International Journal of Intelligent Engineering and Systems

1

Authors: Santhosh Kumar Gangadharaiah, Hosahally Narayangowda Suresh

Automatic extraction of soft biometric characteristics of face image is an emerging research field in recent years. Among these soft biometrics, age estimation is very useful for several applications, like video surveillance, business intelligence, and search optimization in large databases. Generally, facial aging effects perceived in two main forms like, growth related transformations and textural variation. So, in order to generate an effective age classifier, both dimension and texture information should be used together. In this work, an age estimation system that is combination of dimension feature (Hybrid Principal Component Analysis (HPCA)) and textural feature (Log Gabor filter) for feature extraction, is used. The extracted feature values are classified by employing a multi-objective classifier named as Multi-Support Vector Machine (M-SVM). The result of the experiment shows that the proposed approach delivers a better age estimation rate on overlapping age group classes.

18

Authors: Premkumar Manoharan, Sumithira Rameshkumar, Sowmya Ravichandran3

In the field of power electronics, multilevel inverter plays a vital role for power quality improvement. The high switching frequency is used to obtain quality output waveform with a minimum amount of ripple content. The high voltage is reached by using voltage source inverter with almost zero harmonics without series connected switching devices. If the voltage level increased, the harmonic content of the output voltage waveform decreases in multistage converter. In this present work, single phase cascaded nine level inverter is designed for low powered microinverter and switching angles are produced by Selective Harmonic Elimination (SHE) technique. Each bridge in cascaded inverter will produce the output at different levels and allowing an overall nine level AC output voltage. Now-a-days, the solar photovoltaic is connected with microinverter is an efficient way of increasing the performance so that the proposed inverter derives an input from single PV module since it is module level inverter and it can provide good regulation for leads up to their rated capacity. The prototype is designed for 80W rating and the control signals are generated and processed using FPGA controller. The proposed inverter is designed and tested experimentally to verify the theoretical explanations and proposed design delivers high efficiency when compared with the conventional inverter at full load.

39

Authors: Jayapandian Natarajan

Cloud Computing reshapes the entire computing paradigm. In general, cloud computing means outsourcing available services and data storage in centralized scenario. In cloud computing task allocation is a major problem because multiple numbers of tasks are allocated to multiple numbers of processors for simultaneous processing. From the given list, tasks are queued according to the ascending order based on their duration. This paper is designed to solve the Task Scheduling problem, by using our proposed effective new approach of Backfilling algorithm. Depending upon the task duration, tasks are split into multiple threads for processing. Multiple thread tasks are processed in the basic concept of “gang scheduling” technique. Here we implement new backfilling algorithm concept to minimize the idle processing time of the processors. The existing Simple Backfilling Algorithm (SBA) is used to minimize the ideal time processing. Whereas comparatively Dynamic Cloud Scheduling using Backfilling Algorithm (DCBA) is designed to reduce the ideal time processing than SBA to carry out the process of both LQueue and SQueue simultaneously. At the outset, DCBA reduces the average waiting time. As mentioned the algorithm which is specified in the previous line that contains three level which represent the working speed of the algorithm. The first and second level of DCBA algorithm is comparatively similar to the performance of SBA algorithm. The maximum better performance was given in a queue size (q=1.5) by DCBA algorithm as compare to SBA algorithm. The existing type (Gang Scheduling) consist of two approaches namely Adaptive First Come First Serve (AFCFS) and Largest Job First Served (LJFS) that focus on non-parallel jobs with deadline. When compare to existing gang scheduling algorithm and SBA algorithm the average waiting time of DCBA has slight improvement in the loader level of the key. As the separation of the queue like LQ and SQ the waiting time and average waiting time is reduced comparatively.

57

Authors: Shriraghavan Madbushi, Rajeshree Raut, Mulpuri Santhi Sri Rukmini

In this paper, a novel method for detection of Primary User Emulation Attack (PUEA) by tagging (adding tag bits) a test signal in chaotic communication is proposed. The tagged test signal is masked by the secondary user using Lorenz chaotic attractor and sent over the channel. However, it doesn’t interfere with test signals of other secondary users. The Bit Error Rate (BER) analysis of the received test signal indicates whether the channel is free or is under PUEA. If the BER of the received signal is above the set threshold then it indicates an attack. Moreover, for the first time the concept of test signal to identify whether the channel is occupied by the primary user or an attacker is proposed. It is further suggested to compare the result of the proposed method with the database provided by Spectrum Bridge Inc. (SBI). It is worth mentioning here that the proposed method has made the use of the centralized control approach employed by the Federal Communications Commission (FCC) to combat PUEA. Simulation results in terms of the BER have been analysed and compared with other existing methods to show the efficacy of the proposed method.

76

Authors: Suyambu Karthick

Now a day the usage of Self-Organizing Networks (SONs) is increasing, because of its broad application. Unlike common networks, the SONs have the capability of reconfiguration, whenever any defect occurs in the network. However, while routing in this network, the loss of data occurs due to its security lack. Hence many researchers have presented their research for providing secure routing in various SONs. However, the security is still an issue in the routing of SONs especially in Wireless Sensor Network (WSN). Here in this paper, a novel protocol for the secure routing of WSNs has developed. The proposed protocol is named as Trust-Distrust Protocol (TDP). As per the proposed protocol, the routing is done in four stages. The initial stage is topology management using the k-means algorithm. The second stage is Link Quality Appraisal (LQA), where the quality of every network node is evaluated. The third stage is grading, in which it is based on the LQA value and a grade point is allotted to every node in the network. In the last stage, the most secure path for the routing is determined based on the grade points. The proposed protocol is tested in one of the major kinds of SONs, like WSN using the NS2. By comparing with the existing LEACH protocol, the performance is evaluated. Ultimately the proposed protocol outperformed the performance of the existing routing protocol and suggested for rounding in SONs.

93

Authors: Sadanand Ramchandrarao Inamdar, SathishBabu Basavaiah, Ravi Malleshappa Yadahalli

In Mobile Ad Hoc Network (MANET), the existing routing protocol may result in overhead and increased collisions during data transmission. In order to overcome this issue, in this paper, we propose to design a cooperation based directional routing protocol in MANET. Initially the source nodes discover neighbors by constructing the Directional Neighbour Table (DNT). Then the node with minimum transfer time is selected as best relay node. The transfer time is estimated using bio-inspired algorithm. Once the relay nodes are selected, the source node follows the Adaptive Directional Monitoring MAC (ADMMAC) protocol to transmit the data to the destination. In this technique, the nodes use the co-operative transmission mode when it requires transmitting the data packet faster. By simulation results, we show that the proposed technique minimizes the overhead and enhances the efficiency.

111

Authors: Mohamed Kasim Jannathl Firdouse, Mururgan Balasubramanian

Computed Tomography (CT) is the main source for analyzing the lung diseases and the preplanning of pulmonary surgeries. The accurate interpretation of chest CT scan makes a challenge to radiologists due to its complex visual nature. This paper proposes a novel method to segment the left and right lungs from the background of CT images to assist the pathologists for the easy and accurate diagnosis of pulmonary diseases. The segmentation of lung is a challenging task due to the anatomical difference of different people. This paper develops a novel algorithm namely successive peak based quantization transform (SPQT) to segment the lungs from the background. This method extracts 8 bit patterns from the input lung image and at last a BYTE data which is formed from 8 bit patterns is produced. Prior to SPQT lung segmentation, the lung image which may contain impulse noise is reduced into noise free one by using ‘Fuzzy Impulse Detection and Reduction Method’ (FIDRM). The novel lung image hikes the accuracy to a significant level than the existing algorithms.

132

Authors: Enumula Mahesh, Suman Maloji, Dhyapulai Nagendra Rao

Now a days Image forgery (IF) makes many problems in a society. Super Pixels Segmentation and ScaleInvariant Feature Transform based Image Forgery Detection (SPS-SIFT-IFD) has introduced to detect the forgeries in the images. The forgery region extraction algorithm replaces the features point with small SP as feature blocks and neighboring blocks that have similar local color features has been identified by the Scale-Invariant Feature Transform (SIFT) technique. Artificial Neural Network (ANN) classifier is used for better detection of forged parts in the original images. It applies the morphological operation to the merged regions to generate the detected forgery regions. The experimental results indicate that the SPS-SIFT-IFD scheme achieve much better detection results even under various challenging conditions compared with the existing Forgery Detection (FD) methods. Finally, SPSSIFT-IFD method performance is measure, in terms of Recall, Precision, False Measure, Sensitivity, Sensitivity, Accuracy and Gmean.

152

Authors: Manjula Thimsandra Ramakrishna, Raju Garudachar

Signal tracking loop in GNSS receivers play a major role of data extraction by tracking carrier phase. Under adverse signal conditions such as ionosphere scintillation, conventional tracking loops are less robust and hence are susceptible to loss of lock. Kalman filter’s inherent ability to adapt to signal conditions is one of the desirable features which improve the tracking performance. The paper analyses Linear Kalman filter technique of tracking signals in Navigation receiver under scintillation conditions and presents the improvements obtained with Linear Kalman filter based tracking method over conventional tracking method. Performance parameters such as phase error, carrier to noise ratio, correlator power and phase lock indicator are analysed in addition to highlighting the tuning merits of Kalman filter. NavIC L5 band signal modulated with simulated scintillation is used as test signal to analyse the performance of the Kalman filter based tracking method.

