E-Book, Englisch, Band 712, 722 Seiten
Bhateja / Tavares / Rani Proceedings of the Second International Conference on Computational Intelligence and Informatics
1. Auflage 2018
ISBN: 978-981-10-8228-3
Verlag: Springer Nature Singapore
Format: PDF
Kopierschutz: 1 - PDF Watermark
ICCII 2017
E-Book, Englisch, Band 712, 722 Seiten
Reihe: Advances in Intelligent Systems and Computing
ISBN: 978-981-10-8228-3
Verlag: Springer Nature Singapore
Format: PDF
Kopierschutz: 1 - PDF Watermark
The volume contains 69 high quality papers presented at International Conference on Computational Intelligence and Informatics (ICCII 2017). The conference was held during 25-27, September, 2017 at Department of Computer Science and Engineering, JNTUHCEH, Hyderabad, Telangana, India. This volume contains papers mainly focused on data mining, wireless sensor networks, parallel computing, image processing, network security, MANETS, natural language processing, and internet of things.
Vikrant Bhateja is Associate Professor, Department of Electronics & Communication Engineering, Shri Ramswaroop Memorial Group of Professional Colleges (SRMGPC), Lucknow and also the Head (Academics & Quality Control) in the same college. His area of research include digital image and video processing, computer vision, medical imaging, machine learning, pattern analysis and recognition, neural networks, soft computing and bio-inspired computing techniques. He has more than 90 quality publications in various international journals and conference proceedings. Prof. Bhateja has been on TPC and chaired various sessions from the above domain in international conferences of IEEE and Springer. He has been the track chair and served in the core-technical/editorial teams for international conferences: FICTA 2014, CSI 2014 and INDIA 2015 under Springer-ASIC Series and INDIACom-2015, ICACCI-2015 under IEEE. He is associate editor in International Journal of Convergence Computing (IJConvC) and also serving in the editorial board of International Journal of Image Mining (IJIM) under Inderscience Publishers. At present he is guest editors for two special issues floated in International Journal of Rough Sets and Data Analysis (IJRSDA) and International Journal of System Dynamics Applications (IJSDA) under IGI Global publications. João Manuel R.S. Tavares graduated in Mechanical Engineering from the University of Porto - Portugal (1992); MSc in Electrical and Computer Engineering, in the field of Industrial Informatics, University of Porto (1995); PhD in Electrical and Computer Engineering, University of Porto (2001). From 1995 to 2000 he was a researcher at the Institute of Biomedical Engineering (INEB). He is co-author of more than 350 scientific papers in national and international journals and conferences, co-editor of 18 international books and guest-editor of several special issues of international journals. In addition, he is Editor-in-Chief of the Computer Methods in Biomechanics and Biomedical Engineering: Imaging ' & ' Visualization (CMBBE: Imaging ' & ' Visualization); Editor-in-Chief of the International Journal of Biometrics and Bioinformatics (IJBB); Co-Editor-in-Chief of the International Journal for Computational Vision and Biomechanics (IJCV' & 'B); Co-Editor of the Lecture Notes in Computational Vision and Biomechanics (LNCV' & 'B); Associate Editor of the EURASIP Journal on Advances in Signal Processing (JASP), Journal of Engineering, ISRN Machine Vision, Advances in Biomechanics ' & ' Applications, and of the Journal of Computer Science (INFOCOMP), and reviewer of several international scientific journals. Since 2001, he has been Supervisor and Co-Supervisor of several MSc and PhD thesis and involved in several research projects, both as researcher and as scientific coordinator. Additionally, he is co-author of 3 international patents and 2 national patents. His main research areas include Computational Vision, Medical Imaging, Computational Mechanics, Scientific Visualization, Human-Computer Interaction and New Product Development.B. Padmaja Rani is a Professor in Computer Science and Engineering Department at JNTUH College of Engineering, Hyderabad. Her interest area is information retrieval embedded systems. She has published more than 25 papers in reputed journals and conferences in the areas of agile modeling, web services and mining, etc. She was the former Head of Department of CSE, JNTUH. She is a professional member of CSI. V. Kamakshi Prasad is a Professor of Computer Science and Engineering Department at JNTUH College of Engineering Hyderabad. He completed his PhD in speech recognition from IIT Madras, India. He did his M.Tech. from Andhra University and B.Tech. from K.L. College of Engineering. He has completed over 12 years in JNTU on various positions. He has 21 years of teaching and 11 years of research experience. Dr. Prasad has been teaching subjects like speech processing, pattern recognition, computer networks, digital image processing, artificial neural, artificial intelligence and expert systems, computer graphics, object oriented analysis and design through UML, and soft computing. He has supervised 12 PhD and 2 MS students. His research areas are speech recognition and processing, image processing, neural networks, data mining and ad-hoc networks. He has authored two books published by Lambert Academic Publishing and over 50 papers in national and international level journals.K. Srujan Raju is the Professor and Head, Department of CSE, CMR Technical Campus, Hyderabad, India. Prof. Raju earned his PhD in the field of network security and his current research includes computer networks, information security, data mining, image processing, intrusion detection and cognitive radio networks. He has published several papers in refereed international conferences and peer reviewed journals and also he was in the editorial board of CSI 2014 Springer AISC series; 337 and 338 volumes. In addition to this, he has served as reviewer for many indexed journals. Prof. Raju is also awarded with Significant Contributor, Active Member Awards by Computer Society of India (CSI).
Autoren/Hrsg.
