International Journal of Intelligent Engineering and Systems

1

Authors: Vamsidhar Talasila, Chitturi Prasad, Guttikonda Trinesh Sagar Reddy, Allada Aparna

Agriculture planning plays a significant role in economic growth and the food security of agro-based country. Crop yield prediction and selection of crops are the most challenging tasks in agricultural domain and it depends on different parameters such as production rate, market price and government policies. Among the two primary tasks, the crop yield prediction is one of the most demanding tasks for every nation. Due to uncertain climatic changes, farmers are struggling to attain a satisfactory amount of yield from the crops. Many researchers have studied on the prediction of weather, prediction of yield rate of crop, crop classification and soil classification for agriculture planning using statistical methods or machine learning techniques. This study focuses on the prediction of major crops in Andhra Pradesh region and presents an enhanced algorithm known as Deep Convolutional Regression Network (DCRN), which is trained and tested on agricultural data collected from farmers. The experimental results showed that the DCRN method achieved nearly 97% prediction accuracy when compared with existing methods like Decision Tree (DT), Self-Organizing Map (SOM).

19

Authors: Prakash Annamalai

Face recognition is an emerging research area in biometric identification systems, which attracted many researchers in pattern recognition and computer vision. Since, the human facial images are high dimensional in nature, so a new optimization algorithm was proposed in this paper to reduce the dimension of facial images. At first, the input facial images were collected from ORL, YALE, and FAce Semantic SEGmentation (FASSEG) databases. Then, feature extraction was then performed by using Local Ternary Pattern (LTP) and Binary Robust Invariant Scalable Key points (BRISK) to extract the features from the face images. In addition, an enhanced fire-fly optimizer was used to reject the irrelevant features or to reduce the dimension of the extracted features. In enhanced fire-fly optimization algorithm, Chi square distance measure was used to find the distance between the fire-flies and also it uses only a limited number of feature values for representing the data that effectively reduces the “curse of dimensionality” concern. Finally, Deep Belief Network (DBN) was used to classify the individual’s facial images. The experimental outcome showed that the proposed work improved recognition accuracy up to 7-20% compared to the existing work.

38

Authors: Petch Nantivatana, Pattarapong Phasukkit, Supan Tungjitkusolmun, Keerati Chayakulkheeree

This paper presents the optimal antenna slot position and sizing (OASPS), for microwave (MW) hepatocellular carcinoma (HCC) treatment, using multi-objective fuzzy decision making (MOFDM). In the optimal design problem formulation, the multi-objective for, (1) achievement for a near-spherical zone for ablation defined by axial ratio (AR), (2) the minimum reflection coefficient (S11), and (3) maximum volume of destroying (VD), are desired. The finite element method (FEM) is used for MW distribution simulation for coordination analysis with the proposed MOFDM based OASPS. The investigation on the design results shown that the temperature distribution of the proposed MOFDM for OASPS is in the more controllable shape comparing to the existing design, due to the sharp beam of temperature distribution to the target at the front side of slot with the less temperature distribution at the rare side of slot. The results also show that the proposed MOFDM for OASPS for OASPS design is easier to manage with the less effect to the rare side of the slot. Moreover, the proposed MOFDM for OASPS resulted in the temperature distribution shape closer to round shape than the existing design. The MOFDM for OASPS is tested on designing of the antenna build up from the coaxial cable. The coaxial cable used is Semi-rigid 141 (RG402 M17/130-RG402 Copper Jacket) including Inner conductor, Dielectric, and Outer conductor. In the simulation, the slot distance from conductor end (Lts), representing the slot position, is varied as 2.3mm, 3.3mm, 4.3mm, 5.3mm, 6.3mm, 7.3mm, and 8.3mm. Meanwhile, the slot size (Wd), is varied as 1mm, 2mm, 3mm, 4mm, 5mm, and 6mm. The input power (Pi) used is 50 W with the duration of 300 seconds. The comparison of obtained by different Lts and Wd, is investigated. The simulation results show that the proposed MOFDM based OASPS can efficiently and effectively provide the near-spherical zone of ablation result with simultaneously trade-off between S11 minimization and VD maximization.

