Johri / Verma / Paul Applications of Machine Learning

1. Auflage 2020
ISBN: 978-981-15-3357-0
Verlag: Springer Nature Singapore
Format: PDF
Kopierschutz: 1 - PDF Watermark

E-Book, Englisch, 404 Seiten

Reihe: Algorithms for Intelligent Systems

This book covers applications of machine learning in artificial intelligence. The specific topics covered include human language, heterogeneous and streaming data, unmanned systems, neural information processing, marketing and the social sciences, bioinformatics and robotics, etc. It also provides a broad range of techniques that can be successfully applied and adopted in different areas. Accordingly, the book offers an interesting and insightful read for scholars in the areas of computer vision, speech recognition, healthcare, business, marketing, and bioinformatics.

Dr. Prashant Johri is a Professor at the School of Computing Science & Engineering, Galgotias University, Greater Noida, India. He received his MCA from Aligarh Muslim University and Ph.D. in Computer Science from Jiwaji University, Gwalior, India. He has also worked as a Professor and Director (MCA), Noida Institute of Engineering and Technology, (NIET). His research interests include big data, data analytics, data retrieval and predictive analytics, information security, privacy protection, big data open platforms, etc. He is actively publishing in these areas.

Dr. Jitendra Kumar Verma is Assistant Professor (Grade III) of Computer Science & Engineering at Amity School of Engineering & Technology, Amity University Haryana, Gurugram (Manesar), India. He received the degree of Ph.D. from Jawaharlal Nehru University (JNU), New Delhi, India in 2017, degree of M.Tech from JNU in 2013 and degree of B.Tech in Computer Science & Engineering from Kamla Nehru Institute of Technology (KNIT), Sultanpur, Uttar Pradesh, India in 2008. Dr. Verma is awardee of prestigious DAAD 'A new Passage to India' Fellowship (2015-16) funded by Federal Ministry of Education and Research - BMBF, Germany and German Academic Exchange Service (DAAD). He worked at JULIUS-MAXIMILIAN UNIVERSITY OF WÜRZBURG, GERMANY (mother of 14 Nobel Laureate) as a Visiting Research Scholar. Dr. Verma is member of several technical societies e.g. IEEE, IEEE IAS, and ACM. Over his short career, he published several research papers in proceedings of various international conferences and peer-reviewed International Journals of repute. He also contributed numerous book chapters to the several books published with publishers of high international repute. Apart from scholarly contribution towards scientific community, he organized several Conferences/Workshops/Seminars at the national and international levels. He voluntarily served as reviewer for various International Journals, conferences, and workshops. He also served as Guest Editor and Editorial Board Member of numerous international journals.  His research interest includes cloud computing, Mobile cloud, Machine learning, AR & VR, Soft computing, Fuzzy systems, Healthcare, Pattern recognition, Bio-inspired phenomena, and advanced optimization model & computation.
Dr. Sudip Paul is an Assistant Professor at the Department of Biomedical Engineering, School of Technology, North-Eastern Hill University (NEHU), Shillong, India. He received his Ph.D. from the Indian Institute of Technology (Banaras Hindu University), Varanasi, with a specialization in Electrophysiology and Brain Signal Analysis. He was selected as a Postdoc Fellow in 2017-18 under the Biotechnology Overseas Associateship for scientists working in the Northeastern States of India, supported by the Department of Biotechnology, Government of India. Dr. Sudip has published more than 90 international journal and conference papers and has filed four patents. Recently, he completed three book projects and is currently serving as Editor for a further two. Dr. Sudip is a member of numerous societies and professional bodies, e.g. the APSN, ISN, IBRO, SNCI, SfN, and IEEE. He received First Prize in the Sushruta Innovation Award 2011, sponsored by the Department of Science and Technology, Government of India, and various other awards, including a World Federation of Neurology (WFN) Travelling Fellowship, Young Investigator Award, and IBRO and ISN Travel Awards. Dr. Sudip has also served as an editorial board member for a variety of international journals.

Autoren/Hrsg.