Weitere Infos & Material
1;Preface;6
2;Organizing Committee;8
2.1;Conference Chair;8
2.2;Organizing Chairs;8
2.3;Technical Chairs;8
2.4;Technical Co-Chairs;8
2.5;International Advisory Committee;9
2.6;Advisory Committee;9
2.7;Publication Chair;9
2.8;Editorial Board;10
2.9;Organizing Committee;10
2.10;Technical Committee;10
2.11;Web and Publicity Committee;10
3;Contents;11
4;About the Editors;17
5;1 Efficient Video Indexing and Retrieval Using Hierarchical Clustering Technique;19
5.1;Abstract;19
5.2;1 Introduction;19
5.2.1;1.1 Information Retrieval Based on the Content;20
5.3;2 Existing System;20
5.4;3 Proposed System;21
5.4.1;3.1 Advantage of Proposed Technique;21
5.4.2;3.2 Proposed Architecture;21
5.4.3;3.3 Proposed Algorithm;22
5.5;4 Experimental Setup;22
5.5.1;4.1 Image Elements Extraction;22
5.5.1.1;4.1.1 Pseudocode for Color Histogram Calculation;22
5.5.2;4.2 Indexing of Images;23
5.5.3;4.3 Image Retrieval Using Clustering Technique;23
5.5.3.1;4.3.1 Psecudocode for Cluster Calculation;23
5.6;5 Experimental Outcomes;23
5.7;6 Conclusion;25
5.8;References;26
6;2 A Data Perturbation Method to Preserve Privacy Using Fuzzy Rules;27
6.1;Abstract;27
6.2;1 Introduction;27
6.2.1;1.1 Privacy Preserving Data Mining;28
6.2.2;1.2 Data Perturbation in PPDM;28
6.3;2 Background and Related Work;29
6.4;3 Data Perturbation Using Fuzzy Logic;30
6.4.1;3.1 Fuzzy Rule Based Systems;30
6.5;4 Proposed Work;31
6.5.1;4.1 Proposed Algorithm;32
6.6;5 Results;32
6.7;6 Conclusion;33
6.8;References;33
7;3 An Enhanced Unsupervised Learning Approach for Sentiment Analysis Using Extraction of Tri-Co-Occurrence Words Phrases;35
7.1;Abstract;35
7.2;1 Introduction;36
7.3;2 Associated Work;37
7.4;3 Proposed Model;38
7.4.1;3.1 Steps for Preprocessing Dataset;38
7.4.2;3.2 Extract Phrase Patterns;39
7.4.3;3.3 Computation of Semantic Orientation;40
7.4.4;3.4 Pseudocode Procedure for Implementation;41
7.5;4 Results and Discussions;42
7.6;5 Conclusion and Future Scope;43
7.7;Acknowledgements;43
7.8;References;43
8;4 Land Use/Land Cover Segmentation of Satellite Imagery to Estimate the Utilization of Earth’s Surface;45
8.1;Abstract;45
8.2;1 Introduction;45
8.3;2 Related Work;46
8.4;3 Study Area;47
8.5;4 Dataset and Methodology;47
8.5.1;4.1 Dataset Description;47
8.5.2;4.2 Methodology;48
8.6;5 Algorithm;50
8.7;6 Implementation and Performance Analysis;51
8.8;7 Conclusions;53
8.9;References;54
9;5 Grammar Error Detection Tool for Medical Transcription Using Stop Words Parts-of-Speech Tags Ngram Based Model;55
9.1;Abstract;55
9.2;1 Introduction;56
9.2.1;1.1 Prior Work;57
9.3;2 Research Method;58
9.3.1;2.1 Training Stage;59
9.3.2;2.2 Testing Stage;61
9.3.3;2.3 Data Statistics and Parameter Setting;63
9.4;3 Results and Analysis;64
9.5;4 Conclusion;65
9.6;References;66
10;6 Churn and Non-churn of Customers in Banking Sector Using Extreme Learning Machine;68
10.1;Abstract;68
10.2;1 Introduction;68
10.3;2 Literature Survey;69
10.4;3 Methodology;70
10.4.1;3.1 Extreme Learning Machine;70
10.4.2;3.2 Algorithm;72
10.5;4 Results and Discussions;72
10.6;5 Conclusions;74
10.7;References;74
11;7 Identifying the Local Business Trends in Cities Using Data Mining Techniques;76
11.1;Abstract;76
11.2;1 Introduction;76
11.3;2 Related Work;78
11.4;3 Proposed Work;79
11.4.1;3.1 Data Preprocessing;79
11.4.2;3.2 Vector Representation;80
11.4.3;3.3 Clustering;80
11.5;4 Experimental Results;80
11.5.1;4.1 Dataset Description;80
11.5.2;4.2 Data Preprocessing;81
11.5.3;4.3 Vector Representation;82
11.5.4;4.4 Clustering;82
11.5.5;4.5 Discussion;82
11.6;5 Conclusion and Future Work;83
11.7;References;84
12;8 Relative-Feature Learning through Genetic-Based Algorithm;85
12.1;Abstract;85
12.2;1 Introduction;85
12.3;2 Relative-Feature Learning Algorithm;87
12.3.1;2.1 The Adaptive Propagation Planning;88
12.3.2;2.2 Controls Identified in the Adaptive Propagation Planning Method for Feature Learning;89
12.4;3 A Genetic-Based Algorithm;89
12.4.1;3.1 Feature Selection;89
12.4.2;3.2 Population;90
12.4.3;3.3 Fitness and Crossover;91
12.4.4;3.4 Anomaly Detection;94
12.5;4 Conclusion and Future Enhancements;94
12.6;References;94
13;9 Performance of Negative Association Rule Mining Using Improved Frequent Pattern Tree;96
13.1;Abstract;96
13.2;1 Introduction;96
13.3;2 Generating NAR Based on Apriori;98
13.3.1;2.1 Frequent Item Sets Generated Using Apriori Method;98
13.3.2;2.2 Generating PAR;98
13.3.3;2.3 Generating Set of Possible NAR from PAR;99
13.3.4;2.4 Generating Valid NAR;99
13.4;3 Generating NAR Based on FP-Growth;100
13.4.1;3.1 Generating Frequent Item Sets;100
13.4.2;3.2 Generating PAR;100
13.4.3;3.3 Generating Set of Possible NAR from PAR;101
13.4.4;3.4 Generating Valid Negative Association Rules;101
13.5;4 Generating NAR Based on FISM;102
13.5.1;4.1 Frequent Item Sets Generated Using FISM Method;102
13.5.2;4.2 Generating PAR;102
13.5.3;4.3 Generating Set of Possible NAR from PAR;103
13.5.4;4.4 Generating Valid NAR;103
13.6;5 Comparative Results;103