173

Authors: Samuel Peter James I, Ramasubramanian P, Magdalene Delighta Angeline D

The emotions of human in every part of a life are usual and unavoidable. The emotions uplift or cast down a person facing different situations in each moment. The main objective of this research work is to provide learning with emotional-based approach and to analyze the result using data mining algorithms. This paper examine how emotions involve the learners learning and the success of performance improvement of various learners under different environment that leads to the success of a learner. This study scrutinize the Emotional Intelligence (EI) and how it relates to academic performance. The key idea is to bring out different learning environments that focus on the learners’ positive emotional behavior and proceed according to the observed behavior. The proposed work uses Observe, Amend and Analysis (OAA) Method in the learning environment to enhance the learners learning and to evaluate performance using Data Mining Tools to enhance the future outcome. The experimental results show that with the proposed approach the learners learning is improved with positive emotions.

192

Authors: Pushpa Mohan, Kiran Kumari Patil

In India Rice and ragi are the two pre-eminent crops that stable’s the food of eastern and southern part of the country. These two crops mainly grown in rain fed areas, which receives heavy annual rainfall. In this scenario, Mysore district is undertaken for experiment analysis. As the region receives heavy rainfall (782mm). In this region the rainfall rate is high but the productivity of this crops are very low due to irrelevant crop cultivation. In order to overcome this concern, an advanced technology named Weighted-Self Organizing Map (W-SOM) is employed for accurate crop and weather prediction, which is the combination of both Self Organizing Map (SOM) and Learning Vector Quantization (LVQ). In this paper, the prediction accuracy is enhanced by minimizing the Within Class Error (WCE) among the clusters. Therefore, this new approach outcome shows a clear idea about suitable crop cultivation in Mysore. Experimental outcome shows that the proposed approach improved accuracy in crop and weather prediction up to 0.5-2% compared to the existing methods: SOM, Kernel-Nearest Neighbors (KNN) and Ensemble Neural Network (ENN).

208

Authors: Puttaswamy Gowda Vanajakshi, Murugavelu Mathivanan, Thangamuthu Senthil Kumaran

There is a big challenge in speech recognition system due to variability of the spoken languages and also speech signal is degraded due the environmental noise. Therefore speech recognition system requires pre-processing, which plays vital role to restore speech signal more effectively. Many challenges are there to restore the speech from different noisy environment. In this paper, proposed method is divided into two parts. First part is Kannada speech restoration, the modified wiener filter is proposed to restore the Kannada speech signal with very good speech quality. The experimental results are verified for different types of noise by varying input Signal to Noise Ratio (SNR) from -20dB to 5 decibels (dB). Second part is Autocorrelation based Kannada speech recognition system. Autocorrelation technique gives better output SNR for degraded input SNR with -20dB. The Autocorrelation is the simple method to recognize the isolated Kannada word in speech signal. This proposed technique results 100% recognition rate for male, female, with different accents.

225

Authors: Kasarla Satish Reddy, Hosahally Narayangowda Suresh

Reconfigurable Finite Impulse Response (RFIR) filter plays an important role in Software Defined Ratio (SDR) systems, whose filter co-efficient change dynamically during runtime. In this paper, Low Cost Carry Bypass adder Reconfigurable Finite Impulse Response (LC-CBA-RFIR) is introduced to perform the RFIR filter operations. DRAM-based Reconfigurable Partial Product Generators (DRPPG) consists of MUX and dual port distributed RAM, which has co-efficient to perform a FIR filter operation. With the help of Verilog code, the RFIR filter architecture was verified in Modelsim software. The same Verilog code was used to analyse the ASIC performances such as area, power and delay Area Power Product (APP), Area Delay Product (ADP) as well as FPGA performances such as LUT, flip flop, slice and frequency. After implementing ASIC and FPGA, all the performance improved in LC-CBA-RFIR method compared to the conventional methods.

246

Authors: Sunitha Mallasetty Shivamallaiah, Kwadiki Karibasappa

Nowadays, wireless communication plays a major role in sending information from one area to another in an effective way. In wireless communication, the important parameters are coverage area, power consumption, lifetime, and Black Hole (BH) detection in network with interconnected mobile nodes. Ant Colony Optimization (ACO) is used for finding shortest path in the Network. ACO helps in choosing another path, if there is any malicious node in the network. Data is secured using Dual Rivest-Shamir-Adleman (DRSA) technique and Black Hole Detection (BD) is used for identifying malicious node in the network. For efficient wireless system these parameters have been optimized, several algorithms have been applied to optimize the performance parameters and detect the BH in the network. Efficient BH identification with optimized routing algorithm is implemented in secured environment by using Dual RSA. The ACO-DRSA-BD algorithm precisely detected the BH Node (BHN) in finding the proper solution for data transmission using ACO and secured environment using DRSA. Hence, “ACO-DRSA-BD” finds proper solutions for transmitting data in the presence of BH Attacks and enhancing better performance parameters in terms of throughput, routing overhead and energy consumption.

266

Authors: Ammar Djerioui, Dehimi Ouali, Mohamed Ladjal

This paper proposes a sliding mode control strategy for hybrid power system (HPS). The hybrid power system consists of four-leg voltage source Inverter Bridge. The HPS ensures full compensation for harmonic phase currents, neutral current, reactive power compensation and unbalanced nonlinear load currents. The Sliding Mode control strategy with a three dimensional space vector modulation deals with power quality enhancement in standalone power-supply systems with the key objective to compensate for AC side load and phase disturbances that result essentially from the presence of nonlinear and unbalanced loads. The four-leg voltage source inverters play an important role by providing both balanced and unbalanced loads with clean power and balanced output voltage. The simulation results show that the performance of the four-leg HPS with the proposed control algorithm.

1

Authors: Mohcine Bouksim, Fatima Rafii Zakani, Khadija Arhid, Mohamed Aboulfatah, Taoufiq Gadi

In the last decades, 3D models have known a significant expansion, as we can see them in many fields such as computer vision, biology, augmented reality, engineering, and even medicine. They become more and more popular and accessible than ever. Due to these facts, there is an increasing need for a retrieval system, which can return the most similar 3D objects existing in the database to the query. In the present paper, a new retrieval approach is proposed, based on a multi-criteria method to generate a compact descriptor, which represents a signature for each 3D model. The key idea behind this approach is to try to extract the best out of each criterion (i.e., measure) by extracting a combined score using the Data envelopment analysis method (DEA). The results of the proposed method are very satisfactory and outperform some commonly used retrieval methods which highlight the potential and the performance of our approach.

20

Authors: Guchenko Mykola, Sokhin Natalia, Lugovyj Oleksandr, Dobiáš Václav, Čejka Jiří, Ludvík Miroslav

The actual task is to research QoS (Quality of Service) instruments in order to improve existing and develop new methods. This paper presents the modified method of double QoS, which differs from standard one by application of multi-level traffic analysis by user groups, types of traffic and priorities. The efficiency of the proposed method is proved experimentally on routers with the Mikrotik operating system by means of local computer network simulation, based on virtual machines. The experiments were conducted with generated multi-traffic with a uniform distribution for Packet Size and Internet Departure Time parameters. Compared results of router work with standard and modified methods. Using the proposed method allows reducing the number of dropped packets by simply configuring the router system tools and thus improving the quality of user service.

41

Authors: Syed Muzamil Basha, Dharmendra Singh Rajput, Vishnu Vandhan

Boosting is the method used to improve the accuracy of any learning algorithm, which often suffers from over fitting problem, because of inappropriate coefficient associated to the data points. The objective of our research is to train the data, such that the weighing error of linear classifier goes to zero and classify the sentiments accurately. In this paper, Gradient ascent approach is used to minimize the weighing error of sentiment classifier by predicting the proper coefficients to the data points in trained dataset. When compared to previous studies on designing a strong classifier, our research is novel in the following areas: Estimation of Maximum Likelihood for logistic regression using Gradient ascent and making use of weights of metric in understanding the behavior of AdaBoost algorithm in classifying the sentiments. In our finding, the first decision stump has training error of 30.44%. After thousand iterations, we observed a smooth transition, where the classification error tends to go down to 8.22% and actually stays at same value. Finally, concluding that Boosting algorithm outperforms Random Forests with lesser Mean squared Test Errors.

62

Authors: Syaifulnizam Abd Manaf, Norwati Mustapha, Md Nasir Sulaiman, Nor Azura Husin, Helmi Zulhaidi Mohd Shafri, Mohd Norhisham Razali

Observation satellites orbiting the Earth provide important surveillance information that helps in identifying various types of land cover. As such, the resolution of satellite images is critical to ensure high accuracy in classifying land cover types. Clearly, high-resolution images are desirable, but such images are prohibitively expensive. Hence, the use of medium-resolution satellite images seems more economical and practical. Several techniques have been developed to monitor the conditions of land covers across the world, such as aerial photography, ground survey, and remote sensing. Among the three techniques, remote sensing is the best, given its ability to monitor vast geographical areas more accurately and much faster compared to those of the other two techniques. In recent decades, many countries have been relying on remote sensing to monitor the conditions of coastal areas by extracting shorelines from satellite images. To date, several pixel-based methods have been proposed for the extraction of shorelines, but most of these methods are fraught with problems. Thus, the object-based approach is proposed using a combination of segmentation algorithms, namely Felzenswalb, Quickshift, and SLIC, together with 15 machine learning classifiers, to classify segmented images of Langkawi Island. The performance of the segmentation algorithms and machine learning classifiers were assessed in terms of segmentation time and overall accuracy in four experimental settings comprising of three different parameters. The research findings showed that the proposed hybridization of SLIC segmentation and Extra Tree classifier was the most efficient and accurate technique compared to other combinations of techniques in extracting the shoreline of the study area. Specifically, SLIC was faster than Felzenswalb and Quickshift by as much as 37 times and 500 times, respectively. Together with Extra Tree classifier, SLIC managed to achieve 100% overall accuracy in the object-based classification in three out of four settings compared to the rest of the techniques tested in the study.

