerial vehicle (UAV) as an aerial user, in which secure control information for UAV is important. In recent days, the deployment of urban air mobility (UAM) has been actively discussed for a new aerial transport service in an urban area. Since UAM conveys passengers, both the traffic and the control information for passengers and a vehicle are important. Therefore, this paper considers a NOMA-based aerial cellular network with a UAM as an aerial user and a ground user as a terrestrial user. And we derive closed-form outage probabilities of the forward and reverse links of UAM, and the Monet-Carlo simulation verifies the results. Further, the condition to maintain the balance between the forward and the reverse links for the identical quality of service (QoS) is derived. Numerical results show that the outage probability of the forward link decreases with the increase of the received signal-to-noise ratio (SNR). However, we noticed that the outage probability of the reverse link shows the error floor, which does not decrease with the received SNR and remains constant, caused by the interference from the ground user (GU). Also, it is shown that there is an average transmit power of UAM to conform the link balance regardless of strong or weak users.

509

Authors: Riyadh Rahef Nuiaa, Selvakumar Manickam, Ali Hakem Alsaeedi, Dhiah Eadan Jabor Al-Shammary

Distinguishing between network traffic activity, intrusion, and normal bahavour is very difficult and very time-consuming. An analyst has to review all the large and wide data to find the order of intrusion in the network connection. Therefore, a method that can detect network intrusion and reflect the current network traffic is required. In this paper, a new EDFC model (Evolving Dynamic Fuzzy clustering) algorithm is generated to improve and enhance the detection mechanism. The proposed model contains two parts: the cluster part and evolving part. This paper's main objective is to design and implement a novel and data density-based clustering scheme that provides high system performance and persistent grouping of data with high similarity and performance on big data for efficient machine learning. Compared to previous techniques, the suggested model's performance with several standard datasets such as the UNSW-NB15 dataset, KDD99 dataset, and NSLKDD dataset indicates a higher silhouette coefficient. In the EDFC model two metrics have been used to verify the quality of clusters, and these are the silhouette coefficient and the number of clusters. The EDFC model has achieved a high silhouette coefficient, and a low number of clusters compare to other models. Our focus is to enhance the detection mechanism for the DRDoS_DNS attacks. Therefore, The EDFC model has been implemented on the standard CICDDoS2019 dataset which contains DRDoS_DNS attacks and achieved a silhouette coefficient of 0.76 and a number of cluster 13.

530

Authors: Purba Daru Kusuma, Ratna Astuti Nugrahaeni

This work proposes a new flow-shop scheduling model that consists of several flow-shops. Every flow-shop acts as an independent entity, but there is a collaboration among them. Although the relation between flow-shops and their customers is exclusive, collaboration through production sharing is possible. This circumstance is different from most studies in flow-shop scheduling problems (FSP), for example, parallel or distributed, where all jobs come from a single point and are then distributed to the production resources. In the multiple independent flow-shops, each flow-shop has its own processing time and production cost. Through collaboration, efficiency can be achieved in the make-span and total cost aspects, which becomes the objective of this work. This model is developed by combining the first price sealed bid auction and cloud theory-based simulated annealing. The first price sealed bid auction is conducted to minimize the total production cost. Meanwhile, the cloud theory-based simulated annealing is conducted to minimize the make-span. This model is then compared with the existing non-dominated sorting genetic algorithm (NSGA II) based flow-shop scheduling models. The first existing model is a parallel flow-shop, while the second one is a collaborative flow-shop. The simulation result shows that the proposed model outperforms the existing models in the total cost aspect. The proposed model creates a 13 to 29 percent lower total cost than the NSGA II-based parallel flow-shop. Meanwhile, the proposed model creates a 16 to 28 percent higher make-span than the NSGA II-based parallel flow-shop.

549

Authors: Abdelghafour Herizi, Riyadh Rouabhi

The efficiency of a wind turbine depends primarily on the power of the wind, the power curve of the turbine and the ability of the generator to respond to fluctuations in the wind. This article then proposes a robust control strategy of the doubly-fed induction generator applied in the wind energy conversion system, the active and reactive powers, which are generated by the DFIG will be decoupled by the orientation of the stator flux. The proposed control is combined between sliding mode control and type-2 fuzzy logic, this technique is robust to the modeling uncertainties of the generator and the wind generator, and which makes it possible to optimize energy production (efficiency). Finally, the performance of the system was tested and compared by simulation in terms of follow-up of instructions and the robustness with respect to the parameter variations of the DFIG. The results obtained show the interest of such a control in this system.

575

Authors: Mala Sinnoor, Shanthi Kaliyil Janardhan

The Electrocardiogram signal (ECG) is highly susceptible to the electrical environment from where the motion artifacts were being recorded. The accurate representation of the ECG signal will necessitate removing the noise from various sources thereby resulting in a noise-free model. This present research work uses Multi scale Local Polynomial Transform (MLPT) technique that provides wavelet transform as an alternative when the MLPT model was non-equispaced. The proposed research combines two approaches such as MLPT and Ensemble Empirical Mode Decomposition (EEMD) forming a Hybrid Transform Model which is used for denoising in the research. The present research work considers white Gaussian noise and experimental results are based on the MIT-BIH Physionet Database. The results of the proposed hybrid MLPT-EEMD obtained better SNR values of 25.93 dB when compared to the existing Empirical Mode Decomposition technique (EMD) of 5.43dB, EMD with adaptive switching mean filter obtained 9.135 dB and S Transform based Time–Frequency Filtering Approach obtained 13.82 dB.