63

Authors: Suhaila N. Mohammed, Fatin Sadiq Alkinani, Yasmin A. Hassan

COVID-19 is a vital zoonotic illness caused by Severe Acute Respiratory Syndrome Corona Virus 2 (SARS-CoV-2). COVID-19 is a very wide-spread among humans thus the early detection and curing of the disease offers a high opportunity of survival for patients. Computed Tomography (CT) plays an important role in the diagnosis of COVID-19. As chest radiography can give an indicator of coronavirus. Though, an automated Computer Aided Diagnostic (CAD) system for COVID-19 based on chest X-Ray image analysis is presented in this article. It is designed for COVID-19 recognition from other MERS, SARS, and ARDS viral pneumonia. The optimal threshold value for the segmentation of a chest image is deduced by exploiting Li s' method and particle swarm intelligence. Laws' masks are then applied to the segmented chest image for secondary characteristics highlighting. After that, nine different vectors of attributes are extracted from the Grey Level Co-occurrence Matrix (GLCM) representation of each Law's mask result. Support vector machine ensemble models are then built based on the extracted feature vectors. Finally, a weighted voting method is utilized to combine the decisions of ensemble classifiers. Experimental findings show an accuracy of 98.04 %. It indicates that the suggested CAD scheme can be a promising supplementary COVID-19 diagnostic tool for clinical doctors.

85

Authors: Fatna Elmendili, Younès El Bouzekri El Idrissi

The rapidly growing online social networking sites have been infiltrated by a large amount of spam. Spammers are a particular kind of ill-intentioned users who degrade the quality of OSNs information through misusing all possible services provided by OSNs. Social spammers spread many intensive posts/tweets to lure legitimate users to malicious or commercial sites containing malware downloads, phishing, and drug sales. Given the fact that Twitter is not immune towards the social spam problem, different researchers have designed various detection methods, which inspect individual tweets or accounts for the existence of spam contents. Today, social networks are exposed to various threats that exploit their vulnerability. However, although of the high detection rates of the account-based spam detection methods, these methods are not suitable for filtering tweets in the real-time detection because of the need for information from Twitter’s servers. At tweet spam detection level, many light features have been proposed for real-time filtering; however, the existing classification models separately classify a tweet without considering the state of previous handled tweets associated with a topic. First, they propose the identification of spam tweet by the security approach based on social honeypots and then they propose a method based on an algorithm "content filtering" in order to detect those that are similar to spam tweet detected by the approach of honeypots. Our approach has greatly improved the quality of abstraction in terms of performance and design. The algorithm is also fast and simple to implement. Experimental results show the stability and accuracy (over 99%), F-measure 98% of our approach.

111

Authors: Murugesan Suman, Vadugapalayam Ponnuvel Sakthivel, Palanigounder Duraisamy Sathya

In this paper, a new meta-heuristic algorithm, called Squirrel Search Optimizer (SSO) is applied to solve various types of economic load dispatch (ELD) problems. The SSO mimics the foraging behavior of squirrels which is based on the dynamic jumping and gliding strategies. In SSO algorithm, predator presence behavior and a seasonal monitoring condition are employed to increase the search ability of the algorithm, and to balance the exploitation and exploration. The key idea of the suggested approach is to determine the optimal generation scheduling by minimizing total generation cost of units while satisfying various constraints such as power balance constraint, prohibited operating zones (POZ), ramp rate constraints and operating limits of generators. The different generating unit’s characteristics, quadratic fuel cost function, non-convex fuel cost function and multiple fuel options (MFO) are also considered. The feasibility of the proposed algorithm is tested on four different power test systems having different sizes and intricacies. The results are examined in terms of both solution quality and the computational efficiency, and compared with the other approaches in the literature. The comparisons prove the robustness and effectiveness of the proposed algorithm and show that it could be used as a consistent optimizer for solving various ELD problems.