13.7;6 Conclusion and Future Work;104
13.8;References;104
14;10 Iterative Concept-Based Clustering of Indian Court Judgments;105
14.1;Abstract;105
14.2;1 Introduction;105
14.3;2 Literature Survey;106
14.4;3 Court Judgment Dataset;108
14.5;4 Decision of Number of Clusters;109
14.6;5 Proposed Approach;110
14.6.1;5.1 Preprocessing;111
14.6.2;5.2 Documents Vector Space Model;111
14.6.3;5.3 Latent Semantic Analysis (LSA);111
14.6.4;5.4 Cosine Similarity;112
14.6.5;5.5 Hierarchical Clustering;113
14.7;6 Experimental Setup of Baseline Model;113
14.8;7 Experiment Results and Analysis;114
14.9;8 Conclusions and Future Work;115
14.10;References;116
15;11 Improving the Spatial Resolution of AWiFS Sensor Data Using LISS III and AWiFS DataPair with Contourlet Transform Learning;118
15.1;Abstract;118
15.2;1 Introduction;119
15.2.1;1.1 Non-subsampled Contourlet Transform;119
15.3;2 Background;121
15.4;3 Methodology;122
15.4.1;3.1 Image Registration;122
15.4.2;3.2 Normalization;122
15.4.3;3.3 NSCT Training;123
15.4.4;3.4 NSCT Prediction;123
15.4.5;3.5 Quality Assessment;123
15.5;4 Results;124
15.6;5 Conclusion;131
15.7;Acknowledgements;131
15.8;References;132
16;12 Regular Expression Tagger for Kannada Parts of Speech Tagging;133
16.1;Abstract;133
16.2;1 Introduction;133
16.3;2 Related Work;135
16.4;3 Challenges in POS Tagging for Kannada;136
16.5;4 Kannada Morphology-Based Parts of Speech Tagging;137
16.6;5 Tags and Kannada Tagging;138
16.7;6 Experiments and Results;140
16.7.1;6.1 Algorithm Kannada RegEx Tagger;141
16.7.2;6.2 RegEx Tagger Results;141
16.8;7 Conclusion and Future Work;142
16.9;References;142
17;13 Design of Conservative Gate and their Novel Application in Median Filtering in Emerging QCA Nanocircuit;143
17.1;Abstract;143
17.2;1 Introduction;143
17.3;2 Preliminaries;144
17.4;3 Related Works;145
17.5;4 Proposed Gate;146
17.6;5 Simulation Results and Comparison;147
17.7;6 Logic Synthesis with P-QCA;149
17.8;7 Testing and Fault Coverage;151
17.9;8 Conclusion;153
17.10;References;153
18;14 A Brief Survey: Features and Techniques Used for Sentiment Analysis;154
18.1;Abstract;154
18.2;1 Introduction;155
18.3;2 Feature Selection;155
18.3.1;2.1 Feature Selection Algorithms;156
18.3.2;2.2 Feature Selection Methods;156
18.4;3 Survey on Features, Techniques, and Datasets Used;161
18.5;4 Conclusion;161
18.6;References;161
19;15 Content-Centric Global Id Framework for Naming and Addressing for Smart Objects in IoT;164
19.1;Abstract;164
19.2;1 Introduction;164
19.3;2 Related Work;166
19.4;3 Content-Centric Global Id Framework;167
19.4.1;3.1 Protocol Stacks of CCGId;168
19.5;4 Simulation Result;169
19.6;5 Conclusion;172
19.7;References;172
20;16 Road Traffic Management System with Load Balancing on Cloud Using VM Migration Technique;174
20.1;Abstract;174
20.2;1 Introduction;175
20.3;2 Proposed Framework for Road Traffic Data Management Framework;175
20.3.1;2.1 Open Access Control;175
20.3.2;2.2 Optimal Hardware Control;176
20.3.3;2.3 Optimal Replication Control;176
20.3.4;2.4 Service Provider Support for Virtual Machine Migration;177
20.3.5;2.5 Optimal Manageability of Updates;178
20.4;3 Proposed Optimal Migration Framework;178
20.4.1;3.1 Virtual Machine Identification;178
20.4.2;3.2 Virtual Machine Allocation;180
20.4.3;3.3 Cost Analysis of Migration;180
20.5;4 Results and Discussion;181
20.6;5 Conclusion;182
20.7;References;183
21;17 Energy Constraint Service Discovery and Composition in Mobile Ad Hoc Networks;185
21.1;Abstract;185
21.2;1 Introduction;186
21.3;2 Related Work;187
21.4;3 System Model;188
21.4.1;3.1 Node Architecture of a Service in MANET;188
21.4.2;3.2 Response Packet;189
21.5;4 Energy Constraint Service Discovery and Composition in Mobile Ad Hoc Networks;190
21.5.1;4.1 Service Discovery in MANET;190
21.5.2;4.2 Energy Consumption Evaluation;192
21.5.2.1;4.2.1 Energy Index Value for Node;192
21.5.2.2;4.2.2 Energy Index Value for Service;192
21.5.3;4.3 Energy-Aware Service Composition;193
21.6;5 Simulation and Performance Evaluation;194
21.7;6 Conclusion and Future Work;196
21.8;References;196
22;18 Classifying Aggressive Actions of 3D Human Models Using Correlation Based Affinity Propagation Algorithm;198
22.1;Abstract;198
22.2;1 Introduction;199
22.3;2 Proposed Correlation Based Affinity Propagation Algorithm;200
22.4;3 Simulation Results on Benchmark Datasets;201
22.5;4 Classification of Aggressive Actions of 3D Human Models;202
22.6;5 Conclusions;206
22.7;References;206
23;19 How Safe Is Your Mobile App? Mobile App Attacks and Defense;208
23.1;Abstract;208
23.2;1 Introduction;208
23.3;2 Vulnerability of Smart Phones;210
23.4;3 Malware Behavior and Threats;210
23.4.1;3.1 Attacks;211
23.4.2;3.2 Malicious Activities Through Mobile Apps;213
23.5;4 Defense Mechanisms;213
23.5.1;4.1 Preventive Measures;213
23.5.2;4.2 Detection Techniques;214
23.6;5 Common Attacks on a Mobile Phone/Smartphone;214
23.7;6 Algorithm: CURD—Confidential Unrestricted and Restricted Data;215
23.8;7 Conclusion;216