Johri, Prashant

Verma, Jitendra Kumar

Paul, Sudip

Inhaltsverzeichnis

1;Preface;6
2;Editorial Advisory Board;13
2.1;Technical Program Committee;13
3;Contents;17
4;About the Editors;20
5;1 Statistical Learning Process for the Reduction of Sample Collection Assuring a Desired Level of Confidence;22
5.1;1 Introduction;22
5.2;2 Sampling Protocol Proposal;23
5.2.1;2.1 Mathematical Base;23
5.2.2;2.2 New Sampling Protocol;28
5.3;3 Study Cases;29
5.3.1;3.1 Simulation 1;29
5.3.2;3.2 Simulation 2;32
5.4;4 Future Research Lines and Conclusions;33
5.5;References;35
6;2 Sentiment Analysis on Google Play Store Data Using Deep Learning;36
6.1;1 Introduction;36
6.2;2 Literature Review;37
6.3;3 Data;38
6.3.1;3.1 Data Extraction;38
6.3.2;3.2 App Details and Review Details Specifics;40
6.4;4 Dataset Description;41
6.5;5 Data Exploration;43
6.6;6 Methods;43
6.6.1;6.1 Data Processing;44
6.6.2;6.2 Numerical Data Columns;45
6.7;7 Modelling Results;46
6.8;8 Discussion;49
6.9;9 Conclusion;50
6.10;References;50
7;3 Managing the Data Meaning in the Data Stream Processing: A Systematic Literature Mapping;52
7.1;1 Introduction;52
7.2;2 Research Method;53
7.2.1;2.1 Aim and Research Questions;54
7.2.2;2.2 Search Strategy;54
7.2.3;2.3 Filtering Results;55
7.2.4;2.4 Data Extraction Process;56
7.2.5;2.5 Synthesis Process;56
7.3;3 Performing the Systematic Literature Mapping;57
7.4;4 Summary of Results: Data-Meaning Strategies and Real-Time Data Processing;58
7.5;5 Conclusions;64
7.6;References;65
8;4 Tracking an Object Using Traditional MS (Mean Shift) and CBWH MS (Mean Shift) Algorithm with Kalman Filter;68
8.1;1 Introduction;68
8.2;2 Literature Survey;69
8.3;3 Proposed Methodology;71
8.3.1;3.1 Tracking the MS;73
8.3.2;3.2 Normalized Centroid Distance (NCD);74
8.3.3;3.3 BWH MS Tracking;75
8.3.4;3.4 Similarities for Representing the BWH with Usual Representation;76
8.3.5;3.5 CBWH Algorithm;78
8.3.6;3.6 Applications;79
8.4;4 Results;79
8.5;5 Conclusion;81
8.6;References;85
9;5 Transfer Learning and Domain Adaptation for Named-Entity Recognition;87
9.1;1 Introduction;87
9.2;2 Related Work;89
9.3;3 Procedure;89
9.4;4 Results and Analysis;92
9.5;Reference;93
10;6 Knowledge Graph from Informal Text: Architecture, Components, Algorithms and Applications;94
10.1;1 Introduction;94
10.2;2 Knowledge Graph Development Pipeline and Components;95
10.3;3 Knowledge Extraction;96
10.3.1;3.1 Entity Extraction;96
10.3.2;3.2 Relation Extraction (RE) and Attribute Extraction (AE);98
10.4;4 Knowledge Graph Construction;99
10.4.1;4.1 Entity Resolution;99
10.4.2;4.2 Link Prediction;100
10.4.3;4.3 Node Labeling;100
10.5;5 Knowledge Graph Challenges in Sparse Corpus;101
10.5.1;5.1 CRF with Automatic Feature Engineering-Based NER Model;102
10.5.2;5.2 AugmentedIE;103
10.6;6 Industrial Applications;104
10.6.1;6.1 Phase 1—KG Creation;106
10.6.2;6.2 Phase 2—KG Based Req2Test Application;106
10.7;7 Summary;107
10.8;References;108
11;7 Neighborhood-Based Collaborative Recommendations: An Introduction;110
11.1;1 Introduction;110
11.2;2 Notations;111
11.3;3 Neighborhood-Based Recommendations;112
11.3.1;3.1 User-Based Recommendations;114