133

Authors: Rafika El idrissi, Ahmed Abbou, Mohcine Mokhlis

The temperature and radiation changes lead to obvious fluctuations in photovoltaic panels ' output power. To optimally exploit the PV system, maximum power point tracking (MPPT) is needed. Various offline and online methods for monitoring the MPP have been implemented. In this work, a maximum power point tracking (MPPT) technique was created which is primarily based on backstepping integral sliding mode controller (BISMC) design. The control scheme incorporates two parts: the first is based on an artificial neural network that provides the reference voltage, that supplies the maximum power regardless the environmental factors, which is given to the proposed BISMC control that is responsible on regulation of the duty cycle of the DC-DC boost converter's PWM applied switch (Mosfet). This strategy offers very low tracking error, and chattering improvement in tracking the MPP of a PV system when the environmental disturbances occur. The added integral action is very important in the control closed loop because it removes the steady state error. The method is compared with the ANN-sliding mode, PSO-backstepping and P&O-backstepping controllers in order to demonstrate its efficiency. In this later, the P&O (perturb & observe) and the PSO (particle swarm optimization) algorithms serve to generate reference voltage, that corresponds to the MPP, while the backstepping controller tracks this reference voltage. To reduce the PV system cost, a high-gain observer is designed, it requires only the PV output voltage sensor which enables the unmeasured PV system state variables on-line. This allows the minimization of the number of sensors in practical case because they have many disadvantages. The use of these sensors can lead to bulky system. Moreover, they are expensive. The simulation study is carried out under Matlab/Simulink. The results of the suggested MPPT reveal outstanding dynamic response under rapid changes of irradiation and temperature. The suggested method is more accurate and has fast convergence time about 2.2 ms and 1ms depends on the meteorological condition changes and 98% of efficiency to track the maximum power point.

159

Authors: Chaiyut Sumpavakup, Kritsada Mongkoldee, Tosaphol Ratniyomchai, Thanatchai Kulworawanichpong

This article proposed a computer-based simulation approach to estimate touch and step voltages due to a lightning strike at a mass rapid transit railway station. A purely resistive circuit model of a station lightning protection, and earthing & bonding system is formed in MATLAB/Simulink with Yaek Nonthaburi 1 passenger station of MRT purple line in Bangkok, Thailand as a case study. The simulation investigated the consequence of a lightning strike at four different locations on the roof of the station and examined whether or not the lightning protection system met the standard requirements. The results showed the touch voltages, step voltages and body currents in a steady state together with the impact on the human body standing in the station. The simulation can guarantee the effectiveness of the proposed model, and also proved that the lightning protection system of the station is able to conform to the standard and there is no harm for the passenger in the station.

181

Authors: Mamdouh Alenezi, Mohammad Nadeem, Alka Agrawal, Rajeev Kumar, Raees Ahmad Khan

Security and design tactics estimation of web application for ensuring the security, efficiency and design tactics of web applications is necessary. A survey conducted by the security research team, Micro Focus, of the USA reveals that 80% of the vulnerability defects occur due to the coding defect, validation causes 60% of the errors, 70% errors are due to encapsulation and path traversal. Such statistics call for a more efficacious design to enhance software security. The primary research goal of this study is to compute or evaluate the security threats of the software and web applications from the perspective of design tactics. Towards this intent, we have employed the methodology of Fuzzy Analytic Hierarchy Process (F-AHP) to evaluate the security factors or obtain the weight of different factors. The different design tactics of web application have also been selected according to the factors that affect the security. In this article, researchers have used a crossbreed technique of fuzzy based Multi Criteria Decision Method (MCDM) technique, i.e., F-AHP and Fuzzy Technique for Order of Preferences by Similarity to Ideal Solutions (F-TOPSIS) Technique. The results of the assessment of security will be helpful for developers or experts in designing the security tactics of software or web applications. We have also compared the results of classical and Fuzzy approach to determine the weight of alternatives or attributes and rank of the factors. This process is an effective and conclusive methodology for the developers working for more enhanced secure design tactics of software and web application design.

211

Authors: Andreas Andreas, Mochamad Hariadi, Mauridhi H. Purnomo, Kunio Kondo

Lighting is one of the very important things in cinematography. Lighting in cinematography is used not only to illuminate the objects, but it has many important roles such as to make the object looks sharper, has tone, depth and separation, and so on. There are some parameters that affect the lighting result, such as light source type that is used, its colour, intensity, position, and direction. Unfortunately, lighting has so many permutations and variations and there is more than one right way to light the scene. In this research, a designer designs some scenes that will be used as inputs. In this study, the authors found that lighting set is strongly influenced by five important things, which are: the situation of the scene, Point-of-View, the intensity of the attached light sources, camera position, and emotion of the characters, that we called as the SPICE system that is the abbreviation from situation, PoV, intensity, camera, and emotion. some additional light sources will be added into the scene automatically according to the scenario and director’s behaviour using the SPICE system that we propose. The SPICE framework has two fuzzy inference systems in calculating the intensity of light that hits an object and some additional light sources that are added to the scene automatically to make it looks much better. This research will make a calculation to gain the best scenes as an output. There are 20 scenes used in this research. As the final result, designers assess 80% outputs have been as expected.