10

Authors: Farid Ali Mousa, Ibrahim Eldesouky Fattoh

The unequal representation of the various divisions existing in the data is one of the main data inconsistency issues. Data with an imbalanced distribution negatively influence the efficiency of most conventional classifiers. This paper introduces a new method for over-sampling the handling of imbalanced data sets. The method hybridize chicken swarm optimization and fuzzy logic (CSO-FL). The proposed model ensures that the synthetic samples generated reside in minority regions. The proposed hybrid CSO-FL applied on three datasets with different imbalanced ratios between 1.78 and 129.44. It demonstrated significant improvements in the efficiency of various classification techniques. During the classification process, we used KNN, DT, SVM and Naïve classifiers. The obtained results were very promising; the precision, sensitivity, and F_score values are enhanced in all classifiers. The values in one dataset improved with ratios >90 % in many classifiers because of the high imbalanced ratio in this dataset, while in the other two datasets, the measurement values enhanced with ratios from nearly 10% to 30%. The CSO-FL approach compared with three different approaches on the same datasets. The approaches are SMOTE algorithm, modified SMOTE, and TGT algorithm and proved to outperform their results.

30

Authors: Ethala Sandhya, Annapurani Kumarappan

The Internet of Things (IoT) has led to an era with the development of communication between smart devices used in various fields. Due to insufficient measures in the infrastructure of smart devices, it is prone to various attacks, which are launched by intruders during data transmission through the internet. Therefore, providing security measures for IoT systems is considered the highest priority. The present work ensures an Intrusion Detection System (IDS), which monitors malicious activities and helps in the successful functioning of IoT networks. Therefore, Spider Monkey Optimization with Random Forest (SMO-RF) algorithm is proposed to detect attacks in IoT environments. The NSL-KDD dataset is used where the input data is pre-processed and then classification is done using Random Forest (RF). The SMO will consider the features from where the decision for splitting or combining of the data taken by the female leader based on the 80-20 rule at the Global Leader Phase (GLP). Calculating the feature or variable importance with a Random Forest model shows which and all the features of the data are the most helpful for Classification is used. Thus, proposed SMO selects the best highest feature importance value for the classification of attacks using RF that overcomes the problem of over fitting. The results obtained from the proposed SMO-RF show the accuracy of 99.98 % better when compared with the existing SVM-parameter optimization and PSO-multi SVM techniques of 99.8% and 98 % respectively.

50

Authors: Halemirle Appaji Deepak, Thippeswamy Vijayakumar

In recent years, several methods have been established for the automatic detection of the characteristics of electrocardiogram (ECG) signals based on mathematical tools, among which the Fourier Transform, the Continuous Wavelet Transform (CWT), the Discrete Wavelet Transform (DWT) stand out among others. This type of procedure is important because it can be more efficiently detected if a certain patient has heart disease, such as an arrhythmia or ischemia. The primary goal of this paper is the development and implementation of a classification approach based on hybrid features i. e., Dual-Tree Complex Wavelet Transform (DTCWT), SVD-Entropy, Autoregressive modeling, and Multifractal analysis based feature extraction. To accomplish the better classification, the extracted features are further classified by Random Forest Classifier, K-Nearest Neighbors (KNN), and Bayesian Optimized-KNN classifiers utilizing the MIT-BIH database. Highest accuracy achieved in random forest classifier is 98.29 %.The results obtained show the feasibility and practical efficiency of the methodology as a tool to aid in the diagnosis of heart disease in hospital environments.

80

Authors: Kavita Avinash Patil, K. V. Mahendra Prashanth, A Ramalingaiah

The proposed work can be divided into two parts: first, remove the noise from the trabecular lumbar spine L1-L4 of the X-ray images using two-stage principal component analysis with neighbourhood pixel grouping, followed by a hybrid median filter, and the texture features are enhanced with sharpening combined with range filters. Second, detect osteoporosis using texture features. This can be done by one-dimensional discrete wavelet transform, followed by a two-dimensional edge detection filter. Finally, classify the normal or osteoporotic images according to conventional classifications. Testing is conducted using X-ray images and dual-energy X-ray absorptiometry (DXA) reports from the same person. The DXA report describes a statistical analysis of normal or osteoporotic, but the proposed work is classified as osteoporotic or normal according to the texture features. Classified results are validated with the DXA and provide an average accuracy of 99.18%. The proposed method has better diagnostic accuracy than the existing method using DXA with X-ray.

105

Authors: Tallapureddy Subba Reddy, Thimmasandra Venkataswamy Sreerama Reddy, Erappa Rajj Babu, Hosur Nanji Reddy Reddappa

Organic Rankine Cycle (ORC) fluids are applied in Shell and Tube Heat Exchanger for waste heat recovery to increase its efficiency. Various methods have been applied in the ORC in shell and tube heat exchanger, which has the limitation of low efficiency in optimization. In this research, Enhanced Teacher Learning Based Optimization (E-TLBO) method has been proposed to increase the efficiency of the ORC in shell and tube heat exchanger. The Michalewicz was applied to the optimization method to provide global optimum and escape from the local optima. The E-TLBO method improves the convergence of the optimization and provides the effective performance in finding solution. The E-TLBO method has the advantages of two parameters such as population size and the number of iterations requires to set the value for optimization. The Shell and tube heat exchanger model has been developed to evaluate the performance of the optimization. The performance of E-TLBO is evaluated in four fluids namely R245fa, R134a, R290, and R600a in ORC analysis. The proposed E-TLBO method is compared with existing methods of Bell-Delaware and Kinetic Gas Molecule Optimization (KGMO) method. This analysis showed that R245fa fluid has a higher mass flow rate compared to other fluids. The proposed E-TLBO method has an enhancement factor of 3.14 and the existing KGMO has a 1.88 enhancement factor in R245fa fluid.