11.3.2;3.2 Item-Based Recommendations;116
11.3.3;3.3 User-Based Versus Item-Based Methods;117
11.4;4 Neighborhood-Based Methods in Action;118
11.4.1;4.1 Rating Normalization;119
11.4.2;4.2 Similarity Computation;119
11.4.3;4.3 Variations in Selecting Peer Groups;121
11.5;5 Rating Matrix;121
11.5.1;5.1 Continuous Ratings;122
11.5.2;5.2 Interval-Scaled Ratings;122
11.5.3;5.3 Ordinal Ratings;123
11.5.4;5.4 Binary Ratings;123
11.5.5;5.5 Unary Ratings;123
11.6;6 Characteristics of the Rating Matrix;124
11.6.1;6.1 Sparsity;124
11.6.2;6.2 The Long-Tail Property;125
11.6.3;6.3 Cold-Start Problem;126
11.7;References;128
12;8 Classification of Arabic Text Using Singular Value Decomposition and Fuzzy C-Means Algorithms;130
12.1;1 Introduction;130
12.2;2 Literature Review;131
12.3;3 Methodology;134
12.3.1;3.1 Text Preprocessing;135
12.3.2;3.2 Feature Extraction;135
12.3.3;3.3 Applying Fuzzy C-Means Classifier;137
12.4;4 Experimental Results;137
12.4.1;4.1 Feature Reduction;137
12.4.2;4.2 Arabic Datasets;137
12.4.3;4.3 Performance Evaluation Measures;138
12.4.4;4.4 Comparison with Other Approaches;139
12.5;5 Conclusions and Future Work;140
12.6;References;141
13;9 Echo State Network Based Nonlinear Channel Equalization in Wireless Communication System;143
13.1;1 Introduction;143
13.2;2 System Model and Equalization;145
13.3;3 Echo State Network;146
13.3.1;3.1 Architecture of ESN;146
13.3.2;3.2 Training;147
13.3.3;3.3 Testing;148
13.4;4 Reservoir Design Considerations;148
13.4.1;4.1 Reservoir;148
13.5;5 Channel Equalization Using ESN;150
13.6;6 Simulation Results;151
13.6.1;6.1 Effect of ESN Parameters;151
13.6.2;6.2 Equalizer Performance Comparison;154
13.7;7 Conclusion;156
13.8;References;156
14;10 Melody Extraction from Music: A Comprehensive Study;158
14.1;1 Introduction;158
14.2;2 Melody Extraction Techniques;159
14.2.1;2.1 Salience-Based Approaches;160
14.2.2;2.2 Source Separation-Based Approaches;162
14.2.3;2.3 Data-Driven Approaches;164
14.3;3 Datasets;166
14.4;4 Performance Measures;167
14.4.1;4.1 Voice Recall (VR);167
14.4.2;4.2 Voicing False Alarm (VFA);167
14.4.3;4.3 Raw Pitch Accuracy (RPA);168
14.4.4;4.4 Raw Chroma Accuracy (RCA);168
14.4.5;4.5 Overall Accuracy (OA);168
14.5;5 Melody Extraction Applications;169
14.6;6 Challenges;170
14.7;7 Conclusion and Future Perspective;170
14.8;References;171
15;11 Comparative Analysis of Combined Gas Turbine–Steam Turbine Power Cycle Performance by Using Entropy Generation and Statistical Methodology;173
15.1;1 Introduction;173
15.2;2 Brief of Combined GT-ST Power Generation System;175
15.3;3 Plant Operation Condition;178
15.3.1;3.1 Thermodynamic Analysis and Statistical Modeling of Combined GT-ST Power Plant;178
15.4;4 Results and Discussion;184
15.4.1;4.1 Effect of Performance Parameters on Plant;185
15.5;5 Conclusions;189
15.6;References;190
16;12 Data Mining—A Tool for Handling Huge Voluminous Data;192
16.1;1 Introduction;192
16.1.1;1.1 Unavailability of Past Data;193
16.1.2;1.2 Background;194
16.1.3;1.3 Overview of Data Mining;196
16.1.4;1.4 Patterns to Accommodate Different Applications;199
16.1.5;1.5 Data Mining to Big Data Mining: Key Idea;201