23.9;References;216
24;20 An Agile Effort Estimation Based on Story Points Using Machine Learning Techniques;217
24.1;Abstract;217
24.2;1 Introduction;218
24.3;2 Related Work;219
24.4;3 Evaluation Criteria;220
24.5;4 Proposed Approach;221
24.5.1;4.1 Story Points;221
24.5.2;4.2 Project Velocity;222
24.5.3;4.3 Soft Computing;222
24.5.3.1;4.3.1 Adaptive Neuro-Fuzzy Interface System;222
24.5.3.2;4.3.2 Generalized Regression Neural Network;223
24.5.3.3;4.3.3 Radial Basis Function Networks (RBFNs);224
24.6;5 Experimental Results;225
24.7;6 Threats to Validity;226
24.8;7 Conclusion;226
24.9;References;226
25;21 OFS-Z: Optimal Features Selection by Z-Score for Malaria-Infected Erythrocyte Detection Using Supervised Learning;228
25.1;Abstract;228
25.2;1 Introduction;228
25.3;2 Related Work;229
25.4;3 Optimal Features Selection by Z-Score;231
25.4.1;3.1 Methods and Materials;231
25.4.1.1;3.1.1 RGB to Grayscale by PCA [20];231
25.4.1.2;3.1.2 Gamma Equalization;232
25.4.1.3;3.1.3 Median Filter;232
25.4.1.4;3.1.4 Gaussian Filter;232
25.4.1.5;3.1.5 Canny Filter-Based Edge Detection;233
25.4.1.6;3.1.6 K-Means Clustering by Optimal Centroids;233
25.4.1.7;3.1.7 Z-Score;234
25.4.1.8;3.1.8 Classifiers;234
25.4.1.9;3.1.9 Features;234
25.4.2;3.2 Preprocessing;235
25.4.3;3.3 Segmenting Erythrocytes by K-Means with Optimal Centroids;235
25.4.4;3.4 Features Extraction;236
25.4.5;3.5 Feature Optimization;236
25.4.6;3.6 Classification;237
25.4.7;3.7 Validation;237
25.5;4 Experimental Study and Results Analysis;237
25.5.1;4.1 Performance Analysis;238
25.6;5 Conclusion;239
25.7;References;239
26;22 An Effective Hybrid Fuzzy Classifier Using Rough Set Theory for Outlier Detection in Uncertain Environment;242
26.1;Abstract;242
26.2;1 Introduction;242
26.3;2 Related Work;243
26.4;3 Proposed Work;244
26.4.1;3.1 Training Pseudocode;244
26.4.2;3.2 Testing Pseudocode;246
26.4.3;3.3 Rule Matcher;248
26.5;4 Experimental Results;248
26.5.1;4.1 Accuracy;248
26.5.2;4.2 Area Under Curve;248
26.5.3;4.3 Running Time;249
26.6;5 Conclusion;249
26.7;References;250
27;23 CSES: Cuckoo Search Based Exploratory Scale to Defend Input-Type Validation Vulnerabilities of HTTP Requests;251
27.1;Abstract;251
27.2;1 Introduction;252
27.3;2 Related Work;253
27.4;3 Cuckoo Search Based Exploratory Scale (CSES) to Defend Input-Type Validation Vulnerabilities;254
27.4.1;3.1 Cuckoo Search;255
27.4.2;3.2 Feature Selection;255
27.4.2.1;3.2.1 Assessing Hamming Distance is as Follows;256
27.4.3;3.3 Learning Process (the Nest Formation);256
27.4.4;3.4 Testing Phase (Process of Cuckoo Search);257
27.4.4.1;3.4.1 Cuckoo Search on Both Hierarchies;257
27.4.5;3.5 Assessing the State of the Http Request;258
27.5;4 Experimental Study;258
27.5.1;4.1 The Dataset Preparation;259
27.5.2;4.2 Implementation Process;259
27.6;5 Results and Analysis;259
27.7;6 Conclusion;260
27.8;References;261
28;24 Stream Preparation from Historical Data for High-Velocity Financial Applications;263
28.1;Abstract;263
28.2;1 Introduction;263
28.2.1;1.1 Scope and Objective;264
28.3;2 Literature Survey;264
28.3.1;2.1 Disadvantages;265
28.4;3 Requirements;265
28.4.1;3.1 Functional;265
28.4.2;3.2 Nonfunctional;266
28.5;4 Block Diagram for Creating Virtual Live Stream;266
28.5.1;4.1 Description;266
28.6;5 Proposed System of Live Stream Preparation;267
28.6.1;5.1 Description of Data Set;268
28.6.2;5.2 Methodology;269
28.6.2.1;5.2.1 Algorithm Creation of Virtual Live Streams Takes Place by the Following Steps;269
28.6.3;5.3 Results;271
28.7;6 Conclusion;273
28.8;Acknowledgements;274
28.9;References;274
29;25 Context-Based Word Sense Disambiguation in Telugu Using the Statistical Techniques;276
29.1;Abstract;276
29.2;1 Introduction;277
29.2.1;1.1 Motivation;277
29.2.2;1.2 Dealing Word Sense Disambiguation;277
29.3;2 Literature Survey;278
29.4;3 Proposed Method;279
29.4.1;3.1 Methodology;279
29.4.2;3.2 Modules in the System;280
29.4.2.1;3.2.1 Module 1: Collect the Documents;280
29.4.2.2;3.2.2 Module 2: Tokenization;281
29.4.2.3;3.2.3 Module 3: Statistical Method;281
29.4.2.4;3.2.4 Module 4: Assigning Correct Sense;281
29.5;4 Evaluation;282
29.5.1;4.1 Telugu Text Document;282
29.5.2;4.2 Results;283
29.6;5 Conclusion;284
29.7;References;284
30;26 EEG-Controlled Prosthetic Arm for Micromechanical Tasks;286
30.1;Abstract;286
30.2;1 Introduction;287
30.3;2 Literature Survey;287
30.4;3 Methodology;288
30.5;4 Experimental Setup;288
30.5.1;4.1 Digital Acquisition of EEG Data;289
30.5.2;4.2 Preprocessing of EEG Recording;289
30.5.3;4.3 Extraction of Commands from EEG;289
30.6;5 Classification of Blinks Using Machine Learning Techniques;290
30.6.1;5.1 Features of Preprocessed EEG;291
30.6.1.1;5.1.1 Spectral Energy;291
30.6.1.2;5.1.2 First and Second Spectral Maxima and Locations;291
30.6.1.3;5.1.3 Width and Number of Pulses in the Window;291
30.6.2;5.2 Supervised Learning Methods;292
30.6.2.1;5.2.1 Linear Discriminant Analysis (LDA);292
30.6.2.2;5.2.2 K-Nearest Neighbor (KNN);292