125

Authors: Elmostafa Chetouani, Youssef Errami, Abdellatif Obbadi, Smail Sahnoun

This paper proposes a nonlinear optimal Backstepping method for controlling the doubly-fed induction generator used in wind energy conversion and obtainingmaximum power. The grid is connected directly to the stator. The rotor, on the other hand, is connected to the grid via two bidirectional converters. This work aims to regulate active and reactive power while maintaining a unit power factor using the proposed controller. The Lyapunov function guarantees the stability of the system. The most challenging aspect of Backstepping is determining the best positive constants, which are critical to the system performance. This process becomes more complex, especially when the generator parameters are uncertain or when the wind profile varies. As a result, optimizing the gains is an essential aspect of the controller design. The particle swarm optimization method is suggested for determining the optimum Backstepping constants. The performance and robustness of the proposed method are investigated and compared to the Conventional Backstepping and the Proportional-Integral Control strategies of a 5 MW wind power plant system under parameter variations and quickly changing wind speed profiles. Matlab/Simulink makes it possible to get results. The advised methodology ensures the tracking system's robust stability and reduces the response time to 1.8 (m s). Furthermore, it guarantees a negligible static error.

146

Authors: Sandeep Dhanraj Bawage, Manjula Shivkumar

Massive Multi-In-Multi-Out (MIMO) is a promising and popular technique in wireless communication systems, which is used to deliver high reliability, spectral efficiency to several users. The major problem arises in channel contamination and allocation in a massive-MIMO network. In this paper, we proposed a novel adaptive channel allocation scheme (NACAS) to reduce channel contamination and improve channel allocation. The process of channel assignment is randomized at each time slot where data is repetitively transmitted with successive-interference-cancellation across similar packets. Massive-MIMO has the property of successive interference cancellation and majorly depends on asymptotic in-variance power which is received from the user in less time of interval, and asymptotic orthogonality among the user channels. Therefore, the proposed method permit received signals that turn contaminated into the combination of linear data, which provides an increment in throughput compared to the conventional techniques. The numeric and graphical analysis is shown in the result section, evaluation parameters are considered such as throughput, number of antennas, fading effect, etc. where our proposed approach has shown significant improvement as compared to state of art techniques.

168

Authors: Md Shoaibuddin Madni, C. Vijaya

Hand Gestures provide a means for a series of interactive communications with human beings who are deaf and dumb. Deep learning based models have been revolutionized for achieving human level performance through computer vision that automates, classifies and detects presence of objects in an image. Various challenges were faced through this process such as variation in the hand size, color, illumination, skin tone, view point, complex natural backgrounds etc, because of the various conditions present on the images. The present research overcomes the problem of high dimensional data and improved the classification accuracy in gesture pattern recognition for the incomplete data. Then, multilevel segmentation method and morphological model are used to segment the gesture regions and furthermore, Auto Encoder (AE) algorithm is applied to reduce the dimension of the data. Additionally, Bi-Long Short Term Memory (LSTM) classifier is applied to classify the alphabets, numbers, and video symbols. In the experimental phase, the improved AE-BiLSTM model achieved effective performance in recognition of hand gesture in terms of accuracy. Compared to the existing CNN and PCA based uni-modal feature-level fusion model, the proposed AE-BiLSTM model showed a maximum value of 99.85 % in terms of accuracy for ISL dataset and 99.75% for NUS dataset.

187

Authors: Qasim Hadi Kareem, Malik Jasim Farhan

This paper proposes a dual-polarized compact eight-element antenna system with high isolation for 5 G mobile terminal applications, consisting of four elements symmetrically located on the system plane's long edges, while the other four are symmetrically placed on both sides of the substrate surface (upper and lower). The proposed antenna system can, therefore, produce a dual-polarized pattern that can operate with a wide bandwidth (3200-3900 MHz) and therefore cover Long Term Evolution (LTE) 42 (3400–3600 MHz) band and LTE 43 (3600–3800 MHz) band. The equivalent circuit model for the proposed design is analyzed using Advanced System Design (ADS) tool, and the behaviour of the circuit is compared to the Computer Simulation Technology (CST) tool results and shows a match. The designed system displays a reasonable 10-dB effective impedance bandwidth, high isolation levels above 15-dB, lower Envelope Correlation Coefficients (ECC) below 0.01, and an acceptable radiant output. The nominal Mean Effective Gain (MEG) ratio is less than 1 dB and the maximum channel capacity of 8 x 8 Multi-Input-Multi-Output (MIMO) is 42.3 bps / Hz, with the total operating band being 20-dB Signal to Noise Ratio (SNR). The calculations, analysis, and discussions of the main parameters that characterize the proposed design were verified and show the appropriate matching impedance and high isolation (high performance) between simulated and measured results for the entire operating band.