238

Authors: Hazim G. Daway, Esraa G. Daway, Hana H. kareem

Colour image enhancement plays an important role in image processing, computer vision and pattern recognition. Fuzzy logic techniques one of the methods used for digital image enhancement. In this study, Fuzzy Logic Based-on Sigmoid Membership Function (FLBSMF) was developed to improve lightness and contrast in coloured images. The FLBSMF algorithm was applied to the lightness component by using only the YIQ colour space, and the colour compounds were unchanged. The suggested algorithm was compared with other algorithms, such as fuzzy logic enhancement using membership function modification based on square operation, fuzzy logic based on histogram, histogram equalisation and multiscale retinex with colour restoration by using different criteria. Form the result the FLBSMF succeeded in enhancing colour images and it had good average values for entropy (7.44), mean square error in saturation (2.2E-08) and hue (8.11E-07), nature image quality (2.97) and lightness order error (0.90).

257

Authors: Suhaila N. Mohammed, Alia K. Abdul Hassan

Speech emotion recognition finds many applications in the daily life like conversational agents, human robot interaction, call centres etc. However; the task of emotion recognition from speech signal is not trivial due to the difficulty in determining the effective feature set that can recognize the emotion conveyed within the signal in an accurate manner. Image processing techniques are exploited in this paper to solve speech emotion recognition problem. After converting the signal into 2D spectrogram image representation, four forms of Extended Local Binary Pattern (ELBP) are generated to serve as a source for feature extraction stage. The histograms of multiple blocks from ELBP variants are computed and fed to Deep Belief Network (DBN) for classification purpose. Different tests were performed using Surrey Audio-Visual Expressed Emotion (SAVEE) database and the achieved results showed that when using combined vectors of MELBP, the system gives the best accuracy which is 72.14%. The achieved result outperforms state-of-the-art results on the same database.

277

Authors: Smita Chaudhari, Gandharba Swain, Pragnyaban Mishra

In most practical cloud computing applications such as e-voting, auctions, health, and financial applications or cloud services in common, to prove the exactness of outsourced data is one of the major needs today. Most of the time, third party auditing is employed for this task. This auditing work is controlled by assigning the secret inputs to an entity trusted third party, or worker, who is liable for performing computations and hand over the result of the computation to the cloud users or clients. To verify the integrity of computations using traditional cryptographic techniques, the time required to generate and validate the proof is a major computation issue. This paper proposes an improved public auditing technique for multi-party computation to check the integrity of outsourced data using a cryptographic solution. Many researchers have given auditing protocols that generate and verify proof using a cryptographic solution. Most of these scheme uses Non-Interactive Zero-Knowledge Proof (NIZK) which are basically built on bilinear map technology. The verification time using these existing technique is computationally expensive which affect the performance of the auditing system. We propose an efficient protocol that verifies the result correctness using modern cryptographic technique Indistinguishability Obfuscation. The proposed system works in two phases, (i) auction and (ii) audit. During the auction phase, multiple clients share their encrypted bid value to the worker. The worker generates auction result and proof using Pedersen Commitment Scheme. The audit phase starts only after the completion of the auction phase which results in reduced verification time. During the Audit phase, clients can verify the integrity of results using NIZK with the IO technique. The results for reduced verification time in auction system have been presented. It is found that the performance of the proposed system has improved compared to the pertinent NIZK Proof technique. In our setting, we assumed that a worker is one of the trusted entity. By this notion, our protocol also guarantees privacy to the clients during the audit phase.