30.6.3;5.3 Performance Evaluation of Classifiers;292
30.7;6 Command and Control for Prosthetic Hand;293
30.7.1;6.1 Translation of Commands and Feature Extraction;293
30.7.2;6.2 Arduino NanoV3.0;293
30.7.3;6.3 Prosthetic Arm;293
30.8;7 Results and Discussion;294
30.9;8 Conclusion;295
30.10;Acknowledgements;295
30.11;References;295
31;27 Wilcoxon Signed Rank Based Feature Selection for Sentiment Classification;297
31.1;Abstract;297
31.2;1 Introduction;298
31.3;2 Related Work;299
31.4;3 Methods and Materials;300
31.4.1;3.1 Feature Selection Metrics;300
31.4.1.1;3.1.1 Term Occurrence;300
31.4.1.2;3.1.2 Term Presence;300
31.4.1.3;3.1.3 Wilcoxon Signed Rank;301
31.4.2;3.2 Classifiers;301
31.5;4 Feature Selection;302
31.5.1;4.1 Corpus Preprocessing;303
31.5.2;4.2 Sentiment Lexicons Selection;303
31.5.3;4.3 Sentiment Term Selection as Features;303
31.5.4;4.4 Optimal Feature Selection;304
31.6;5 Experimental Study;308
31.6.1;5.1 Datasets and Statistics;309
31.6.2;5.2 Feature Selection and Performance Statistics;310
31.7;6 Conclusion;312
31.8;References;312
32;28 A Color Transformation Approach to Retrieve Cloudy Pixels in Daytime Satellite Images;315
32.1;Abstract;315
32.2;1 Introduction;315
32.3;2 Proposed Approach: Cloud Detection Algorithm;317
32.3.1;2.1 Preprocessing;317
32.3.2;2.2 Detection;318
32.4;3 Simulation Results;320
32.4.1;3.1 Test on Combine Approach to Detect Clouds;320
32.4.2;3.2 Comparing Results of Proposed Algorithm Against Existing Algorithm;322
32.5;4 Conclusions;322
32.6;References;322
33;29 Identifying Trustworthy Nodes in an Integrated Internet MANET to Establish a Secure Communication;324
33.1;Abstract;324
33.2;1 Introduction;324
33.3;2 Related Work;325
33.4;3 Proposed Work;325
33.4.1;3.1 Trust Value Calculation;326
33.4.2;3.2 Algorithm;327
33.5;4 Simulation Results;328
33.5.1;4.1 Experimental Setup;328
33.6;5 Conclusion and Future Work;331
33.7;References;331
34;30 Energy-Efficient Routing in MANET Using Load Energy Metric;332
34.1;Abstract;332
34.2;1 Introduction;332
34.3;2 Related Work;333
34.4;3 Load Energy Metric Algorithm;333
34.4.1;3.1 Update Queue Length at Every Node;334
34.4.2;3.2 Calculate Energy Level of Nodes;334
34.4.3;3.3 Select the Reliable Route;336
34.5;4 Simulation Parameters and Performance Evaluation;336
34.6;5 Conclusion;339
34.7;References;339
35;31 Design Optimization of Robotic Gripper Links Using Accelerated Particle Swarm Optimization Technique;340
35.1;Abstract;340
35.2;1 Introduction;340
35.3;2 Gripper Configuration Design;342
35.4;3 Accelerated Particle Swarm Optimization;345
35.5;4 Proposed Methodology;345
35.6;5 Result and Discussions;346
35.7;6 Conclusion;347
35.8;References;348
36;32 Cognitive Decision Support System for the Prioritization of Functional and Non-functional Requirements of Mobile Applications;349
36.1;Abstract;349
36.2;1 Introduction;349
36.3;2 Related Work;350
36.4;3 Proposed Work;351
36.4.1;3.1 Identification of Quality Attributes;351
36.4.2;3.2 Prioritization Using AHP;352
36.4.2.1;3.2.1 Basic Principles of AHP;352
36.4.3;3.3 Identification of Functional Requirements;353
36.4.4;3.4 Stakeholder Opinion and Triangular Fuzzy Number (TFN);353
36.4.5;3.5 Defuzzification and Normalization;354
36.4.6;3.6 Alternatives and Evaluation Using CDMOP;354
36.5;4 Case Studies;356
36.6;5 Results and Discussion;358
36.7;6 Conclusions and Future Work;359
36.8;References;359
37;33 Audio CAPTCHA Techniques: A Review;361
37.1;Abstract;361
37.2;1 Introduction;361
37.3;2 Related Work;362
37.3.1;2.1 Speech CAPTCHA;362
37.3.2;2.2 Acoustic CAPTCHA;363
37.4;3 Attacks on Audio CAPTCHA;364
37.5;4 Techniques to Prevent Attacks on Audio CAPTCHA;365
37.6;5 Accessibility;366
37.7;6 Conclusion;369
37.8;References;369
38;34 An Efficient Cache Refreshing Policy to Improve QoS in MANET Through R371
38.1;Abstract;371
38.2;1 Introduction;372
38.3;2 Preliminaries;373
38.3.1;2.1 Overview of DSR;373
38.3.2;2.2 Characterization of R373
38.3.3;2.3 Role of Cache Optimization Techniques;374
38.4;3 Proposed Methodology;375
38.4.1;3.1 Algorithm 1: Add Route;375
38.4.2;3.2 Algorithm 2: Find Route;376
38.5;4 Simulation Environment;376
38.6;5 Simulations;377
38.6.1;5.1 Packet Delivery Ratio (PDR);377
38.6.2;5.2 End-to-End Delay;377
38.6.3;5.3 Overhead;378
38.6.4;5.4 Packet Drop;378
38.6.5;5.5 Energy Consumption;378
38.7;6 Results and Discussions;379
38.7.1;6.1 PDR;379
38.7.2;6.2 End-to-End Delay;379
38.7.3;6.3 Overhead;379
38.7.4;6.4 Packet Drop;379
38.7.5;6.5 Energy Consumption;381
38.8;7 Conclusion;381
38.9;References;381
39;35 A Novel Parity Preserving Reversible Binary-to-BCD Code Converter with Testability of Building Blocks in Quantum Circuit;384
39.1;Abstract;384
39.2;1 Introduction;385
39.3;2 Background of Reversible and Quantum Computing;386
39.3.1;2.1 Reversible and Quantum Computing;386
39.3.2;2.2 Existing Parity Preserving Reversible Gates;387
39.4;3 Previous Work;387
39.5;4 Synthesis of Proposed Binary-to-BCD Code Converter;388