208

Authors: Yolla Faradhilla, Agus Zainal Arifin, Nanik Suciati, Eha Renwi Astuti, Rarasmaya Indraswari, Monica Widiasri

In performing dental implant surgery on the mandible, it is necessary to measure the height and width between alveolar bone and mandibular canal. A system that is able to measure the height and width automatically is required since a manual measurement takes a long time. One of the important processes in this system is mandibular canal segmentation. The main problem in this segmentation process is the unbalanced numbers of data between object and background classes. This problem often led to misclassifications, especially at pixels on the object boundary. This research proposed a new architecture based on residual fully convolutional network (RFCN) by considering the loss values in the region and boundary of the mandibular canal segmentation. Dual auxiliary loss (DAL) functions are introduced to optimize RFCN, so that the network performs object segmentation better. For this research, DAL used focal loss to calculate the loss value in region and boundary to overcome the unbalanced class between the mandibular canal and the background. There are 2 datasets used for this research. The first dataset contains 200 images with mandibular canal and the second dataset contains 300 images consisting of 200 images with mandibular canal and 100 images without mandibular canal. We tested our network and compared it with state-of-the-art segmentation methods. The experiment showed that the proposed method outperforms all the comparing methods with Dice Similarity Score of 0.914 on the first dataset and 0.868 on the second dataset.

234

Authors: Khulood Eskander Dagher, Mohammed Najm Abdullah

An airborne computer system is avionics-based model that consists of an electronic system and a specifically designed equipment. In this paper, we propose a collision-free path finding flight strategy that enhances the output performance of a drone system for free-navigation between buildings. This strategy is based on a reactive method that requires metaheuristic algorithms to process environmental information during drone flying. In addition, a robust controller is designed to achieve drone flight and reach the target point. The goal of this paper is to discuss the determination of the shortest flight path with the minimum cost function evaluation and this flight path should avoid the collision by using four heuristic algorithms including: Chaotic Particle Swarm Optimization (CPSO) algorithm, Fire-Fly (FF) algorithm, Bees (B) algorithm and a hybrid optimization algorithm that combines the CPSO, FF and B algorithms. To fly the drone and to follow the generated flightpath, six adaptive PID controllers are designed in order to control the highly nonlinear model and under-actuated drone system using an on-line CPSO algorithm to learn and tune the eighteen control gain parameters. The purpose of this control design is to precisely and quickly obtain robust thrust forces control actions to control the attitude and altitude of the drone model. The numerical results of the proposed flightpath-finding algorithms and robust control strategy confirm that the hybrid (CPSOFFB) flightpath algorithm has the minimum number of iterations and evaluation functions as well as free navigation and the shortest flight path length generated. Moreover, the proposed six adaptive PID controller results show that the four thrust forces control actions are smooth and accurately generated making the drone take off and follow the desired flight path quickly with the minimum number of cost function and around ±10 cm minimum error tracking translation location. The maximum overshoot of the altitude did not exceed 10 cm in the transient state and the orientation error of the drone is approximately zero in the steady-state. To demonstrate the effectiveness of the proposed flight path finding and control strategy, a comparison is made with the results other types of algorithms.

258

Authors: Dedy Kurnia Setiawan, Mochamad Ashari, Heri Suryoatmojo

This research attempted to control a Four-Leg Inverter (FLI) on microgrid rooftop solar (MGRS), which connects to a distribution network (grid) via a distribution transformer. The connected load on an MGRS system comprises two loads: nonlinear load and unbalanced linear load. Rooftop Solar (RS) injection current on each grid phase fluctuated depending on irradiation value. Load and irradiation fluctuations and RS capacity differences on every phase caused the transformer’s current unbalance and harmonic. Since the pulled current load varied between grid phases, the current load’s instantaneous fundamental power demand (active and reactive) also differs for each phase. Optimized Constructive Neural Network (OCNN) with single-phase PQ theory was utilized to independently control FLI in every phase determined by fundamental power demand. Therefore, a transformer would perceive load and RS injection as balanced despite varied and unbalanced conditions. OCNN builds networks by self-constructive methods. Each training session enables the addition of new hidden layers and neurons inside each layer. The OCNN network compares the error value associated with the training results to the error value associated with the temporary best network (TBN). Throughout each training session, this comparison is made to determine the network with the lowest error value or the global best network (GBN). The frequent irradiation fluctuation indicated that the system often stayed in a transient rather than a steady-state. In high transient conditions, the performance of the proposed controlling method had been tested in simulations. The result revealed that the OCNN controller obtains the lowest peak values under high transient conditions, namely 2.62% for PCU and 6.73%, 7.33%, and 6.63% for THDi, respectively, at phases A, B, and C.

290

Authors: Syavira Tiara Zulkarnain, Nanik Suciati

Face recognition is a personal identification system based on facial biometric data. By looking at the characteristics of the image data that has lighting variations and contains Gaussian/Poisson/Quantization noise when taken using a camera, facial recognition systems working in the real world with uncontrolled environmental conditions is a challenge. Local Ternary Pattern (LTP) is a representation of image features that are invariant to lighting, resistant to noise, but require manual threshold determination. In this study, we propose an automatic calculation of adaptive LTP’s threshold using the statistical characteristic of image histograms. We also propose a Multi-scale Block Adaptive Local Ternary Pattern (MBALTP) which combines local features extracted using adaptive LTP and global features captured using multi-scale block for face recognition. We experimented on the Extended Yale-B dataset, which were collected under different lighting variations and contains noise. The experimental result demonstrated that the proposed method can improve the recognition performance with an accuracy of 98.87%.