16.2;2 Conclusion;202
16.3;References;202
17;13 Improving the Training Pattern in Back-Propagation Neural Networks Using Holt-Winters’ Seasonal Method and Gradient Boosting Model;204
17.1;1 Introduction;204
17.2;2 Related Works;206
17.3;3 Proposed Method;206
17.4;4 Results and Discussions;209
17.5;5 Conclusions;212
17.6;References;212
18;14 Ensemble of Multi-headed Machine Learning Architectures for Time-Series Forecasting of Healthcare Expenditures;214
18.1;1 Introduction;214
18.2;2 Background;216
18.3;3 Method;217
18.3.1;3.1 Data;217
18.3.2;3.2 Evaluation Metrics;218
18.3.3;3.3 Experiment Design for Multi-headed LSTM;218
18.3.4;3.4 Experiment Design for Multi-headed ConvLSTM;220
18.3.5;3.5 Experiment Design for Multi-headed CNN-LSTM;220
18.3.6;3.6 Ensemble Model;221
18.4;4 Results;222
18.4.1;4.1 Multi-headed LSTM Model;222
18.4.2;4.2 Multi-headed ConvLSTM Model;223
18.4.3;4.3 Multi-headed CNN-LSTM Model;225
18.4.4;4.4 Ensemble Model;226
18.5;5 Discussion and Conclusions;227
18.6;References;230
19;15 Soft Computing Approaches to Investigate Software Fault Proneness in Agile Software Development Environment;232
19.1;1 Introduction;232
19.2;2 Related Work;233
19.2.1;2.1 Soft Computing Approaches;234
19.3;3 Dataset and Metrics Definitions;236
19.4;4 Proposed Methodology;237
19.5;5 Results and Discussion;241
19.6;6 Conclusion and Future Research Scope;242
19.7;References;245
20;16 Week Ahead Time Series Prediction of Sea Surface Temperature Using Nonlinear Autoregressive Network with and Without Exogenous Inputs;249
20.1;1 Introduction;249
20.2;2 Literature Review;251
20.3;3 Time Series Models;254
20.3.1;3.1 Basic Nonlinear Autoregressive Models;254
20.3.2;3.2 Error Measures;256
20.4;4 Dataset Used;258
20.5;5 Proposed Methods;258
20.5.1;5.1 SSTA;259
20.5.2;5.2 SSTANAR;260
20.5.3;5.3 SSTAAirT;261
20.5.4;5.4 SSTAZ;262
20.5.5;5.5 SSTAM;263
20.6;6 Results;263
20.7;7 Summary;264
20.8;References;269
21;17 Regression Model of Frame Rate Processing Performance for Embedded Systems Devices;271
21.1;1 Introduction;271
21.2;2 Background and Related Works;272
21.3;3 Model of Performance Estimation;273
21.4;4 Results;276
21.5;5 Discussions;278
21.6;6 Conclusions;278
21.7;References;278
22;18 Time Series Data Representation and Dimensionality Reduction Techniques;280
22.1;1 Introduction;280
22.2;2 A Taxonomy of Representation/Dimensionality Reduction Techniques;281
22.3;3 Piecewise Linear Methods;283
22.3.1;3.1 PAA;283
22.3.2;3.2 APCA;284
22.3.3;3.3 DPAA;284
22.3.4;3.4 PLA;285
22.3.5;3.5 PTA;285
22.4;4 Symbolic-Based Methods;286
22.4.1;4.1 SAX;286
22.4.2;4.2 SFA;287
22.4.3;4.3 Trend-Based SAX Reduction;289
22.5;5 Feature-Based Methods;290
22.5.1;5.1 BOP;290
22.5.2;5.2 BOSS;291
22.5.3;5.3 Shapelets;292
22.6;6 Transformed-Based Methods;293
22.6.1;6.1 DFT;293
22.6.2;6.2 DCT;294
22.6.3;6.3 DWT;294
22.7;7 State of the Art;295
22.8;8 Conclusion and Future Research Direction;295
22.9;References;296
23;19 Simultaneous Localization and Mapping with Gaussian Technique;298
23.1;1 Introduction;298
23.2;2 Statistical Estimation and Learning in Robotics;299