39.6;5 Individual Building Block Testability Methodology;390
39.7;6 Conclusions;393
39.8;References;393
40;36 Differentiated WRED Algorithm for Wireless Mesh Networks;395
40.1;Abstract;395
40.2;1 Introduction;396
40.3;2 Related Work;397
40.4;3 Proposed Improvements;398
40.5;4 Conclusion;401
40.6;References;401
41;37 Robust Estimation of Brain Functional Connectivity from Functional Magnetic Resonance Imaging Using Power, Cross-Correlation and Cross-Coherence;403
41.1;Abstract;403
41.2;1 Introduction;404
41.3;2 Materials and Methods;405
41.3.1;2.1 fMRI Time Series;405
41.3.2;2.2 Cross-Coherence;405
41.3.3;2.3 Cross-Correlation;406
41.3.4;2.4 High-Pass Filter;406
41.4;3 fMRI Data Acquisition;408
41.5;4 Signal Processing;408
41.5.1;4.1 Program Code;410
41.6;5 Results on fMRI Data Set;410
41.7;6 Conclusion and Discussion;412
41.8;References;413
42;38 Statistical Analysis of Derivatives of Cranial Photoplethysmogram in Young Adults;415
42.1;Abstract;415
42.2;1 Introduction;416
42.2.1;1.1 Beer–Lambert’s Law;416
42.2.2;1.2 Sensor Specifications;416
42.3;2 Methods;417
42.3.1;2.1 Velocity Photoplethysmogram (VPG);418
42.3.2;2.2 Acceleration Photoplethysmogram (APG);418
42.3.3;2.3 Statistical Parameters;420
42.4;3 Results;421
42.5;4 Discussion;423
42.6;5 Conclusion;423
42.7;References;424
43;39 Fuzzy Decision-Based Reliable Link Prediction Routing in MANET Using Belief Propagation;426
43.1;Abstract;426
43.2;1 Introduction;427
43.3;2 Related Research;427
43.4;3 Link Prediction with Proposed Approach;428
43.5;4 Results and Discussions;430
43.6;5 Conclusions;432
43.7;References;433
44;Adaptive PET/CT Fusion Using Empirical Wavelet Transform;434
44.1;1 Introduction;434
44.2;2 EWT: An Overview;436
44.2.1;2.1 Empirical Wavelets;436
44.2.2;2.2 Empirical Wavelet Transform;437
44.2.3;2.3 Tensor 2D EWT;437
44.3;3 Image Fusion with EWT;438
44.4;4 Experimental Data and Analysis;439
44.5;5 Results and Discussion;440
44.5.1;5.1 Data Set1;440
44.5.2;5.2 Data Set2;441
44.6;6 Conclusion;443
44.7;References;443
45;41 Sudoku Game Solving Approach Through Parallel Processing;445
45.1;Abstract;445
45.2;1 Introduction;446
45.3;2 Existing Solutions for Solving Sudoku Serially;447
45.3.1;2.1 Rule-Based Methods;448
45.4;3 Algorithm for Serial Code;448
45.5;4 Existing Solution for Execution Through Parallel Algorithm;449
45.5.1;4.1 Parallel Algorithm;450
45.6;5 Experimental Results;451
45.7;6 Conclusion and Future Scope;452
45.8;References;452
46;42 VANET: Security Attacks, Solution and Simulation;454
46.1;Abstract;454
46.2;1 Introduction;454
46.3;2 Requirement of Security;456
46.3.1;2.1 Routing;456
46.3.2;2.2 Integrity;458
46.3.3;2.3 Confidentiality;458
46.3.4;2.4 Availability;458
46.4;3 Categories of Attackers;459
46.5;4 Security Solution for VANET Attacks;460
46.6;5 Simulation Results of VANET;461
46.7;References;462
47;43 A Novel Approach for Efficient Bandwidth Utilization in Transport Layer Protocols;464
47.1;Abstract;464
47.2;1 Introduction;465
47.3;2 Literature Review;466
47.4;3 Various Transport Protocols;467
47.4.1;3.1 Sliding Window;467
47.4.2;3.2 Simple Protocol;468
47.4.3;3.3 Stop-and-Wait Protocol;468
47.4.4;3.4 Go-Back-N Protocol (GBN);469
47.4.5;3.5 Selective Repeat;470
47.4.6;3.6 Automatic Repeat Request;471
47.5;4 Proposed Solution;471
47.5.1;4.1 Research Gap;471
47.5.2;4.2 Proposed Solution;471
47.6;5 Algorithm;472
47.6.1;5.1 Complexity of the Algorithm: O(n);473
47.6.2;5.2 Justification of the Study;473
47.7;6 Results and Discussions;474
47.7.1;6.1 Increased Bandwidth Utilization;474
47.7.2;6.2 Less Network Congestion;474
47.7.3;6.3 More Robust;474
47.7.4;6.4 Reliable;475
47.7.5;6.5 Higher Efficiency;475
47.8;7 Conclusion;475
47.9;8 Future Scope and Directions;475
47.10;References;476
48;44 Functional Link Artificial Neural Network-Based Equalizer Trained by Variable Step Size Firefly Algorithm for Channel Equalization;477
48.1;Abstract;477
48.2;1 Introduction;477
48.3;2 Equalization;478
48.4;3 Multilayer Perceptron Network-Based Equalizer;479
48.5;4 Trigonometric Functional Link ANN;479
48.6;5 Chebyshev Functional Link ANN;480
48.7;6 Computational Techniques;481
48.7.1;6.1 Particle Swarm Optimization (PSO);481
48.7.2;6.2 Firefly Algorithm (FFA);482
48.7.3;6.3 Variable Step Size Firefly Algorithm (VSFFA);483
48.8;7 Simulation Results;483
48.9;8 Conclusion;485
48.10;References;486
49;45 Real-Time FPGA-Based Fault Tolerant and Recoverable Technique for Arithmetic Design Using Functional Triple Modular Redundancy (FRTMR);487
49.1;Abstract;487
49.2;1 Introduction;488
49.2.1;1.1 Single Event Upset (SEU);489
49.2.2;1.2 Error-Correction Circuitry (ECC);489
49.3;2 Related Work;489
49.4;3 Proposed System;490
49.4.1;3.1 One- and Multi-Bit Voter;490
49.5;4 Simulations and Results;493
49.5.1;4.1 Compilation, Analysis, and Synthesis;493
49.6;5 Discussion on the Proposed System and Results;493
49.7;6 Conclusion;494
49.8;References;495
50;46 A New Approach of Grid Integrated Power System Stability and Analysis Through Fuzzy Inference PSO Algorithm for Handling of Islanding PDCS Mode Datasets;496