311

Authors: Gouramma Halidoddi, Rubini Pandu

Wireless Sensor Networks (WSNs) attain much attention in different areas due to their self-configurability, easy maintenance and scalability feature. WSN is configured with more nodes to transfer the data inside the network. The sensor networks are usually characterized based on low bandwidth, limited energy, limited power supplies and small size memory, which leads to demand for the environment to provide security. Recently, the objective is to accomplish network security with low energy utilization is a challenging task in WSN. In this paper, an appropriated node selection and secure route path generation are achieved by using Grasshopper Optimization Algorithm (GOA) and Elliptic Curve Cryptographic and Diffie Hellman (ECCDH) based key exchange algorithm. The main aim of using the GOA-ECCDH method is to select the optimal route path with minimum energy consumption and improving the network lifespan in WSN. The performances of the GOA-ECCDH method are evaluated and compared to the existing Secure and Energy-aware Heuristic-based Routing (SEHR) method and Secure Routing Protocol based on Multi-Objective Ant-colony-algorithm (SRPMA) method in terms of packet delivery ratio, average energy consumption, packet loss rate, and routing load. The packet loss rate of the GOA-ECCDH method is 7.2% for the network with 8 black hole nodes, which is lesser when compared to the SEHR method and SRPMA method.

333

Authors: Tabarek A. Abdulabbas, Lwaa Faisal Abdulameer

FSO link suffers from a deep fade in some ranges of frequencies and it is very difficult to ensure the availability for this link especially in sever channel conditions such as dense fog, while RF link with mmWave working otherwise. FSO/RF hybrid system has emerged as a powerful solution for signal unavailability due to these conditions. The specific objective of this paper was to drive the error performance for the proposed coded hybrid communication system operating over atmospheric turbulence channel, considering gamma-gamma turbulence model for FSO and mmWave channel for RF. Error correction coding such as LT code, Polar code and Raptor code were used over FSO/RF link to mitigate turbulence fading and multipath effects. The numerical results of this paper show that the hybrid FSO/RF MIMO system implementing raptor code has a significant improvement over the system implementing LT or polar codes, 16×16 MIMO system implementing raptor code has a gain of 5 dB SNR when compared with the same system without implementing code. Additionally, the 16×16 MIMO hybrid system implemented Raptor code required 6 dB SNR to obtain BER of 10-3, while the 8×8 and 4×4 MIMO system with the same code required 8 dB and 9 dB SNR to achieve the same BER.

357

Authors: Arif Muntasa, Muhammad Yusuf

Acute Lymphoblastic Leukemia (ALL) is one of the most dangerous cancer diseases. Therefore, it is necessary to classify this disease accurately. We proposed a method to classify ALL using multi-distance models of the Gray Level Co-occurrence Matrix (GLCM). We employed sixteen distance models to obtain several features of the main object. We applied three channels of the image's enhancement results, where each channel has been extracted using second-order statistic models, which are homogeneity, entropy, energy, and contrast. We have obtained one hundred and ninety-two features for each object. Moreover, the feature extraction performances have been classified using Canberra and Chebyshev techniques. We have evaluated our proposed method using the ALL Image database and produced accuracy at 96.97%, where 2.27% false positive and 0.75% false negative. Our developed method has been compared to other approaches, such as Support Vector Machine (SVM)-Linear Binary Pattern (LBP), SVM Shape, Naïve Bayes Deterministic, Fuzzy based Leukemia detection, Color Correlation, Hausdorff SVM-based Leukemia detection, Automated Differential Learning Vector Quantization (LVQ), and Multi-Level Perceptron (MLP). The results show that our proposed method outperformed the others.

377

Authors: A. Vijaya Lakshmi, P. Mohanaiah

Facial Expressions are one of the most essential and general means for human beings to express their feelings and communicate their emotions; thus, Facial Expression Recognition (FER) has gained a significant research interest and an attractive topic in Human-Computer Interactions (HCI). Towards such, this paper proposes a novel face descriptor, Gradient Direction Pattern (GDP), for facial expression recognition. With the help of gradients, GDP encodes the structure of the facial image in a more compact way such that the FER is robust to pose variations. Furthermore, the GDPs are measured for edge feature maps, extracted from Gaussian filtered and Gabor filtered facial images at different orientations. These edge feature maps make the recognition system robust to noise, illumination, scaling, and orientational variations. Initially, the facial image is divided into small regions, and GDPs are extracted from them. Then these patterns are concatenated, and Histograms are measured, called GDP Histograms (GH). Simulation experiments were conducted over two standard datasets, such as CK+ and JAFFE, and the average accuracy is observed as 95% and 91% approximately.