295

Authors: Yashesh Joshi, Hiren Mewada

Object detection and tracking is one of the active areas of studies because of variation in object location, pose, illumination, scale and occlusion. Singular object tracking (SOT) is an important task in human-computer interaction, anonymous tracking in the robotic application and security analysis. This paper proposes single visual tracking in a complex environment. We propose SOT using patch sparse formulation that is robust to pose, scale, log-term occlusion and low- and high- luminance conditions. A sparse dictionary using the patches from the previous frames is used to track object in the current frame under such a clutter environment. Contrast modeling, patch resizing and likelihood measurement in the proposed sparse framework allows the selection of key patches to tackle long-term occlusion and extreme illumination variation. We evaluate the proposed method on different challenging datasets involving Illumination variation, heavy occlusion and pose variation. The result analysis indicates that the proposed patch wise joint sparse occlusion and contrast (PJS-OC) tracking method outperforms other methods with the maximum precision rate is 99%. Also for the sampling value of 0.5, the proposed tracker shows excellent results compared with the other different sampling values. The proposed sparse formulation provides excellent performance in various quantitative parameters, achieving better precision and speed. The comparative analysis with state-of-art methods using the benchmark database shows the outstanding performance of the proposed method.

317

Authors: Yohanes Setiawan, Chastine Fatichah, Riyanarto Sarno

Globus Pallidus is an object in Magnetic Resonance Imaging (MRI) with severe intensity inhomogeneity and noises, such as small, low contrast, and weak boundary. Existing active contour methods fall into false boundaries while segmenting objects, which is smaller than the background like Globus Pallidus. This paper proposes a new local gaussian variational level set (NGVLS) for Globus Pallidus segmentation. We developed an energy term to create a smooth curve and prevent evolving curve into the false boundary. In the experiment, we compare NGVLS qualitatively and quantitively with existing methods such as Chan-Vese (CV), Region Scalable Fitting (RSF), Improved Region Scalable Fitting (Im-RSF), Local Pre-Fitting (LPF), and Local Gaussian Distribution Fitting (LGDF). We use Dice Similarity Coefficent (DSC) and Misclassification Error (ME) to measure the accuracy and error of the segmentation, respectively. The experiment is using 40 MRI datasets from Rumah Sakit National Hospital Surabaya, Indonesia. Qualitatively, the results show that NGVLS shows the best segmentation compared to the existing methods. Quantitatively, NGVLS achieves the highest average, minimum, and maximum value from DSC in 0.8291, 0.7119, and 0.9050, respectively. Also, NGVLS achieves the lowest average, minimum, and maximum value from ME in 0.0050, 0.0023, and 0.0155, respectively.

337

Authors: Abdelmoujoud Assabir, Jamal Elmhamdi, Ahmed Hammouch

Indoor communication system has known an exponentially growth due to high demand of wireless data service ratio. As an alternative way, the visible light zone of the electromagnetic spectrum is explored to fulfil the future wireless data traffic requirements. Among the main issues that can be handled in the visible light communication (VLC) system are the resources allocation and interferences management. In this paper, we aim to enhance the throughput of the edge user based on the joint optimization of the power and bandwidth in the VLC downlink indoor cellular network. We propose a new geometry design that alleviates the inter-cell interference (ICI) of the edge users which occurs especially in the overlapping areas between the adjacent cells. An orthogonal frequency division multiple access (OFDMA) based on the direct current optical (DCO) is regarded as the channel access protocol for supporting the multiusers at the same time. At the edge of the coverage area, we evaluate the performance of the proposed method in terms of the achievable throughput and signal-to-interference-plus-noise ratio (SINR).Furthermore, based on the least square (LS), the joint optimization of the power and bandwidth result to a parameter ρ_0 which varies between 0 and 1. The results show that the new optimization with ρ_0=0.9 depict better improvements in term of throughput 〖R(ρ_0)〗_(D,δ)=65Mbps at r_3,1=3m.We further notice that the signal-noise-ratio (SNR) is increased with ρ_0=0.9 at the expense of the error probability falling (P_z≅〖10〗^(-4)).

368

Authors: Khairiyyah Nur Aisyah, Chastine Fatichah, Riyanarto Sarno

Most of neuroimaging applications tend to still rely on expert knowledge in determining anatomies of the brain. For example in Parkinson’s disease surgery, detection of the anterior commissure (AC) and posterior commissure (PC) are still done manually by doctors. Previously, various methods have been developed related to the automatic detection of AC and PC. However, the majority of previously methods have several drawbacks, such as only compatible on T1-W or T2-W, only compatible for data with the same matrix size, and requires a time-consuming training process. This study proposes a new strategy by combining a multilevel thresholding and morphological relationships approach for automatic detection of AC and PC. The process divided into 4 main stages: preprocessing, multilevel thresholding, segmentation, and detection of AC and PC. The segmentation is performed on several anatomies of the brain including corpus callosum, fornix, and colliculus. From the experiment, it can be concluded that the use of multilevel thresholding and morphological relationship was successfully detecting AC and PC with the mean error were 1.02 mm and 1.06 mm, respectively. The proposed method can perform an automatic detection of AC and PC with simply algorithm, does not require a large of diverse data sets for the training process, without training process that takes up time, and reliable on the diversity of MRI since it is compatible for T1-W and T2-W with various matrix sizes of 256 x 256 and 512 x 512 pixels which cannot be handled by previous researches.