83

Authors: Clara Kanmani Arulanandu, SumaVasu Deva Murthy, Guruprasad Nagraj

In this paper, a new secured data model for cloud computing is proposed which uses partial resource description framework (RDF) encryption and token based access control system in which sensitive data in an RDF graph is encrypted and all other non-sensitive data are publicly lucid. The security process, the decryption process, and query process are the three essential procedures in this framework. The consequence of the security process is the encrypted data, encrypted metadata, and plain text fragments. The proposed technique permits the token based access control system for the decryption procedure. The query process incorporates the map reduce framework is for lessening the immense measure of employments. At long last, the query answer is sent to the user in light of the access token list (AT-list) of the system administrator. Our test comes about demonstrate that, the performance of the proposed technique is assessed in view of the precision, recall and execution time of the framework. Our proposed approach is actualized using Java and keep running on Windows XP framework and the Lehigh University Benchmark (LUBM) datasets are used for our examination. In the paper this new secured RDF data model is deployed and tested using AWS elastic beanstalk.

104

Authors: Dhanavijayan Ramakrishnan, Sudhakar Pushparajan

This paper demonstrates an ideal procedure to find the desirable bus location and operating power of distributed generation in radial power distribution system with the aid of unified particle swarm optimization algorithm. In general, an electrical power network economics primarily relies on the conductor line losses. Hence in the proposed study, the network active power loss is picked as the minimization problem, and it is reduced by incorporating optimum distributed energy source at appropriate buses using proposed unified particle swarm optimization algorithm. The system power loss is handled as the cost function for each particle in a swarm. The simulation analysis of the purposed procedure is successfully executed for different radial distribution system using MATLAB. The prosperous solutions achieved from the simulation studies manifest that the high level of system loss reduction and desirable bus voltage profile, when compared against earlier existing methods such as genetic algorithm, particle swarm optimization, and parameter improved particle swarm optimization.

121

Authors: Swati Srivastava, Bipin Kumar Tripathi

This paper aims to develop a recognition system which incorporates a novel fusion from different areas of computational intelligence along with a proposed artificial neuron structure. Our Deep Hybrid Computational Model (DHCM) is a novel aggregation of fuzzy clustering fused with evolutionary searching and a neural network based on a proposed neuron model TROIKA. The deep architecture with evolutionary fuzzy clustering followed by hybrid neural network, built upon novel neuron TROIKA, yields a powerful tool for face recognition applications. The proposed TROIKA neuron is based on nonlinear aggregation functions which enables our hybrid neural classifier to inculcate the benefits of its computational power resulting in superior learning and generalization. The proposed TROIKA neuron reduces the complexity of DHCM because very few neurons are sufficient to recognize a subject in database. The experimental results completed on two benchmark face datasets-INDIAN and FERET datasets demonstrated the effectiveness of the proposed model. The performance comparisons revealed the outperformance of (i) TROIKA based model over conventional neuron based model (ii) proposed model over other classification methods.

142

Authors: Jayapal Joseph, Ravi Subban

Nowadays, the exploitation of images is inevitable in all the domains. However, the major issue being faced by the images is ‘noise’, which seriously affects the image quality. In order to address this issue, this article presents a novel denoising algorithm that is based on superpixel clustering and dictionary learning process. The superpixel clustering groups the similar pixels together to form a superpixel. As soon as the superpixels are computed, the sparse coefficients are computed by the steepest descent orthogonal matching pursuit algorithm. The process of dictionary updation is achieved by Discriminative K- Singular Value Decomposition (DK-SVD). The dictionary is trained by DK-SVD algorithm, as the discriminative capability of the algorithm is greater. The proposed approach shows promising results, which when compared to the existing techniques. Additionally, the time consumption of the proposed approach is very minimal than the comparative techniques.

163

Authors: Metta Venkata Satya Sairam, Mupparaju Sivaparvathi

Radio spectrum (3 KHz to 300 GHz) is a limited natural resource and efficient utilization of the spectrum can be accomplished by cognitive radio (CR). In CR, spectrum sensing is one of the significant challenging issues. Cooperative spectrum sensing (CSS) based CR is a captivating solution to enhance spectrum sensing. In CSS, multiple secondary users (SUs) report their results to fusion center (FC) and final decision is taken on the status of the primary user (PU) based on the predetermined fusion rule. This cooperative decision in CSS based CR, improves the spectrum sensing performance. Nevertheless, the foremost drawback in CSS is low throughput due to reporting time introduced by the multiple SUs. We propose a novel method to reduce the reporting time so as to enhance the throughput performance for the same number of SUs in CSS based CR. In the proposed scheme k SUs, where k is even, are divided into two groups, each with k/2 users. Two groups report their sensing results to two FCs separately and final decision is taken by the third FC. Consequently, the reporting time is condensed in the proposed scheme. The sensing performance of the proposed CSS (PCSS) for all possible fusion rules is reviewed. Analytical expressions for probability of false alarm, probability of detection and throughput are derived for PCSS. Both simulation results and theoretical analyses validate that PCSS improves throughput significantly when compared with CSS.

181

Authors: Bukka Narendra Kumar, Mantena S. V. Sivarama Bhadri Raju, Bulusu Vishnu Vardhan

With the huge development of the usage of computer over network and advancement in applications running on various platforms captures the attention towards network security. The Intrusion Detection System (IDS) plays a vital role in detecting anomalies and attacks in the network. Earlier approaches of IDS relied on Machine Learning (M L) techniques. Due to some limitations, a better approach is needed. A combination of Machine Learning techniques and data preprocessing is an effective approach for IDS. In this work, a new dimensionality reduction technique combined with the Multi-class SVM (Support Vector Machine) is proposed for intrusion detection. In the proposed model, Multi-Linear Dimensionality Reduction (ML-DR) is proposed as a feature extraction technique to reduce the dimension in order to shorten the training time. A Multi-class SVM (M-SVM) is used to detect whether the action is an attack or not. Here the Multi-class SVM is adopted to perform multi-attack classification in a layered fashion. Radial Basis Function Kernel is used as a SVM kernel. NSL-KDD data set is used for the performance evaluation of the proposed approach. The performance metrics such as classification accuracy, false alarm rate and the correlation coefficient are evaluated to measure its efficiency. In comparison with other detection approaches, the experimental results show that the proposed model outperforms the higher classification accuracy.

201

Authors: Vulapula Sridhar Reddy, Barige Thirumala Rao

In this paper, we plan a combined clustering and geometric data perturbation approach for improving privacy preservation of health care data in hybrid clouds. We will possibly plan an answer that can productively give protection to information put away in the cloud without presenting substantial overhead on both computation and communication. At first, the high-dimensional data are separated into various parts by utilizing the K-mean clustering method, each partition is considered as a cluster. At that point the mean estimate of each cluster processed; after that the contrast between the each cluster member and the mean of the cluster value is computed. In the next stage, the clustered information is perturbed by utilizing the Geometric Data Perturbation (GDP) algorithm which makes the values difficult to be recognized. These perturbed values are stored in the public cloud and the key parameters for randomizing and clustering is stored in the private cloud. Our approach would contribute in reduction of too much storage on private cloud on the off chance that we basically store the entire sensitive information on private clouds. The experimental results show that, the GDP algorithm has better privacy preserving compared with the other existing methods.

221

Authors: Megala Tulasiraman, Vivekanandan Kalimuthu

Regression testing is one among the strongest testing criteria which ensure the quality of the software under test. However, regression testing is too expensive due to execution of too many test cases .Test case prioritization is one of the traditional techniques which improve the regression testing by proposing a test case order that increases the rate of fault detection . In this paper, we propose a cost – cognizant history based test case prioritization approach that utilizes the historical information of the test cases like cost, fault identified by the test case and the severity of the identified fault for prioritization. Also an artificial immune system based, Clonal selection algorithm is proposed to find an effective test case order from existing test suite. To evaluate the proposed approach, controlled experiment were performed and the evaluation results indicates the test case order produced by proposed approach shows improvement in terms of average percentage of fault detected per cost.

239

Authors: Biswa Mohan Acharya, Ajit Kumar Nayak

Wireless multimedia sensor network (WMSN) deals with transmitting multimedia traffic over a long range in multi-hop along multiple paths. This is so for achieving the objectives of Quality of Service (QoS). In clustered routing, the load on the cluster head nodes increase and the energy consumed at the cluster head nodes lead to energy depletion of that node which degrades the network performance. The proposed protocol focuses on QoS and energy efficiency in WMSN by considering the hierarchical deployment of heterogeneous nodes. This protocol makes use of hierarchical structure of powerful cluster head nodes and the optimized multiple paths to support reliable and energy efficient multimedia transmission in WMSN. The reliability and life of the network increases because of the fault tolerance and load balanced feature of the protocol. Simulation results describe a significant performance improvement in terms of energy consumption of the nodes and the QoS parameter.