402

Authors: Hasib Daowd Esmail Al-ariki, Mohammed Hamdi

Energy efficiency and security are the most vital requirements in Wireless Sensor Networks (WSN). Therefore, modern routing protocols have been forced to consider these issues as the primary challenges. This study proposes the develop meat of an Energy Efficient Secured Fault-Tolerant Routing (EESFTR) protocol that improves routing efficiency and also increasing network reliability. The proposed EESFTR protocol consists of cluster head (CH) selection, optimal route selection, fault detection and recovery process. First, the clustered network utilizes Fuzzy logic to select optimal energy surplus CH. The routes are then discovered and the optimal routes are selected based on energy, link quality and network lifetime designing a Modified Butterfly Optimization Algorithm (MBOA). To ensure security and fault-tolerance, the efficient Elliptical Curve Digital Signature Algorithm is enhanced through unknown parameter signature verification. Finally, the faults which are detected to be malicious to the network are either repaired or eliminated based on a disruptive process. The proposed EESFTR protocol has been evaluated and compared with the existing routing protocols to highlight its efficiency. The results showed that the proposed EESFTR protocol has better a routing performance with 13% less time consumption, 8.3% less energy consumption, 20% increased lifetime, and 12% reduced packet drops to ensure higher fault tolerance and security when compared to the performance of the efficient existing routing protocols.

427

Authors: Chadaporn Sookpuwong, Chow Chompoo-inwai

This paper presents a model and simulation results of the active noise control (ANC) system in a wide-area virtual environment using the acoustics finite-difference time-domain (FDTD) propagation approach defined by particle velocities and sound pressure level (SPL) within a certain absorbing boundary conditions called a perfectly-matched layer (PML) technique. The ANC excitation applies a single-frequency noise source with an adaptive feedforward configuration. The FDTD algorithm is used to model the area of interest acoustically, including a desired quiet zone, considering the effects from a primary path, a secondary path, and a feedback path. A processing unit of the ANC system based on the least mean-squared (LMS) algorithm is utilized to synthesize a cancelling noise using a secondary loudspeaker. A single-channel feedforward ANC system used in this paper is modified from the proposed multi-channel models and forms. Acoustics FDTD propagation results can be used to determine the optimum placements for ANC sensors and actuators. The SPL numerical and graphical results are plotted to demonstrate the performance of the proposed ANC system. All of the simulation results confirm that the proposed modeling approach can be combined with wide-area acoustic simulations and a feedforward LMS adaptive algorithm. The proposed model also provides a way for the optimum placement of the ANC sensors and actuators before being used in a more-complex practical environment.

453

Authors: Chetana Reddy, Virendra Shete

The rapid development of wireless communication technology makes Orthogonal Frequency Division Multiplexing (OFDM) technology and Multiple Input Multiple Output (MIMO) technology, key candidates for the next generation mobile communication system. OFDM system has high frequency utilization and effectively resists multipath and narrowband interference. MIMO technology can effectively improve system capacity and system separation. This paper presents a hybrid Linear-Quadratic Estimation (LQE) technique for Channel Estimation in MIMO-OFDM system. In channel estimation, the noise covariance matrix (Q) plays a key role. In general, the value of Q depends on the previous state values. In a dynamic system, the previous values are not always known. The proposed hybrid model uses two techniques to address this issue. When the previous state values are known, Fast Adaptive Hybrid - Linear Quadratic Estimation (FAH-LQE) is used and when the previous state values are unknown Discrete Multivariate Hybrid - Linear Quadratic Estimation (DMH-LQE) is used. This enables the channel estimation to perform effectively in both scenarios. The FAH-LQE method uses covariance channel noise estimation equations and updates the threshold limit. DMH-LQE finds previous values using discrete generate matrix. The switching between FAH-LQE and DMH-LQE, based on the availability of previous state values, has increased the performance of the system effectively. The proposed algorithm produced lower BER values. For a mobility of 55km/h at SNR 15, BER values of proposed algorithm are 22%, 10%, 7%, 6%, and 3% lower than existing methods namely CE with and without EEP-Kalman tracking, perfect channel estimation, FAH-LQE, and DMH-LQE respectively. Similarly for a mobility of 115km/h at SNR 15, BER values of the proposed algorithm are 45%, 35%, 20%, 15% and 5% lower than above mentioned existing methods namely CE with and without EEP-Kalman tracking, perfect channel estimation, FAH-LQE, and DMH-LQE respectively. The SER has been reduced by 5% when no compensation method is applied. By using the proposed method, the Peak to Average Power Ratio (PAPR) has also reduced.

476

Authors: Yuslena Sari, Hargokendar Suhud, Andreyan Rizky Baskara, Ricardus Anggi Pramunendar, Iphan F. Radam

The increasing ownership of four-wheeled vehicles creates a new problem: difficulty finding available parking spaces in significant places. Issues citizens often experience these in the city centre who use their cars for transportation. This causes the detection of parking lots to attract the attention of researchers. Unfortunately, this system fails when the vehicle occupies more than one place or when the parking lot has a different parking space. In this study, an automation method is proposed that utilises a combination of gray level co-occurrence matrix (GLCM) and support vector machine (SVM) methods with genetic algorithm (GA) optimisation techniques or called SVMGA. The results showed that the SVMGA could provide an accuracy performance of 96.99% for training data and 94.36% for test data. The results of this study are expected to help the queue of people to find a parking space and reduce the density of lines in the parking lot.