392

Authors: Esther Irawati Setiawan, Ferry Ferry, Joan Santoso, Surya Sumpeno, Kimiya Fujisawa, Mauridhi Hery Purnomo

The user’s feedback on healthcare services is usually based on ratings from post-service questionnaires. However, in order to get a clear view of the user's perspective, online text reviews need to be analyzed. We combined targeted and aspect-based sentiment analysis by multi-level attention to get a specific user sentiment on a target of an aspect. The multi-level attention consists of Target-level and Sentence-level attention. Our proposed framework is based on Bidirectional Gated Recurrent Unit. Bi-GRU is commonly known to have comparable results compared to LSTM while having lesser computational complexity. We also utilized Bidirectional LSTM based Character-Enhanced Token-Embedding to handle out of vocabulary words and misspelling to avoid error in detecting sentiment. We created a dataset of online healthcare reviews from 2018-2020, targeting the name of the hospital or department, with ten aspects: cleanliness, cost, doctor, food, nurse, parking, receptionist and billing, safety, test and examination, and waiting time. To improve the results of our proposed method, we calculated polarity weight to handle imbalanced aspects in the dataset. We classified these reviews into three polarities, which are positive, negative, and neutral. Based on our experiments, we achieved the best F1-Score of 88%.

416

Authors: Khamla NonAlinsavath, Lukito Edi Nugroho, Widyawan, Kazuhiko Hamamoto, Somphone Kanthavong

The growing research interest in the localization tracking system has prompted development alongside availability positioning techniques to apply to the real environment and current situation. An integrated system that can support navigation and tracking in both indoor and outdoor conditions has been equipped with location information to improve the requirement and fulfil the demand of a seamless localization system based on existing technologies. This paper proposes a system called an integrated location-aware computing system using received signal strength indicator to support the direction and location information that works together with a smart devices and integrates an indoor-outdoor environment seamlessly by combining both conditions to be the system without any obstacle. Furthermore, the technologies of indoor and outdoor will be integrated into the users. Then, they move from different conditions; the system can provide as an indicator for the complication that arises between indoor and outdoor locations, as well as location-based service technology itself. The transition between indoor and outdoor is less than 5 seconds switching at the overlapped area, the certainty value of the performance when moving from outdoor to indoor is 98.4% accuracy, from indoor moved to outdoor is 97.7% accuracy at the first floor. Moreover, having this seamless location system makes a lot of benefits to assist the users in discovering interesting things from the system, enable the seamless in real-time operation based on Android platform and providing direction maps and multi-pathways from current locations to destinations, the combination between different environments is generated with higher performance and smoothly works when users have many alternatives to choose the available signals from both indoor and outdoor technologies, transmission computation of switching from indoor to outdoor and vice versa has been decreased time consumption with excellent reliability and continuity service by proposed system.

441

Authors: Gede Angga Pradipta, Retantyo Wardoyo, Aina Musdholifah, I Nyoman Hariyasa Sanjaya