259

Authors: Calduwel Newton Pitchai, Nismon Rio Robert

Routing in Mobile Ad-hoc Networks (MANETs) is a very challenging task since, nodes are mobile and links are frequently created and broken. Traditional proactive routing algorithms initiate path discovery process from beginning after link failure occurrence. Generally, link failure occurs due to frequent topology change, fading, multiuser interference, etc., In MANETs link stability is the important criterion for link failure. Once the link meets with failure, it affects the overall performance of MANETs topology and it is very difficult to select optimum path as it leads to more transmission delay. The objective of this paper is to develop a mathematical model for Path Selection Algorithm based on Hamming Distance and delay parameters (PSA-HD). In this paper, link failure is identified, stable link is selected from the available links to reach the destination and it determines a stable path. The simulation result reveals that there is a decrease in average End-to-End delay and increase in Packet Delivery Ratio (PDR).

276

Authors: Tamilarasan Santhamurthy, Kumar Parasuraman

The cognitive radio (CR) offers keen solution to the serious scarcity of spectrum in wireless communication. In Multi-Input and Multi-Output (MIMO), primary user recruits some secondary users to cooperatively relay the primary traffic. It is very difficult to assign channel allocation and resource distribution in heterogeneous networks. We propose EPBDRA-CRN technique which provides priority scheduling scheme resulting in more reliability and efficient data transmission. The resource allocation can be done dynamically after ensuring that the nodes satisfy the specified constraints such as fairness, minimum-rate-guarantee, and minimum-delay-guarantee. Proposed EPBDRA-CRN algorithm does resource allocation and scheduling for PU and SU to exploit the performance of entire network by reducing the interference at PU. The proposal also supports different rates of transmission with priority, minimizes the transmission delay and improves fairness and provides significant network throughput and avoids collision. We compare EPBDRA-CRN with existing DRA-CRN algorithm using ns-2 simulation. The simulation result shows that the proposal is 27% more efficient than the existing DRA-CRN algorithm.

1

Authors: Neha Singh, Agrawal Kalpesh, Swathi Jamjala Narayanan

Prediction of fault proneness of modules in software is one of the ways to ensure the achievement of software quality and reliability. Software delivered cannot not always be bug free, the more the number of bug the more the dis-satisfaction among client due to degradation in software quality and reliability. Though we have few models for detecting software fault prone modules, the intend of our work is to increase the reliability of the software by using an approach named Rough Fuzzy c-means (RFCM) clustering algorithm to analyse the fault proneness of the software modules under test. This helps in an efficient analysis of the modules having an ambiguous behaviour using rough set boundary which is not possible using traditional clustering methods. A dataset from PROMISE software engineering repository has been taken for the experimental analysis. The results were promising enough to determine software modules which fall in the boundary region of ambiguity emphasizing the software team to focus on those modules to achieve higher reliable system.

20

Authors: Naradon Chotiwanaporn, Chow Chompoo-Inwai

This research paper presents the new idea of applying the transmission line teleprotection scheme called direct transfer trip (DTT) technique to use with a closed-loop distribution network. A large-scale 163MW gas turbine power plant connected to a three-substation closed-loop distribution network was chosen to be a case study here. A newly-proposed DTT configuration, DTT logic diagram and circuit breaker trip matrix had been redesigned and presented in this paper. For the proposed DTT configuration, several remote terminal units will be installed at every substation connected to the distribution network, whereas the logic controller will be installed at the selected power plant. A huge advantage over the conventionally-installed zoning peer-to-peer protection scheme is that the proposed DTT logic controller is able to almost instantaneously compute and send out the clearing faults command, regardless of fault locations in this particular closed-loop distribution network, while the conventional one cannot in many cases. Additional benefit is that the proposed DTT teleprotection scheme completely prevent the generators from operation in island mode resulting in minimal lost and damages caused from this circumstance. The relay test tool is used to verify the proposed DTT protective capabilities and speed. The simulation and commissioning test results confirm the proper functionality of the proposed technique. The implementation to the real field has been done and presented here as well. What we have learned from this case study shall be a very good guideline for other similar circumstances.

39

Authors: Bachir Bendjaima, Djamel Saigaa, Djalal Eddine Khodja

In industry, the service continuity of an electrical system drives requires degrees of reliability of operation and high safety. Thus, the system requires robust elements to avoid falling into the defects. But the appearance of defects, it is inevitable. It is therefore necessary to solve this problem by developing a control technique that can ensure continuity of operation in the presence of faults. Indeed, the sliding mode adaptive control based on fuzzy logic ensures the stability of the system healthy and able to compensate certain types of defects: the defects of low severity. In fact, is with the fuzzy sliding controller with varying control gains. This one is based on supervisory fuzzy inference system using the adaptive tune in order to improve the performance of controller in presence of current sensors faults. In addition, the sensors are the most sensitive elements and the seat of frequent faults, and play a leading role in the closed loop control. An operation of a tolerant control the default intended to compensate the default offset sensor. The developed algorithm is validated by simulation and the obtained results showed the effectiveness and the robustness of the proposed approach under different scenarios.

60

Authors: Srihari Mandava, Abhishek Gudipalli, Vidhyasagar Gorla, AmuthaPrabha Nagarajan

The harmonics injecting into power systems are increasing from day to day with the increasing use of power electronics and nonlinear loads. These harmonics are to be monitored and analyzed to measure their impact on the quality of the power flowing through the lines during normal and abnormal conditions. It is easy to measure the fundamental frequency and it’s off nominals of power signal using DFT and its extended methods when the power system frequency is stable. But, with increase in micro-grids and renewable energy sources like wind into the power network, the frequency of the power system in not stable. The DFT leads to errors in frequency estimation during this unstable state .This work uses the demodulation method for estimating the amplitudes and phase angle of fundamental frequency and its off-nominals of a power system having dynamics in frequency. This demodulation principle is part of the orthogonal frequency division multiplexing (OFDM) used for digital multi-carrier modulation.

78

Authors: Madhav Vaidya, Yashwant Joshi, Milind Bhalerao

Recognition of handwritten Marathi character/digits is comparatively a tough task as compared to English. It has several types of applications including the postal code reading and sorting, banks check amount processing. In this paper a novel feature extraction and selection method is proposed for the recognition of isolated handwritten Marathi numbers which is based on one dimensional Discrete Cosine Transform (DCT) algorithm. The scanned document is pre-processed and segmented to create isolated numerals. Features for each numeral can be calculated after normalizing the numeral image to 32 × 32 size. Based on these reduced features, the numerals are classified into appropriate groups. Neural network is used for classification of numerals based on the extracted features. The results of proposed method are compared with the results obtained using Discrete Wavelet Transform and zonal discrete cosine transform (ZDCT). The proposed approach gives improved results as compared to zonal DCT and DWT method. Experimental results shows accuracy observed for the method is 90.30% with normalized numeral image of size 32 × 32.

98

Authors: Kairat Jaroenrat, Natchamol Srichumroenrattana

One popular IP network routing protocol is OSPF (Open Shortest Path First), which uses algorithms to find its own path by calculating the path with the least weight from source to destination. As a result, the design and routing of the data flow may not meet the requirements. To meet the efficiency of cable installation and routing, the Branch Exchange for network design process was applied. With the ability to select the number of links to be exchanged with others, we can trade-off between the design efficiency and the processing time. We used the ability of the Branch Exchange method to determine a network with an efficient traffic flow distribution. We calculated the end-to-end delay time using the M/M/1 model, then analyzed the network design efficiency of 8- and 9-node networks compared to the Simplex method. For 8-, 9-, and 10-node networks, we compared the MENTOR-II method to traffic flow and network complexity. The results showed that the efficiency of the Branch Exchange method in terms of delay and cost closely align to the Simplex method but with faster calculation time. However, more exchange links (r) means a processing time closer to the Simplex method.

116

Authors: Viji Gripsy Jebaseelan, Anithalakshmi Srinivasan

Location aided routing in Mobile-Ad hoc networks are the most significant process because it limits the route search and allows routing with least messages. Due to the dynamic and uncertain infrastructure of Ad-hoc and sensor networks also creates several security issues like route misbehaviors. This paper aims to develop a new lightweight route selection scheme with the security concern. In this scheme, the routing attack targets are identified and avoided by deploying intellectual watchdog and lightweight key verification mechanisms, the scheme also utilizes the curved rectangle zone selection for shrinking route search space. The scheme is extended to adopt the curved rectangle zone routing for both Ad-hoc and Sensor Networks. The core functionality of the proposed work in terms of cost effective and secure route selection is validated by NS-2 tool. The experimental results demonstrated that the proposed approach is cost effective and secure and provides significant performance improvements with least energy consumption

134

Authors: Sindhu Babulogiah, Valarmathi Jayaraman, Christopher Sargunaraj

This paper discusses about the range estimation using multiple model method for single sensor bearing only tracking (BOT) in 3D. For BOT, the ownship is assumed to take a manoeuvre to gain observability in range and target state. The unknown target range was divided into uniform sub-intervals and nonlinear filters like Extended and unscented Kalman filter (EKF and UKF) with Cartesian and modified spherical coordinates (MSC) were implemented. Comparative results indicate that, UKF in MSC performs better with high computational time. This paper introduces Adaptive nonlinear filter (ANF) to get better range estimate with reduced computational time without affecting the filter performance. It is accomplished by conjoining Cartesian EKF with UKF in MSC, adaptively during the stationary and manoeuvring ownship conditions. The performance comparison was analysed using root mean square error, bias error and computational time. Simulation results reveal that ANF shows better results with reduced computational time.