498

Authors: Shilpa VenkataRao, Vidya Ananth

Nowadays, Wireless Sensor Networks (WSNs) are extensively utilized as the communication system in the Internet of Things (IoT). Security of the sensor nodes is considered as one of the important aspects of the IoT-based WSN because the nodes in the network are susceptible to malicious attackers. The main objective of this investigation is to generate secure routing and mutual authentication over the IoT-based WSN. In this paper, the Hybrid Optimization Algorithm (HOA) based secure Cluster Head (CH) selection and routing path generation is obtained for secure data transmission. The HOA is the combination of the Grey wolf optimization (GWO) and Moth Flame Optimization (MFO) whereas the fitness functions are trusted value, residual energy, distance and node degree. Additionally, the Shamir Secret Sharing (SSS) method is used for providing mutual authentication between the nodes. The performance of the HOA-IoT-WSN is analyzed in terms of Packet Delivery Ratio (PDR). Packet Loss Ratio (PLR), Average End-to-End Delay (AEED) and network overhead. An existing method such as Energy-efficient and Secure Routing (ESR) protocol, Hybrid Harris Hawk and Salp Swarm (HHH-SS), and Light Weight Trust Sensing (LWTS) methods are used to evaluate the proposed HOA-IoT-WSN method. The PDR of the HOA-IoT-WSN method is 99.848% for 100 nodes, it is high when compared to the ESR, HHH-SS and LWTS.

518

Authors: Sharon Rose Victor Juvvanapudi, Pullakura Rajesh Kumar, Konala Veera Venkata, Satyanarayana Reddy

In this study, a new watermarking system was proposed to address two major concerns: slow learning and computational capability. At first, cover image was transformed into wavelet environment utilizing Integer Wavelet Transform (IWT) that makes the cover image free from false errors. Then, Grey Wolf Optimizer (GWO) was utilized for selecting the image pixels to embed the secret image in the cover image. GWO effectively selects the pixels utilizing fitness function, which calculates entropy, pixel intensity and edge of the cover images. Besides, the secret image was encrypted by using chaos encryption with hybrid mapping (logistic and henon map) that improves computation efficiency and security with good embedding capacity. After the cover image transformation and secret image encryption, Least Significant Bit (LSB) was utilized to deliver self-recovery features and also for locating the tempered region in the digital image. Experimental results showed that the developed system attained a secure transmission network with low complexity in light of Unified Averaged Changed Intensity (UACI), entropy value, Structural Similarity Index (SSIM), Normalized Cross Correlation (NCC), and Peak Signal-to-Noise Ratio (PSNR). Compared to the existing systems, the proposed system showed 3dB to 4.4 dB improvement in PSNR and 0.32 value improvement in SSIM.

539

Authors: Ayad Mohammed Jabbar, Ku Ruhana Ku-Mahamud

Grey wolf optimization (GWO) algorithm is one of the best population-based algorithms. GWO allows sharing information in the wolf population based on the leadership hierarchy using the hunting mechanism behavior of real wolves in nature. However, the algorithm does not represent any key exchange information sharing for the traveling salesman problem because of two issues. The candidate solutions are improved dependently, similar to local search concepts, losing their capability as a population-based algorithm. The algorithm is limited in its search process in finding only the local regions and ignoring any chance to explore search space effectively. This study introduced an adaptive grey wolf optimization algorithm (A-GWO) to solve the information-sharing problem. The proposed A-GWO maintains sufficient diverse solutions among the best three wolves and the rest of the population. It also improves its neighborhood search by obtaining more locally explored regions to enhance information sharing among the wolves. An adaptive crossover operator with neighborhood search is proposed to inherit the information between the wolves and provide several neighborhoods to find more solutions in the local region. Experiments are performed on 25 benchmark datasets, and results are compared against 12 state-of-the-art algorithms based on three scenarios. The credibility of the proposed algorithm produces approximately 53%, 58%, and 63% better tour distance in the first, second, and third scenarios, respectively. The proposed A-GWO achieves approximately 87% better minimum tour distance compared with the GWO algorithm.

568

Authors: Mohamed S.S. Basyoni, Hesham A. Hefny

Fuzzy rules have been used extensively in data mining. Our model is proposed to construct Fuzzy Rules with considering criteria of accuracy. The model consists of five phases: (1) Automatic attributes fuzzification, (2) Feature selection via core and reduct, (3) Fuzzy rules extraction via SQL statement, (4) Calculates Accuracy and Confidence for each rule, (5) Genetic coding of fuzzy rules. The algorithm determines automatically the parameters width of each attribute then uses the rough set to reduce the number of attributes (Feature Selection) via core and reduct. The model then extracts fuzzy rules using SQL statements and calculates Accuracy and Confidence. Finally, our genetic model represents each fuzzy set by “Real number” to improve the accuracy. The model applied on Iris and Wine datasets and the result will be better than the other models in term of the number of fuzzy sets and classification rate for evaluating the accuracy of training and test instances.

588

Authors: Khalissa Behih, Salah Eddine Saadi, Ziyad Bouchama

This paper addresses the design of synergetic control (SC) for synchronizing two chaos systems represented by Takagi-Sugeno (T-S) fuzzy models. Unlike many works published, the present paper provides a new synchronization algorithm of two different hyperchaotic systems which corroborate the given analytical stability proof of the closed-loop systems. The main idea is to represent the chaos systems as an aggregated fuzzy model which compromises a set of linear models in the first place. Afterwards, the synergistic controller is applied to synchronize a nonlinear hyperchaotic (slave) system with another hyperchaotic (master) system. The proposed approach achieves hyperchaos synchronization such that it has a simple structure leading to an easy implementation. Then, theoretical analysis and numerical simulation results are compared to those obtained with a conventional sliding mode (SMC) approach clearly showing the effectiveness of the proposed strategy.