23.3;3 Simultaneous Localization and Mapping [SLAM];300
23.4;4 Kalman Filter, Extended Kalman Filter;300
23.5;5 Future Work;303
23.6;References;303
24;20 Unsupervised Learning of the Sequences of Adulthood Transition Trajectories;305
24.1;1 Introduction;305
24.2;2 Literature Review on Unsupervised Learning of Sequences;307
24.2.1;2.1 Sequences of Biological Processes;307
24.2.2;2.2 Social Processes;309
24.3;3 Data and Methods;311
24.3.1;3.1 Method;312
24.4;4 Exploratory Analysis of Distribution of Adulthood Events by Geographical Region;314
24.4.1;4.1 Proportion of Events by Geographical Region;314
24.4.2;4.2 Failure Rate Function;316
24.5;5 Sequence Analysis;316
24.5.1;5.1 Index Plot;316
24.5.2;5.2 State Frequency Plot;318
24.5.3;5.3 State Distribution Plot;319
24.5.4;5.4 Entropy and Turbulence Measures;320
24.5.5;5.5 Cluster Analysis;322
24.6;6 Conclusion;323
24.7;References;329
25;21 A Quantile-Based Approach to Supervised Learning;332
25.1;1 Introduction;332
25.2;2 An Introduction to the Quantile-Based Distributions;334
25.3;3 Formulation of the Regression Model;336
25.4;4 Method of Fitting the Best Line of Regression;338
25.4.1;4.1 Convergence of the Algorithm;340
25.4.2;4.2 Validation;341
25.5;5 Regression Quantile Models Using Quantile-Based Distributions;342
25.5.1;5.1 Simulation Study;343
25.6;6 Empirical Applications;343
25.7;7 Conclusion;350
25.8;References;350
26;22 Feature Learning Using Random Forest and Binary Logistic Regression for ATDS;352
26.1;1 Introduction;352
26.2;2 Related Work;353
26.3;3 Background;354
26.3.1;3.1 Random Forest;354
26.3.2;3.2 Binary Logistic Regression;356
26.3.3;3.3 DUC 2002 Dataset;356
26.4;4 Proposed Approach;357
26.5;5 Experiment and Results;358
26.6;6 Concluding Remark;359
26.7;References;362
27;23 MLPGI: Multilayer Perceptron-Based Gender Identification Over Voice Samples in Supervised Machine Learning;364
27.1;1 Introduction;364
27.2;2 Gender Classification Related Work;365
27.3;3 Proposed Work;366
27.3.1;3.1 Used Dataset;366
27.3.2;3.2 Voice Preprocessing;367
27.3.3;3.3 Voice Features Extraction;367
27.3.4;3.4 Classification;368
27.3.5;3.5 Used Models for Classification;368
27.4;4 Experiment and Result;371
27.5;5 Conclusion and Future Scope;374
27.6;References;375
28;24 Scrutinize the Idea of Hadoop-Based Data Lake for Big Data Storage;376
28.1;1 Introduction;376
28.2;2 Research Methodology;378
28.2.1;2.1 Research Description or Definition;378
28.2.2;2.2 Searching Articles;379
28.2.3;2.3 Article Verification;380
28.2.4;2.4 Analyze Research;380
28.3;3 Research Classification;380
28.4;4 What Are Big Data and Big Data Storage?;381
28.4.1;4.1 Big Data Life Cycle;384
28.4.2;4.2 Tools and Technology to Process and Analysis Big Data;385
28.5;5 Data Lake;386
28.5.1;5.1 Data Lake Versus Data Swamp Versus Data Warehouse;392
28.5.2;5.2 The Need for Data Consumer and Producer;393
28.5.3;5.3 Application and Use Cases of the Data Lake;394
28.6;6 The Architecture of Data Lake;395
28.6.1;6.1 Technology Service Architecture;397
28.6.2;6.2 Data Architecture of Data Lake;397
28.7;7 Conclusion;399
28.8;8 Future Direction;399
28.9;References;400
29;Author Index;403