50.1;Abstract;496
50.2;1 Introduction;497
50.3;2 An Overview of Particle Swarm Optimization;497
50.4;3 Schematic Layout of Model;499
50.5;4 Proposed Modified PSO for PDCS Mode of Network;500
50.6;5 Fuzzy Inference for Proposed Modified PSO for PDCS Mode of Network;501
50.7;6 Results and Discussion;503
50.8;7 Conclusion;504
50.9;References;505
51;47 Predictive Methodology for Women Health Analysis Through Social Media;506
51.1;Abstract;506
51.2;1 Introduction;506
51.3;2 Motivation;507
51.4;3 Problem Statement;508
51.5;4 Existing System;508
51.6;5 Proposed System;508
51.7;6 Experimental Results;510
51.8;7 Conclusion;514
51.9;8 Future Work;514
51.10;References;514
52;48 A Reversible Data Embedding Scheme for Grayscale Images to Augment the Visual Quality Using HVS Characteristics;516
52.1;Abstract;516
52.2;1 Introduction;516
52.3;2 Proposed Scheme;517
52.3.1;2.1 Data Embedding Procedure;519
52.3.2;2.2 Data Extraction Procedure;521
52.4;3 Results and Discussions;522
52.5;4 Conclusion;526
52.6;References;526
53;49 Optimal Feature Selection for Multivalued Attributes Using Transaction Weights as Utility Scale;528
53.1;Abstract;528
53.2;1 Introduction;528
53.3;2 Related Work;530
53.4;3 The Utility Scale Design and Optimal Set of Values Selection for Multivalued Attribute;532
53.5;4 Experimental Study and Performance Analysis;535
53.5.1;4.1 The Dataset;535
53.5.2;4.2 Assessment Metrics and Strategy;536
53.5.3;4.3 Performance Analysis;536
53.6;5 Conclusion;538
53.7;References;539
54;50 Android-Based Security and Tracking System for School Children;541
54.1;Abstract;541
54.2;1 Introduction;541
54.3;2 Related Work;542
54.4;3 Proposed System;543
54.5;4 Methodology;544
54.5.1;4.1 Child Module;544
54.5.2;4.2 Bus Module;544
54.6;5 Results;544
54.7;6 Conclusion;549
54.8;References;549
55;51 Video Shot Boundary Detection and Key Frame Extraction for Video Retrieval;551
55.1;Abstract;551
55.2;1 Introduction;551
55.3;2 Shot Boundary Detection;553
55.3.1;2.1 Scale Invariant Feature Transform;553
55.3.2;2.2 Key Point Matching for Shot Boundary Detection;555
55.4;3 Key Frame Extraction;555
55.4.1;3.1 Image Information Entropy;556
55.4.2;3.2 Extract Ultimate Key Frames Using Edge Matching Rate;556
55.5;4 Framework of the Proposed Method;557
55.6;5 Experimental Results;558
55.7;6 Conclusion;560
55.8;References;560
56;52 Performance Enhancement of Full Adder Circuit: Current Mode Operated Majority Function Based Design;562
56.1;Abstract;562
56.2;1 Introduction;563
56.3;2 Elements of the Proposed Full Adder;564
56.3.1;2.1 Current Mirror;564
56.3.2;2.2 Sensing Mechanism for the Proposed FA;565
56.4;3 State-of-the-Art of Proposed FA;566
56.4.1;3.1 Majority Function;566
56.4.2;3.2 Implementing FA Using Majority Function;567
56.5;4 Simulation Results and Discussion;568
56.6;5 Conclusion;571
56.7;References;571
57;53 A Tripartite Partite Key Generation and Management for Security of Cloud Data Classes;572
57.1;Abstract;572
57.2;1 Introduction;572
57.3;2 Literature Survey;573
57.4;3 Background and Preliminaries;574
57.4.1;3.1 Preliminaries;574
57.5;4 The Approach;576
57.5.1;4.1 Class Random Primes;576
57.5.2;4.2 Generation of Key Pairs;576
57.5.3;4.3 Description of Class Data;576
57.5.4;4.4 Tripartite Hives for Key Management;577
57.5.5;4.5 Performance comparisons;579
57.6;5 Conclusion;579
57.7;References;580
58;54 Transforming the Traditional Farming into Smart Farming Using Drones;581
58.1;Abstract;581
58.2;1 Introduction to Smart Farming;581
58.3;2 Need for Transforming the Traditional Farming;583
58.4;3 Existing Methods;585
58.5;4 Case Studies: Applications of Drones in Agriculture;586
58.6;5 Proposed Method;587
58.7;6 Discussions and Conclusion;589
58.8;References;589
59;55 Implementation of Power Law Model for Assessing Software Reliability;591
59.1;Abstract;591
59.2;1 Introduction;591
59.3;2 Proposed Model;592
59.4;3 Related Work;594
59.5;4 Results and Analysis;596
59.5.1;4.1 Existing System;596
59.5.2;4.2 Proposed System;596
59.5.3;4.3 Results;597
59.6;5 Conclusion;599
59.7;References;600
60;56 Energy Distribution Using Block-Based Shifting in a Smart Grid Tree Network;601
60.1;Abstract;601
60.2;1 Introduction;601
60.3;2 Energy Demand at Grid Based on Load Request in a SGTN;603
60.4;3 Adaptive Block-Based Intelligent Shifting Energy Distribution;605
60.5;4 Simulation Results;606
60.6;5 Conclusions;608
60.7;References;608
61;Properties and Applications of Hermite Matrix Exponential Polynomials;611
61.1;1 Introduction;611
61.2;2 Hermite Matrix Based Exponential Polynomials;614
61.3;3 Operational Representations;617
61.4;References;618
62;58 Economical Home Monitoring System Using IOT;619
62.1;Abstract;619
62.2;1 Introduction;619
62.2.1;1.1 Overview;619
62.2.2;1.2 Advantages of Home Monitoring System;620
62.3;2 Related Work;620
62.3.1;2.1 Remote Home Supervising System by Gowthami T. and More;620
62.3.2;2.2 Waste Electronics for Home Supervision System by Dingrong Yuan and More;621