605

Authors: Purba Daru Kusuma, Meta Kallista

Multi-depot capacitated vehicle routing problem is a derivative of vehicle routing problem and a well-known area that has been studied widely with various applications and constraints. Many studies in it focused on minimizing cost and distance with assumption that all nodes are visited. Ironically, number of unserved customers (nodes) in a single trip was rarely explored and often ignored. Based on this problem, this work aims to minimize the total travel distance and the number of unserved customers in single routing cycle. The solution is developed by combining the stable marriage algorithm and k-means clustering in the clustering process. The nearest neighbour algorithm is used in the routing process. This work proposes two contributions. The first is the usage of the stable marriage and k-means clustering. The second is concerning the predetermined distribution of the vehicles in the solution to reduce the number of unserved customers. In the simulation, this proposed model is compared with the hybrid evolutionary algorithm (HEA), partition-based algorithm-nearest neighbour algorithm (PBA-NN), genetic algorithm-nearest neighbour algorithm (GA-NN) and simulated annealing algorithm (SA). Based on the simulation result, it is found that the proposed model performs moderately as a trade-off between the SA and PBA-NN. In the number of unserved customers aspect, when the number of customers is low, the proposed model creates 71 percent lower than the PBA-NN model. Meanwhile, when the number of customers is high, the proposed model creates 73 percent lower than the PBA-NN model. In the total travel distance aspect, when the number of customers is low (50 persons), the proposed model creates 63 percent higher than the GA-NN model and 48 percent lower than the SA model. Meanwhile, when the number of customers is high (100 customers), the proposed model creates 52 percent higher than the PBA-NN model and 54 percent lower than the SA model.

629

Authors: A. N. Revathi, S. Mohanaselvi

This work will be illustrating a model for dealing with multi level four dimensional fractional multi item transportation problem whose parameters in both objectives and constraints are considered as uncertain variables. The Fractional programming technique is useful in dealing with real life situations where the decision maker has to maximize or minimize the ratios of two objective functions. In any hierarchical system or decentralized system, multi level programming problem can be used to obtain efficient solution based on the preferences of each decision maker at each level. The usage of fractional method and level wise preference in real life problems helps us to obtain the efficiency of system and also enables hierarchical decision making which is common in day to day transportation firms. An equivalent deterministic model has been obtained for the multi level four dimensional fractional multi item transportation problem under uncertain environment by using expected and chance constrain model of uncertainty theory. Then the deterministic model is solved by using the modified fuzzy goal programming technique to obtain the compromise solution of the proposed model. The validity of the proposed model has been explained using the numerical example.

656

Authors: Naga Siva Jyothi Kompalli, Dasika Sree Rama Chandra Murthy

The texture is an important feature in the visual content of the images and plays a significant role in the computer vision system. Many existing methods were involved in applying the feature selection and classifiers for texture classification. Existing methods have the limitation of poor convergence in the feature selection and overfitting problems in the classification. In this research, the Elite FireFly – Long Short Term Memory (EFF-LSTM) model is proposed to improve the efficiency of the texture classification. The EFF method has the advantage of replacing the low fitness firefly with a high fitness firefly in the search process and the LSTM model has the advantage of a store the important features in long term for the classification. This process provides good convergence in the feature selection and important features are applied to overcome the overfitting problem. Two datasets such as UIUC and KTHTIPS-2b were used to test the performance of the proposed EEF-LSTM model. The Min-Max normalization method is applied to enhance the quality of the images. The Local Directional Ternary Pattern (LDTP), Dual-Tree Complex Wavelet Transform (DTCWT), and Grey-Level Co-occurrence Matrix (GLCM) were the extracted features from the pre-processed images. The EFF method is applied to select the relevant features with good convergence. The LSTM method is applied to classify the images based on the EFF selected features. The proposed EFF-LSTM model has an accuracy of 96.5 % and the existing Convolutional Neural Network (CNN) has 94.3 % accuracy.

678

Authors: Veena Seenappa, Narayanappa Chikkajala Krishnappa, Pradeep Kumar Mallesh

In telemedicine applications, the images pertaining to medicines and diseases can undergo tampering and forging, where it increases risk in diagnosis. The reversible watermarking technique is capable to extract the embedded information and retrieve the original images completely from watermarked images. It has some specific features like lower distortion of images and high capacity of payload. To solve such an issue, a reversible watermarking method is proposed to provide security for the medical images using hyperchaotic with Deoxyribonucleic Acid (DNA) sequence. The proposed reversible watermarking method utilized standard images (lena, Barbara, boat and medical images) for encryption and decryption. Discrete Wavelet Transform (DWT) and Inverse Discrete Wavelet Transform (IDWT) are used to compress the cover images and to decompress the stego images. Further, the thresholding with morphological transform is employed for segmentation of Region of Interest (RoI) in secret images. In addition, the encryption and decryption of secret image is done by hyperchaotic system with DNA sequence. Lastly, the embedding and extraction of secret images and cover images from the stego images is performed by reversible watermarking with differential expansion and modulus function. Simulation result shows that the proposed reversible watermarking method achieved Peak Signal to Noise Ratio (PSNR) of 99 dB for secret image construction, which is better compared to other traditional watermarking techniques.