156

Authors: Ketthari Thandapani, Sugumar Rajendran

Privacy Preserving Data Mining (PPDM) has turned into a well-known research region. Step by step instructions are adjusted between privacy assurance and knowledge discovery in the sharing procedure is a critical issue. Likewise, currently, not more strategies are accessible in the literature to hide the sensitive itemsets in the database. One of the existing privacy-preserving utility mining strategies uses two algorithms, HHUIF and MSICF to disguise the sensitive item sets so that the foes can't mine them from the modified database. This paper concentrates the privacy for the sensitive data actualize in a hybrid approach that is Optimal High Utility Item Selector (OHUIS) method. This Item Selector (IS) procedure upgrades the threshold utilizing inspired Krill Herd Optimization (KHO) method. With a specific end goal to hide the sensitive item sets, the frequency estimation of the items is changed. On the off chance that the utility estimations of the items are same, the OHUIS algorithm chooses the precise items and after that, the frequency estimations of the selected items are altered. The proposed OHUIS reduces the computation many-sided quality and also enhances the hiding performance of the item sets. The algorithm is actualized and the resultant item sets are thought about against the item sets that are acquired from the traditional privacy preserving utility mining algorithms. The test comes about demonstrate that OHUIS accomplishes the lower miss costs compared to the existing procedures for various manufactured datasets.

174

Authors: Zavli Juwantara, Maman Abdurohman, Sidik Prabowo

This paper proposes the enhancement of a selected Fuzzy Multiple Attribute Decision Making algorithm, namely Modified Multiplicative Exponent Weighting (M2EW) algorithm. The main focus of improving the Multiplicative Exponent Weighting (MEW) algorithm is to enhance the reliability of alternative vector preference calculations for selecting network candidates in a vertical handover (VHO). However, MEW algorithm has resulted in relative accuracy from each network which has not, in many cases, matched the necessary conditions. The improvement is done by calculating the Euclidean distance between the nodes represented by the weight values of each selected network candidate parameter. There are various algorithms used to support the VHO mechanism, for example an algorithm that calculates the value of each of the network selection parameters such as RSS, bandwidth or network speed such as Simple Additive Weighting (SAW) and MEW algorithm. The result shows that the M2EW algorithm has increased the relative standard deviation value by 0.2% and has shown the same delay as the MEW algorithm.

192

Authors: Eman El Sayed, Abeer El Korany, Akram Salah, Hesham Hefny

Continually, search engines improve their capabilities toward facilitating search and the retrieval enhancement. Despite the great efforts in the information retrieval field, the retrieved results may be out of user’s expectation. This may be due to the huge number of web resources, and unidentified user’s interests and domain. This paper proposes exploiting social annotations for improving retrieval based on personalization. The personalization focuses on web resources and retrieval process. In this context, new layer of knowledge is added to the web resource analysis and retrieval. Then, the additional knowledge leads to improve the retrieved results to be close to user’s interests. So, it retrieved different results for the same query based on the user’s interests. By applying the system, the experiments realize 36% precision improvement compared to non-personalized search engine. Moreover, the user satisfaction measured by evaluating search results versus user’s priorities, where it was in between 92% up to 100%.

211

Authors: Vinod Kumar, Ramjeevan Singh Thakur

High utility webpage set states to those set of webpages which have high utility value in a weblog database. To find high utility item sets from transactional databases, there exist various algorithms. However, these existing algorithms mostly deals with data like- categorical, time series, binary etc. The weblog data is different from other types of data. The utility webpages extracted from the log data can be used for knowing the user’s behaviour. In this research paper, two algorithms named HUWSM (high utility webpage sets mining) and HUWP-FP (high utility webpage sets - frequent pattern) Tree have been developed and used for efficiently mining high utility webpage sets from web log database. Along with this, a pattern generation technique based on the ‘Jaccard Similarity’ is also included in this method. The HUWSM method has also been compared with various other existing methods. This algorithm has shown a much better performance and more effectiveness over other algorithms like FHM, HUI-MINER and IHUP methods in terms of memory consumption and execution time.

230

Authors: Kotari Sridevi, Mandapati Sridhar

An unstructured version of a traditional wireless network provides a mobile ad hoc network (MANET) that is well suited for emergencies. However, due to lack of infrastructure and resource limitations, many performance problems occur at the same time. High-security vulnerabilities are likely to arise, largely because of dynamic behavior, and the complete communication cycle dependent on unidentified nodes which join and leaves as they want. Several past security schemes studies suggested that reliable and trusted nodes can minimize communication overhead and achieve higher throughput. This kind of scheme affects the route chosen for communication because it cannot distinguish between intentional and unintentional errors at runtime. It is, therefore, important to categorize node activities and also provide a node recovery scheme to regain their original reliability for the genuine nodes. In this paper, we propose a Reliable Trustworthy Approach (RTA) based on node behavior prediction for secure routing. It presents a behavior prediction algorithm for recognizing node behavior by differentiating among the unintentional transient errors and intentional malicious behavior, and the RTA mechanism which provides a method for node trust computation and a method for trust recovery. Experiment results show throughput improvisation against the malicious node intrusion. With increasing, malicious nodes in network RTA mechanism effectively predicted with an optimal packet loss and delay it attained prove the effectiveness of the mechanism.

250

Authors: Sumalatha Madugula, Panchala Venkata Naganjaneyulu, Kodati Satya Prasad

In VLSI design, performance parameters such as speed and hardware cost are important facts during the implementation of complex algorithms. In this paper, Low Cost Carry SeLect Adder Finite Impulse Response (LC-CSLA-FIR) is introduced to perform the FIR filter operations. With the help of shifter-I, shifter-II, and Shifter-III circuits, the FIR filter operation is performed without using any multipliers. In this new architecture, there is no need of storing the co-efficient in the ROM and number of multipliers. Due to the absence of multipliers, the quantity of hardware is reduced and the performance of the architecture is increase. With the help of Verilog code, the FIR filter architecture is verified in Modelsim software. After Field Programmable Gate Array (FPGA) analysis, Look Up Table (LUT), slices, flip flops, frequency and ASIC implementation area, power, delay, Area Power Product (APP), Area Delay Product (ADP) is improved in LC-CSLA-RFIR method compare to conventional methods.

273

Authors: Sharmasth Vali Yerur, Prakash Natarajan, Tiruchirai Ramanujam Rangaswamy

The open nature of Mobile Ad Hoc NETworks (MANETs) provides an opportunity for intrusions. The current intrusion mechanisms are reactive and incapable of preventing the intrusions proactively. This paper proposes the secure routing using Hybrid intrusion prevention systems against dropping and data integrity THreat (SHEATH). This proposal implements self-key and mutual-key reliant prevention and the appearance frequency based behavior certainty measurement on routing paths. The self-key prevention scheme exploits the encrypted value of the sequence number as a normal pattern and the decryption determine whether the route reply is the result of a malicious node or not. The behavior certainty measurement using distributed selection of Squad Head nodes ensures the effective observation of misuse pattern and minimum routing overhead. The data forwarding phase shares a mutual key between the communicating nodes that prevent the data integrity attacks. The simulation results confirm the efficiency of the hybrid preventive scheme against intrusions.

1

Authors: Abdelhamid El Ibrahimi, Abdennasser Baali

This contribution will verify the effectiveness of formal neural networks for predicting drought in a semi-arid region using a hybrid model of formal neural networks (ANN-MLP) and the standardized precipitation index ( SPI). Three types of models have been optimized to achieve this objective. A database consisting of SPI values, rain, temperature and potential evapotranspiration (PET) at the monthly time step was used as input for these models. These data have been standardized between 0 and 1 and subdivided into two blocks: a first block composed of 2/3 of the data for learning and a second block composed of 1/3 of the data for the test and the validation of the models. These models have been optimized with supervised learning. The activation function chosen is the logistic variant of the type sigmoid. The mean square error (RMSE), the correlation coefficient (R), the criterion of Nash-Sutcliffe (Nash) and the absolute mean error (MAE) were used to test the performance of these models. The results obtained show that the 3rd model is the most efficient. The application of neural networks for the estimation of the dryness of the Saïss Plain yielded quite good results. Indeed, the coefficients of correlation between the predicted and the measured values range from 0.63 to 0.97. It is therefore noted that the performances obtained are relatively good and could be improved by using a larger database.

19

Authors: Pallab Kumar Dey, Sripati Mukhopadhyay

Most of the data mining algorithm's application hampers due to missing attribute values. Inadequate treatment of missing values seriously affects the data mining and classification accuracy. A useful technique has been proposed to deal with missing attribute values. Rough set approach to incomplete information system has been shown. Application of discernible matrix for incomplete information to compute core and reduct has been shown. Imputation based preprocessing approach depends on relation between present attribute value and incomplete attribute value, so have to found most similar object to impute missing value. To find similar objet importance or priority should be given in core attributes, after that reduct attributes if matching occur in corresponding attributes value and other attributes may be neglected. In this paper this concept of core and reduct attributes of rough set has been utilized to fill missing values using the proposed Core Reduct Based (CRB) algorithm. Efficiency of the CRB algorithm in the completeness analysis to incomplete data has been shown by comparing its performance with other existing algorithms using some real life data sets.