The umbilical cord is one of the important organs on the growth and development of the fetus in the womb. Umbilical cords are associated with an adverse perinatal outcome such as intrauterine deaths, preterm delivery, repetitive intrapartum fetal heart deceleration, operative delivery for fetal distress, meconium staining, and chromosomal abnormalities. Initial screening stages of the fetal umbilical cord are carried out by analyzing the coiling pattern of two umbilical arteries. In this study, we propose a relevant feature extraction for classifying this organ based on texture and morphological approach. However, this study is facing an imbalanced class problem, which leads to the inability of the traditional classifier to predict data in the minority class. To deal with the emerging issues, this study proposed a model by optimizing data and algorithmic levels using a combination SMOTE method and Multiclassifier Voting. At the data level, the SMOTE method is used to generate new synthetic data and to balance the skewed data distributions directly. Subsequently, the classification uses a multiclassifier method that combines several traditional classifier methods in making final decisions based on voting schemes. The first experiment was conducted on imbalanced and small size data with a total of 62 umbilical cord images from 3 classes namely hypercoiling, hypocoiling, and normalcoiling. The results showed the multiclassifier voting method was able to achieve the best results with an accuracy of 73%, average recall of 72%, and ROC of 48% compared to other classifier methods such as SVM, Random Forest, KNN, Naïve Bayes, and Decision Tree (C.45). However, all classifiers failed to predict the normocoiling class because of the limited amount of normocloing data in the trainning phase. Then the second experiment was carried out by adding synthetic data using the SMOTE method with the total data increasing to 111 images spread evenly in each class. The results show a combination of multiclassifier voting and SMOTE methods ultimately leading and produced higher performance than other classifiers, which yielded and accuracy of 81.4%, average recall of 80%, average precision of 81.5%, and ROC of 89.1%.

463

Authors: Abdullah Baz, Hosam Alhakami, Ebtihal Alshareef

The whole world is reeling under the brunt of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2 virus or COVID-19 disease) at present. Ever since the first case of this highly contagious virus was detected in Jinyintan Hospital in Wuhan, in December 2019, the disease has spread rapidly in Saudi Arabia and entire world. The current situation is extremely critical and as per the data released by WHO (the World Health Organisation), till 22 May 2020, there were 5,265,750 confirmed cases in the world. In Saudi Arabia alone there were 67,719 COVID-19 patients till 22 May, 2020 and the numbers continue to rise as more people get afflicted by this virus. Generating appropriate, knowledgeable and consistent estimates for the pandemic COVID-19 disease is an enormous challenge. Tackling this virus has become the key objective of both the government as well as the entire medical and scientific community across the world. Responding to the compelling contingency of COVID-19 pandemic, this research pursuit intends to develop a computational model that can be used to gauge the spread of Coronavirus and predict the most vulnerable regions that are likely to be affected by it. Furthermore, the framework of the model also analyzes the impact of Coronavirus on various societal factors. Once identified, these factors can be prioritized so as to device accurate and efficient countermeasures. For developing the expected model, the study has adopted the Fuzzy-AHP technique of computational modeling. Moreover, a decision making technique and severity analysis technique along with the prioritization Fuzzy-AHP approach has been employed to validate the efficacy of the suggested model. Through rigorous study of different models of COVID-19, the proposed framework provides the best model to use according to the social factors prevalent in a country. After evaluation through fuzzy AHP, the priority of proposed model is found to be the highest amongst the seven other models used for comparison. Though the present study is aimed at adding to the government’s initiatives to counter the current health emergency in the Kingdom of Saudi Arabia, the proposed computational model can be an effective aid for the specialists across the world working on containment strategies to minimise the spread of Coronavirus.

490

Authors: Aola Yousfi, Moulay Hafid El Yazidi, Ahmed Zellou

Schema matching is critical for applications that manipulate data across heterogeneous, autonomous and scattered data sources. We pick the schema matching approach based on the total number of data sources we wish to integrate: holistic matching approaches are ideally used for a big to a huge total number of data sources, while pairwise matching approaches are ideally used for a small to a medium total number of data sources. Nonetheless, the state of the art matching approaches obtain a very moderate (sometimes poor) matching accuracy. Furthermore, the state of the art holistic schema matching approaches proceed in a series of two-way matching steps. In this paper, we present hMatcher, an effective approach to holistic schema matching. To perform collective schema matching, hMatcher generates frequent schema elements before proceeding with the matching. To reach high matching accuracy, hMatcher employs a context-based semantic similarity measure. Experimental results on a real-world domain dataset show that hMatcher performs holistic schema matching properly, reaches a high matching accuracy (Precision=0.89;Recall=0.66;Overall=0.57), and outperforms the state of the art matching approaches in terms of matching accuracy.