62.3.3;2.3 Home Intrusion System Using Raspberry Pi by Shivprasad Tavagad, and More;621
62.3.4;2.4 Robot Monitored Home by Madhavi Shinde, and More;621
62.4;3 System Analysis;622
62.4.1;3.1 Problem Definition;622
62.4.2;3.2 Proposed System Feature;622
62.5;4 System Design and Implementation;622
62.5.1;4.1 Proposed Home Monitoring System;622
62.5.2;4.2 Proposed Home Monitoring System Functions;623
62.5.3;4.3 Software Design;624
62.5.4;4.4 Implementation Setup;624
62.6;5 Results and Efficiency;626
62.7;6 Conclusion and Future Work;628
62.7.1;6.1 Conclusion;628
62.7.2;6.2 Future Work;628
62.8;References;629
63;59 Hybrid Approach of Feature Extraction and Vector Quantization in Speech Recognition;630
63.1;Abstract;630
63.2;1 Introduction;630
63.3;2 Type of Speech Uttered by Human Beings;631
63.4;3 Feature Extraction Techniques;632
63.5;4 Feature Matching;634
63.6;5 Conclusion and Future Work;635
63.7;References;635
64;60 Security in Home Automation Systems;637
64.1;Abstract;637
64.2;1 Introduction;637
64.3;2 Literature Review;638
64.3.1;2.1 Summary of Papers;638
64.4;3 History of Home Automation;638
64.5;4 Home Automation Systems Today;639
64.5.1;4.1 Wireless Home Automation Networks (WHAN);639
64.5.2;4.2 Types of WHANs;640
64.5.3;4.3 Issues with Current Systems;641
64.5.4;4.4 Types of Home Automation Systems Based on WHAN;642
64.6;5 Key Findings;644
64.7;6 Conclusion;645
64.8;References;645
65;61 A Modified Technique for Li-Fi Range Extension;646
65.1;Abstract;646
65.2;1 Introduction;646
65.3;2 Existing Technology;647
65.4;3 Problems with Existing Technology;647
65.5;4 How Li-Fi Helps;648
65.6;5 Li-Fi—Working;649
65.7;6 Limitations of Li-Fi;650
65.8;7 Developing a Technique for Range Extension;650
65.9;8 Reflecting Devices on Doors;651
65.10;9 Reflecting Floors;652
65.11;10 Multidirectional Lighting;653
65.12;11 Receiver–Transmitter Module;653
65.13;12 Li-Fi––Wi-Fi Hybrid System;654
65.14;13 Discussion and Future Scope;655
65.15;14 Conclusion;656
65.16;References;656
66;62 Accelerating EGENMR Database Operations Using GPU Processing;657
66.1;Abstract;657
66.2;1 Introduction;657
66.3;2 Related Work;659
66.3.1;2.1 GPU Architecture;659
66.3.2;2.2 GPU Memory Hierarchy;661
66.3.3;2.3 GPU Accelerator for Database Operations;661
66.4;3 Proposed Model;662
66.4.1;3.1 Hybrid Query Processing Using GPU Co-processor;662
66.4.1.1;3.1.1 Hybrid Query Processing Works on the Following Algorithm;663
66.4.1.2;3.1.2 Total Time for Executing the Operations for Hybrid Query Processor on GPU Includes;663
66.4.2;3.2 E-GENMR Model Using GPU Processing;664
66.4.2.1;3.2.1 EGENMR Query Processing Works on the Following Algorithm;665
66.4.2.2;3.2.2 Our Proposed Model Takes Total Time to Execute Query on GPU Includes;665
66.4.3;3.3 Comparison of Time and Complexity for Hybrid Query Processing and EGENMR Using GPU;665
66.5;4 Conclusion;666
66.6;References;666
67;63 Hardware Implementation of IoT-Based Image Processing Filters;668
67.1;Abstract;668
67.2;1 Introduction;669
67.2.1;1.1 Purpose of Image Processing;669
67.2.2;1.2 Objectives of This Research;669
67.3;2 Related Work;669
67.4;3 Proposed Methodology;672
67.5;4 Experimental Results;673
67.6;5 Conclusion;676
67.7;6 Future Scope;677
67.8;References;677
68;64 An Extensive Study on IoRT and Its Connectivity Coverage Limit;679
68.1;Abstract;679
68.2;1 Introduction;679
68.3;2 Literature Survey;681
68.4;3 Use of an Interface;682
68.5;4 System Description;683
68.6;5 Application;684
68.7;6 Case Study;685
68.8;7 Connectivity Coverage;685
68.9;8 Robot–Device Connectivity (RDC);685
68.10;9 Motion Control Strategy;687
68.11;10 Interpretation of the Results;688
68.11.1;10.1 Architecture Model;688
68.11.2;10.2 Simulation Parameters;689
68.11.3;10.3 Simulation Results;689
68.12;11 Conclusion;690
68.13;References;690
69;65 Statistical Analysis Using Data Mining: A District-Level Analysis of Malnutrition;692
69.1;Abstract;692
69.2;1 Introduction;693
69.3;2 Literature Survey;693
69.3.1;2.1 Data Mining Methods;693
69.3.2;2.2 Clustering;694
69.3.3;2.3 Davies–Bouldin Index;695
69.3.4;2.4 Pearson’s Correlation;695
69.4;3 Methodology;696
69.4.1;3.1 Steps Involved;696
69.4.2;3.2 Experimental Setup;697
69.4.3;3.3 Model Structure;698
69.5;4 Result and Analysis;699
69.5.1;4.1 Clusterization;699
69.5.2;4.2 Correlations;700
69.6;5 Discussion;701
69.7;6 Conclusion;705
69.8;References;706
70;66 Traversal-Based Ordering of Arc–Node Topological Dataset of Sewer Network;707
70.1;Abstract;707
70.2;1 Introduction;707
70.3;2 Literature Review;708
70.4;3 Methodology;709
70.4.1;3.1 Prerequisites;709
70.4.2;3.2 Dataset;709
70.4.3;3.3 Data Structure Employed;709
70.4.4;3.4 Conceptual Modeling;710
70.4.5;3.5 Automation Rules;711
70.5;4 Algorithm;713
70.6;5 Implementation;714
70.6.1;5.1 Problem Statement;714
70.6.2;5.2 Implementation Process;715
70.6.3;5.3 Observation;716
70.6.4;5.4 Result;717
70.7;6 Future Work;718
70.8;References;718
71;Author Index;720