38

Authors: Vimala Vellaichamy, Vivekanandan Kalimuthu

A Recommender system (RS) is an information filtering software that helps users with a personalized manner to recommend online products to Users and give suggestions about the products that he or she might like. In e-commerce, collaborative Movie recommender system assist users to select their favorite movies based on their similar neighbor’s movie ratings. However due to data sparsity and scalability problems, neighborhood selection is more challenging with the rapid increasing number of users and movies. In this paper, a hybrid Collaborative Movie Recommender system is proposed that combines Fuzzy C Means clustering (FCM) with Bat optimization to reduce the scalability problem and enhance the clustering which improves recommendation quality. Fuzzy c means clustering is used to cluster the users into different groups. Bat Algorithm is used to obtain the initial position of clusters. Lastly, the proposed system creates movie recommendations for target users. The proposed system was evaluated over Movie Lens dataset. Experiment results obtained show that the proposed Algorithm can yield better recommendation results compared to other techniques in terms of Mean Absolute Error (MAE), precision and Recall.

57

Authors: Anand Shanker Tewari, Asim Gopal Barman

This paper proposes a recommendation system (RS) that generates items recommendations to users with the help of dynamic content based filtering, collaborative filtering, association rules and opinion mining. This RS uses dynamic content based filtering for creating and continuously monitoring the changing shopping behaviour of users. The proposed approach finds other like-minded people with the target user that may cooperate with each other, in the form of items ratings using collaborative filtering. The approach uses association rule mining for the analysis of current market trend. It generates association rules only from those items that are liked by the users. Most of the people prefer to read reviews about the product, before purchasing. Almost all well-known e-commerce websites have hundreds of product reviews available, so it becomes very difficult for the user to read each and every review before buying any item. The proposed approach uses its own unique weighted opinion miner that summarizes the reviews and generates the weights for each item based on customers’ reviews. These weights help in estimating the popularity of an item among customers. This RS generates the final recommendations to users by combining the outputs from the collaborative-classifier, association rules and weighted opinion miner. The proposed RS is evaluated over live dataset using precision evaluation metric. The result shows that recommendations generated by proposed method out performed existing benchmark recommendations methods.

77

Authors: Boominathan Perumal, Aramudhan Murugaiyan

This paper presents a novel application of hypercube framework of ant colony optimization to the virtual machine (VM) placement problem, with the objective of minimizing the power consumption and resource wastage. The aim of the VM placement is to develop an optimal placement strategy to allocate the VM’s to physical servers such that the usage of physical resource is minimized. The hypercube framework of ACO differs from its usual ACO implementation in the hyperspace for the pheromone values. In other words, in the hypercube framework, the updating of pheromone values is constrained to lie between 0 to1. This constrained pheromone updating has an advantage of automatically handling the scaling of objective function values and further leads to robust version pf ACO procedure. Here, we experimentally investigate the influence of hypercube framework of ACO for virtual machine placement using three ACO variants, namely, Ant system, Max-Min Ant System, and Ant colony system.

95

Authors: Srinivasan Kuppuswamy, Balamurugan Panchanathan

Object tracking is a dynamic optimization process based on the temporal information related to the previous frames. Proposing a method with higher precision in complex environments is a challenge for researchers in the field of study. In this paper, we have proposed a novel framework for similar object tracking. In our proposed technique we are considering both PETS and Cricket video for input video sequence. The primary steps of suggested technique are preprocessing, background subtraction and segmentation, similar object detection and object tracking. In the preprocessing stage, the adaptive median filter is used to remove the noise from each frame. Next, the foreground and background images are separated and then segmentation of object is carried out by using morphological operation. For similar object detection, the recommended technique uses the modified local self-similarity descriptor and similar object tracking is done by a particle filter. The performance of the suggested technique is evaluated by means of precision, recall, F-measure, FPR, FNR, PWC, FAR, similarity, specificity, and accuracy. An experimental result shows that the proposed technique attains the maximum tracking efficiency for both videos when compared to the existing techniques.

115

Authors: Devi Thiyagarajan, Ganesan Ramachandrarao

Cloud computing is a popular subject across the IT industry, but many risks associated with this relatively new delivery model is not yet fully understood. Cloud computing is an budding information technology of data storage, of local networks (infrastructure) as well as software and has its advantages of scalability, reliability, high performance and comparatively low cost feasible solution contrast to committed infrastructures. Here, initially the data owner will encrypt the searchable index with ElGamal cryptosystem utilizing Hyper Elliptical Curve Cryptography for double encryption. The ElGamal cryptosystem is utilized for security analysis where in sharing of multiple keys between two parties are performed aiming for better security. The random integer selection in the ElGamal cryptosystem is modified based on optimization process using Modified cuckoo search (MCS). Further Hyper elliptical curve cryptography is incorporated with ElGamal cryptosystem which is utilized for encryption and decryption. Also, the hyper elliptic curve cryptography is modified using auxiliary input in the divisor calculation in order to improve security. For selecting keys, we have used Gravitational search algorithm (GSO). The retrieval process will take a two-round communication between the cloud server and the data user. The experimental results shown that, the recommended technique attains minimum storage cost and minimum computation time when compared to the existing technique.

134

Authors: Monika Verma, Vandana Dixit Kaushik, Vinay Pathak

In this paper a novel method for removing haze is given which is based on the Hue Saturation Value color model together with dark channel subtraction. Single image fog/haze removal is a challenging task due to its ill posed nature. As fog/haze increases the brightness of the images captured also increases. In the current wok, a new methodology has been used which involves the subtraction of extra image brightness from the hazy images for keeping the hue and saturation intact. It uses the information of image brightness to get the clear image by histogram equalization. Together, the three approaches of HSV color model, histogram equalization and Dark Channel Subtraction gives clear images. Experimental results are shown in comparison with the state of the art methods. The approach used in the current paper is at par with the current methodologies and the results are better than the existing approaches.

153

Authors: Veera Venkata Murali Krishna Ravinuthala, Satyananda Reddy Chinnam

Graph based keyword extraction approaches represent the text document as a graph with the words as vertices. An edge between two vertices exists only if the corresponding words are related. The effectiveness of the graph representation is dependent on how the relationship is defined between two words. Early approaches used word order, word co-occurrence and syntactic relationships. Recent graph representation approaches are using lexical association measures for defining relationship between two words. The existing relationships can only help in identifying the words which form the topics in a document. But the topics in a document essentially form a theme in the document. Theme is the central idea conveyed though the topics in a document. In this paper a new relationship is defined between the words to capture the words which convey the theme of the document. This relationship is defined using lexical association among the words in the document. Based on the relationship a graph representation of text is defined and used for extracting the words that build the theme of the document. These words are used for selecting important sentences in the document. Experiments on DUC 2002 data set indicated that the proposed keyword extraction approach improves the quality of Extractive summarization.

172

Authors: John Sahaya Rani Alex, Nithya Venkatesan

Traditional Dynamic Time Warping (DTW) technique find similarities between two one-dimensional time series sequence. Initially, in earlier decades, DTW was not preferred because of its computational complexity. However, due to the evolution of computing power, this has been revisited for spoken keyword detection recently. Conventional spectral features such as Mel-Frequency Cepstral Coefficients (MFCC) and contemporary wavelet features are multi-dimensional in nature which are used in speech recognition. In this work, a new strategy of DTW is proposed to work with multi-dimensional feature vector in calculating the local distance matrix. Additionally, a faster approach is specified to find the similarity in the global distance matrix. The proposed methods are evaluated with MFCC and wavelet features on a connected TIDIGITS corpus for spoken keyword detection system. Experimental results prove that there is an improvement in reduction of computational complexity compared to traditional DTW. Also, contemporary wavelet feature based spoken keyword detection system gave better detection accuracy than MFCC based spoken keyword detection system in the noisy environment.

191

Authors: Azzeddine Dahbi, Siham Jabri, Youssef Balouki, Taoufiq Gadi

Using the association rules in datamining is one of the most relevant techniques in modern society, aiming to extract the interesting correlation and relation among sets of items or products in large transactional databases. The huge number of extracted association rules represents the main problem that a decision maker can face. Hence, the knowledge post-processing phase becomes very important and challenging to define the most interesting association rules, many interestingness measures have been proposed. Currently, there is no optimal measure that can be selected to evaluate the extracted association rules. To bypass this problem, we propose an approach based on multi-criteria optimization aiming to find a good compromise without excluding any measures. The experiments performed on numerous benchmark datasets show that the proposed algorithm is properly reducing a large number of association rules and keeping the most significant and interesting ones compared to other approaches which illustrate the efficiency and the applicability our approach.

210

Authors: Nophanut Katephap, Sunpasit Limnararat

This research investigates the operational, economic and environmental advantages of the returnable packaging under various reverse logistics arrangements, in relation to the disposable packaging. The business under study is a Thai manufacturer and exporter of automotive parts with the trading partners in the Philippines and Vietnam. In the study, a switch was made from the currently disposable packaging to the standardized returnable packaging under three reverse logistics arrangements: the single-, round- and multi-trip arrangements. Due to the large initial investment associated with the returnable packaging, a mathematical model was proposed to calculate the total effective packaging cost. The research findings revealed that the multi-trip reverse logistics arrangement was most operationally and environmentally viable, with the largest total packaging cost reduction and packaging waste reduction of 61% and 68%, relative to the disposable packaging. Meanwhile, the single-trip reverse logistics arrangement was most favorable economically due to its shortest payback period of 0.33 year. Moreover, the life cycle assessment (LCA) was applied to the disposable and returnable packaging to evaluate the environmental impacts throughout their lifetime. The LCA results validate the more environmentally-friendly nature of the returnable packaging.