514

Authors: Mohammad Dehghani, Mohammad Mardaneh, Josep M. Guerrero, O. P. Malik, Vijay Kumar

Heuristic optimization algorithms are widely used to solve problems in different fields of science. In this paper, a new game based optimization method called football game based optimization (FGBO) is presented which simulates the game of football. The population of FGBO are clubs and the variables of the problem are the players belonging to the clubs. FGBO has four phases: a) league holding, b) player transfer, c) practice, and d) promotion and relegation. The power of FGBO in solving optimization problems has been investigated on several benchmark test functions. The result of FGBO and other algorithm are obtained from implantation of these algorithms on unimodal, multimodal, and fixed-dimension multimodal benchmark test functions. Eight optimization algorithms called Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Teaching Learning Based Optimization (TLBO), Grey Wolf Optimizer (GWO), Grasshopper Optimization Algorithm (GOA), Emperor Penguin Optimizer (EPO), Shell Game Optimization (SGO), and Hide Objects Game Optimization (HOGO) have been used to compare these results. The proposed FGBO algorithm is also used to solve the energy commitment (EC) problem. Based on the simulation studies and obtained results, FGBO has a higher efficiency than a number of other algorithms. The results and data obtained from applying FGBO and other mentioned algorithms on unimodal test functions, multimodal test functions, and energy commitment problem show that FGBO is able to provide better results in comparison with other well-known optimization algorithms.

539

Authors: Marwa Sayed Moustafa, Sayed Ahmed, Amal Ahmed Hamed

Recently, deep hashing dominated single label image retrieval approaches. However, the complex nature of remote sensing images, which likely contains multi-labels, hardly benefits from the above approaches. To overcome single-label image retrieval limitations in remote sensing domain, we address this problem by proposing a multi-label remote sensing image retrieval (MLRSIR-NET) framework. Specifically, the proposed MLRSIR-NET composed of two main sub-networks: multi-level feature extraction and deep hash. The multi-level feature extraction network predicts multi-level features to exploit different levels of Convolution Neural Network (CNN (characteristics. To suppress discriminative feature representation, the multi-level features are aggregated and feed to Convolutional Block Attention Module (CBAM) to amplify the representation of relevant multi-label features. CBAM is flexibly integrated into our network with end-to-end training. The hash network stacked two fully connected layers aimed to learn multiple hashing functions to encode the feature vector into a compact hash code. Finally, we conduct experiments on two benchmarks for multi-label images: Dense Labelling Remote Sensing Dataset (DLRSD) and Wuhan Dense Labeling Dataset (WHDLD) to systematically assess the performance. The results show that the proposed framework improved the accuracy in terms of Mean Average Precision (MAP) by a considerable margin of 85.4%, 87.2%, 90.8% and 92.9% for 12-bit, 24-bit, 32-bit and 48-bit code lengths respectively on DLRSD. For WHDLD, it can be noted that the proposed framework supers the DCH by 93.8%, 98.7%, 91.9%, and 94.6% on average respectively.

560

Authors: Adiba Sabilla Ajrina, Riyanarto Sarno, Hari Ginardi, Aziz Fajar

Indonesia is one country that is rich in natural resources, both natural, marine and air resources. The existence of abundant resources is not properly utilized by the people of Indonesia. Improper use of resources will cause environmental damage. One form of environmental destruction is natural Sandy Gravel (Sirtu) mining activities in Kediri Regency. This study aims to map potential place for mining areas assessed using Geographic information system (GIS) and Multi criteria choice Making (MCDM) using Simple Additive Weighting Method (SAW), Multi Objective Optimization on the basis of Ratio Analysis Method (MOORA) and Complex Proportional Assessment Method (COPRAS). The weighting of the criteria used in this study is based on the Fuzzy Analytical Hierarchy Process (F-AHP) method. GIS is used to score the criteria and build the decision matrix needed by the MCDM method. The criteria used in this study are based on UU Republik Indonesia 4/2009. Those criteria are grouped into 3 categories which are natural factors, environmental factors, and aesthetic factors. Natural Factors have sub-criteria such as geomorphology, lithology, and hydrology. Environmental factors are comprised of vegetation, wildlife, distance from main road, distance from settlements, and population density. While aesthetic factors consist of natural features and touristic places. The results showed that from the three methods used which are SAW, MOORA and COPRAS methods, the most suitable method was the COPRAS method with 19/19 aggregation values. The order of sub-districts in Kediri Regency with the most suitable potential for Natural Sandy Gravel (Sirtu) is as follows: Kras, Bulan, Papar, Tarokan, Purwoasri, Mojo, Pare, Ngadiluwih, Kukung, Kandatel, Gampengrejo, Semen, Grogol, Plosoklaten, Ngancar, Puncu, Wates, Kepung, Kandangan.