231

Authors: Mohanaprasad Kothandaraman, Jeet Kiran Pawani, Arulmozhivarman Pachaiyappan, Sankar Ganesh Sankaran

In this paper a PEVD (Polynomial Eigen Value Decomposition) based adaptive kalman filter is proposed for Acoustic Echo Cancellation (AEC) in the presence of noise. Acoustic echo is the phenomenon when the speaker listens to his own voice after some delay while speaking to his fellow mate on a call. The presence of acoustic coupling between the loudspeakers and the near-end microphone signal produces an undesired acoustic echo, which reduces the speech quality. Existing AEC system implemented adaptive kalman filter which results in less output efficiency in the noisy environment. In the proposed method, the near end speech is separated from the acoustic echo as well as from the surrounding noise by using PEVD based adaptive kalman filter. Initially mixed microphone signal is pre-processed by Polynomial Eigen Value Decomposition which strongly de-correlates the signal and also de-correlates out the noise. The pre-processed signal is passed through adaptive kalman filter for estimation of the acoustic echo. The efficiency of the output is calculated using Echo Return Loss Enhancement (ERLE). If the ERLE lies in the range of 30-40 dB indicates the good echo cancellation. The simulations show that the proposed PEVD based adaptive kalman method provides higher cancellation of echo. The simulations are being carried out in Matlab 2016a.

247

Authors: Parvathy Madhukumar, Ganesan Ramu, Balaji Veerasamy, Felix Joseph

Turbo decoding for the advanced 4GPP-LTE wireless communication standard is the most challenging technique in terms of computational complexity and power consumption of corresponding cellular devices. The standard VLSI implementation of turbo decoder requires memory, latency, area, power, and throughput. These particularities cannot tolerate in some applications as well as the previous method of floating point has some pitfalls due to this; the performance is degraded. The novel fixed point technique for SISO parallel advanced long-term evolution turbo decoders with new hard-wried 6144 bit interleaver is proposed here to achieve the specification. The major contribution of the planned methodology is the enhancement of throughput in parallel SISO decoders by eliminating the critical data path problem in floating point method. The signal to noise ratio is calculated to reduce the power consumption, and zero state metrics are used to eliminate the bit error rate. The designed algorithms are used to enhance the error correction capacity.

267

Authors: Shankar Ramasamy, Karthikeyan Eswaramoorthy

Voice over Inter Protocol (VoIP) empowers in the integration of voice data over IP networks, minimizing the cost of network transmission for helping users of IP protocol. Robust and effective procedure of handoff is introduced for increasing the quality and the dependability of the networks. Ant Colony Optimization (ACO) is presented for the handoff mechanism and Mean Opinion Score (MOS) is observed to be the fitness value for obtained measurements of the assessment of voice quality. In this research, the scheme of Multiplex-Multicast (M-M) is proposed that will improve the capability of VoIP in WLAN to 100% in the form of an infrastructure Basic Service Set (BSS). This research work deals with the security features of VoIP in order to enhance the quality making use of Verifiable Secret Sharing (VSS) with the help of M-M scheme. The M-M scheme will eliminate the downlink VoIP traffic ineffectiveness through the multiplexing of the packets from different VoIP streams into one multicast packet for transmitting over the WLAN. The results from simulation indicate the advancements in the security enhancements making use of the proposed schemes. The average Round Trip Time (RTT) results of the proposed VSS with M-M are 0.30436 milliseconds, whereas average RTT is 0.3598 milliseconds and 0.43604 milliseconds for VSS and Shamir SS methods respectively. It concludes that the proposed VSS with M-M takes lesser RTT results when compared to existing methods.

1

Authors: Sreesudha Parnapalli, Barooru Lakshmi Malleswari

In the late years, MIMO MC-CDMA approach has been proposed in order to expand framework capacity over frequency-selective wireless channels. The key component of MIMO MC-CDMA is the capacity of abusing diversity jointly in time, frequency and in the space domain. In this work, we implement an efficient multi-user STBC MC-CDMA transmission System Based on Minimum Conditional BER Criterion and Oppositional krill herd algorithm (OKHA) assisted channel estimation. The multiuser MC-CDMA system using Alamouti’s Space-Time Block coding for encoding the transmitting sequence. The estimation of Channel State Information (CSI) is optimally selected using OKHA. Normally, KHA is a natural-inspired metaheuristic algorithm which mimics the herding behavior of ocean krill individual. To improve the convergence speed and accuracy of the basic KHA algorithm, in this proposed work we combine KHA with oppositional based learning (OBL). The experimental results are conducted for the different algorithm based on BER, SER, and spectral efficiency. The simulation results show that the proposed algorithm is properly reducing the BER, SER and properly increase the spectral efficiency value compare to other techniques.

18

Authors: Gadekallu Thippa Reddy, Neelu Khare

Huge amount of medical data is available today. In order to predict the disease we need a reliable method to diagnose the disease. In this paper we introduce a technique known as FFBAT-ANN prediction algorithm which is categorized as Feature reduction and Diabetes disease classification and such a process is carried out using LPP algorithm and FFBAT- artificial neural network classifier respectively. Initially, LPP algorithm is employed to produce fuzzy rules by recognizing the attributes corresponding to the diabetes disease. Later on, the classification is carried out by blending FFBAT optimization technique with Artificial Neural Network classifier. Finally, the experiment is performed on diabetes dataset. The experimental result proves that the performance of our proposed method outperforms the other conventional methods.

41

Authors: Hady E. Abdel-Maksoud, Mahmoud M. Khater, Shaaban M. Shaaban

Aiming to improve the control performance in the switched reluctance (SR) motor drives, this paper presents a simple nonlinear mathematical model of SRM. The model depends on describing the characteristic data obtained from finite element analysis (FEA) in a simple parametric formula. An adaptive fuzzy logic PI controller is used with the suggested model in speed control drive system. The controller is designed based on Mamdani type with nine control rules along with Gaussian function memberships. The control technique is implemented and tested under different operating conditions as well as its results are compared with those of conventional PI controller. Both control schemes operate in pulse width modulation (PWM) control mode. The proposed adaptive fuzzy logic PI improves the motor speed performance in terms of tracking precision and travel time.

60

Authors: Shounak Rushikesh Sugave, Suhas Haribhau Patil, B. Eswara Reddy

Software testing is required to detect the faults and to ensure the quality of the software under development. Usually, test suites are used to evaluate the software system during the software development cycle. But often test suites contain more redundant test cases due to overlapped test objectives. So, the test-suite reduction is an important step to reduce the number of test cases so as to satisfy the entire objectives with less computational cost. Literature presents different methods to select the suitable test suites of optimal subsets for regression testing. Accordingly, this research aims to develop an effective test suite reduction approach for regression testing. The proposed algorithm (GTAP) is newly designed using TAP measure and greedy search algorithm. This algorithm uses TAP-measure which is specially developed for measuring the importance of test cases. The performance of the GTAP algorithm is evaluated using four different evaluation metrics with eleven subject programs available in SIR repository. From the experimentation, the average performance of the proposed GTAP algorithm in all the programs is 93.07% which is higher than the DIV-GA which obtained the value of 90.27%.

81

Authors: Sharmasth Vali Yeruru, Tiruchirai Ramanujam Rangaswamy

The distinctive aspect of Mobile Ad Hoc Networks (MANETs), including dynamic network topology, susceptible wireless medium, limited battery power, network overhead are highly vulnerable and remains as major issues in designing Intrusion Detection Systems (IDS). This paper proposes a framework of Anomaly IDS with Subjective logic based Trust (AID-ST) system to discern and eradicate the intruders from the network. AID-ST system incorporates multi-dimensional trust parameters and subjective logic theory to effectively detect and confirm the attack behavior. The system measures indirect trust of a node using subjective logic theory, and IDS estimates trustworthiness of a suspected node by collecting and combining the evidence from various observers. The simulation results depict that the AID-ST attains high performance in terms of detection accuracy, overhead, and energy consumption when compared to existing AIPD AODV.

100

Authors: Mahendra Pratap Singh, Sanjay Kumar Dubey

Anaemia is a serious health condition caused primarily by deficiency of iron in the body. In India cases of anaemia are on an alarmingly high rate affecting pregnant women, men and children alike. Malnutrition has been identified as the primary cause of iron deficiency. The treatment of anaemia can be accomplished by adhering to a stringent diet plan containing all the critical nutrients in the right amount. This makes it a complex process to pick the most relevant diet plan among all the available ones. Our objective here pertains to determining the best diet plan for anaemia patient and to procure this we are employing Analytic Hierarchy Process (AHP) in the proposed paper. Diet recommendation for anaemia patient using AHP is relatively new, making this work as unique. The results obtained show the best diet among the available ones that must be recommended to an anaemia patient. This diet contains all the meals that must be consumed at breakfast, lunch and dinner by an anaemia patient. The proposed work is further validated using Fuzzy Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS). The results obtained after validation are exactly the same as determined using AHP.

117

Authors: Fakhriy Hario, I Wayan Mustika, Adhi Susanto, Sholeh Hadi, Sevia M Idrus

Nonlinearity characteristic in OFDM (Orthogonal Frequency Division Multiplexing)-RoF (Radio over Fiber) system which causes the frequency shift of light and has a high electrical field on medium transmission. We begin by discussing SPM (Self Phase Modulation) and GVD (Group Velocity Dispersion) are part of nonlinear characteristic. SPM induced spectral broadening will be degrade performance of light wave and GVD will be impact on duration pulse of optic. The impaired information signal reduces the power and later affects the quality of signal. This research aims to focus on the improvement of two external modulator LiNbO3 MZM (Lithium Niobate-Mach Zehnder Modulator) and applying of frequency dithering techniques to reduce the existing nonlinearity of the optical fiber purposely to enhance the receiving power for the lower input power with the length of fiber up to 100 km. Finally, the result shows an average of 18.5% increase in the power level for linewidth of 1 MHz, 3 MHz, and 7 MHz across 50 km distance with the log BER (Bit Error Rate) -2.407, BER 0.003, and SNR (Signal to Noise Ratio) 43.8, across 100 km of optical fiber the value of log BER -2.471, BER 0.003, and SNR 49.14.

135

Authors: Thaksin Sangsuwan, Teerawat Thepmanee, Amphawan Julsereewong

Detailed knowledge of how to balance between safety and availability for instruments is essential to successful design and implementation in fieldbus-based process control systems. The configuration correctness is crucial to actually obtain the benefits of digital fieldbus technology used. In actuality, a number of device parameters must be set to provide the required functionalities. This paper focuses on improving safety and availability for the proportional-integral-derivative (PID) and cascade control strategies using Foundation Fieldbus (FF) with control in the field. The aim of this paper is to analyze the logical behaviors of PID and cascade loops in two conflicting purposes for studying how different configuration options affect the interlocks between function blocks located in instruments as well as the initialization and fail-safe mechanisms in response to invalid measurements. For safety purpose, the interested control loops are configured to bring the process to a safe state in the presence of a fault. For availability purpose, the interested control loops are configured to keep the process running in the event of a failure. A water tank process is utilized as a case study for control loop implementations. Interactions between the status propagation and mode shedding for demonstrating the studied control loop behaviors are examined experimentally in Petri net models. In addition, the function block options for bumpless transfer and setpoint tracking are also described. The proved configuration method for proper operations in balancing the interests of safety and availability is proposed.

157

Authors: Theagarajan Senthil, Balasubramanian Kannapiran

Energy conservation is the major concern of Wireless Sensor Networks, as the energy is the determining factor of the network lifetime. The reason is that the energy level of sensors has a great impact on the network lifetime. Several mechanisms have been proposed to minimize the energy consumption of nodes. In this paper, a cluster based, trustworthy topology management mechanism is presented and is proved to be energy efficient. The entire work relies on three important phases and they are cluster formation, chief node selection, trust degree computation and node’s state control. The cluster is formed by taking the location coordinates into account. This is followed by the selection of chief node. The chief node is responsible for computing the trust degree and to control the state of the constituent nodes. As limited count of nodes is involved in the process, the lifetime of the network is considerably improved. Finally, the proposed work is tested for its efficacy and the experimental results are satisfactory with respect to network lifetime.

175

Authors: Shyamala Loganathan, Renuka Devi Saravanan, Saswati Mukherjee

A cloud system uses virtualization technology to provide cloud resources (e.g. CPU, memory) to users in form of virtual machines. Job requests are assigned on these VMs for execution. Efficient job assignment on VMs will reduce the number of hosts used. Hence, it is essential to achieve energy optimization in cloud computing environments. Therefore, in this paper, a job scheduling mechanism is proposed to assign job to a VM of the existing active hosts itself by considering job classification and preemption. So that minimizing the number of host used in allocation intern reduces the energy consumption in the Cloud datacenter. In our proposed job scheduling algorithm, categorizing the job in to three different types and assigned based on preemption policy with the earliest available time of the resource (VM) which is attached to a host. Thereby, we reduce the energy consumption by making less number of hosts in the active state and increase the utilization of active host. Finally, we conduct simulations using CloudSim and compare our algorithm with other existing methods. Significant energy savings can be obtained depending on system loads. Energy saving is about 2% to 46% with respect to the non-energy aware algorithm, 1% to 7% than the energy aware algorithms.

193

Authors: Vangapelli Sowmya, Bulusu Vishnu Vardhan, Mantena S.V.S. Bhadri Raju

Semantic Textual Similarity (STS) measures the degree of semantic equivalence between two segments of text, even though the similar context is expressed using different words. The textual segments are word phrases, sentences, paragraphs or documents. The similarity can be measured using lexical, syntactic and semantic information embedded in the sentences. The STS task in SemEval workshop is viewed as a regression problem, where real-valued output is clipped to the range 0-5 on a sentence pair. In this paper, empirical evaluations are carried using lexical, syntactic and semantic features on STS 2016 dataset. A new syntactic feature, Phrase Entity Alignment (PEA) is proposed. A phrase entity is a conceptual unit in a sentence with a subject or an object and its describing words. PEA aligns phrase entities present in the sentences based on their similarity scores. STS score is measured by combing the similarity scores of all aligned phrase entities. The impact of PEA on semantic textual equivalence is depicted using Pearson correlation between system generated scores and the human annotations. The proposed system attains a mean score of 0.7454 using random forest regression model. The results indicate that the system using the lexical, syntactic and semantic features together with PEA feature perform comparably better than existing systems.

217

Authors: Samarth Borker, Sanjiv Bonde

This paper proposes a novel method for underwater image enhancement algorithm using Principal Component Analysis (PCA) fusion. For fusion process, the dual images are derived using single underwater degraded image. The novelty of this work is the fact that it does not demand any underwater scene parameters beforehand and is independent of prior based information. Secondly, we demonstrated the successful use of homomorphic filter and adaptive histogram equalization for individual color channels followed with image smoothing as two inputs to fusion scheme. The fused image is subsequently post-processed using color constancy technique for effective results. The visual and quantitative analysis of this method is carried out with contemporary underwater dehazing and enhancement algorithms. Metrics such as entropy and quantification of restored edges is utilized to validate our findings. The outcome reveals better exposure of dark areas, enhancement of edges, increase in overall contrast and preservation of natural colors.

235

Authors: Jay Prakash, Rakesh Kumar, Jai Prakash Saini

Mobile Ad-hoc Networks (MANETs) find numerous applications. Its utility can be extended by integrating it with Internet. Some real-life applications where such integrated networks can be used are disaster situation viz., earthquake, battle fields etc. MANETs are dynamic topology, infrastructure less and standalone networks of wireless mobile nodes. To overcome this limitation, MANET needs to connect to the Internet. In such networks, mobile nodes do not have wired connection, so they do not follow any particular route to transfer their packets. Thus, every time when topology changes, routing paths changes too. However, every node selects the shortest path to route their packet. In that case, this path will be congested due to overload. We propose a load balancing adaptive Internet gateway discovery approach which focuses on solving the problem of overload and congestion in mobile ad-hoc domain. Particle Swarm Optimization is used for selecting an optimal path among all paths available. Our work is to optimize this load balancing problem. We are using Particle Swarm Optimization (PSO) concept to overcome this problem. In our approach, we use soft computing technique viz., working procedure of PSO algorithm which searches the optimal paths using some mathematical function. Then, we combine shortest path algorithm with the gateway discovery algorithm. Thus, the algorithm first selects the shortest path stored in the memory and check whether it is free for routing packets or not, if the route is free or lightly loaded, then the source node will transfer packets otherwise if the node is overloaded, then PSO searches for the next optimal neighbour or node to route the packet. The new path is selected to route packets and stored in the place of current available path. Proposed algorithm has been implemented in MATLAB. Our approach outperforms the existing approaches.

256

Authors: Santhi Kannan, Saravanan Ramakrishnan

Cloud technology is broadly supported by healthcare organizations worldwide. Throughout the previous few years, healthcare industries have recognized the potential of cloud computing architecture and how it can assistance them to give quality services to patients. The cloud technology has faster the way healthcare industry can use or share information crossways a network. This paper offering an e-health solution founded on healthcare information systems joined with cloud computing concept emphasis on medical information processing. Our proposed work based on public cloud and request management application has been proposed and analysed in terms of waiting time defined as Quality of Service criteria (QoS). The service of the public cloud has been modelled using queueing theory as two serially connected queues (Tandem Queues) M/M/s and single server retrial queue (SSRQ). The results obtained in our proposed model are considerably reducing the total waiting time of different class of units in the cloud system than the existing system and more utilization of service in cloud.

274

Authors: Kavita Bhatnagar, Subhash Chander Gupta

Our previous article has proposed a simulation model to explore the nonlinear relationship between the nonlinear regime of the fiber, laser intensity and the error probability of the optical link. This paper extends the model to include the effective area of the fiber. In order to handle the extended parameter, time series feed forward neural network based prediction model is proposed. The reliability of the model is substantiated by extensive experimental analysis through which the relationship exhibiting between the laser intensity and the corresponding nonlinear regime and effective area of the fiber can be observed. The observed results demonstrate the performance of the prediction model in estimating the launch power to meet the desired error probability under varying nonlinear regime and effective of the fiber.