Machine Intelligence and Signal Analysis

Preface......Page 6
 International Advisory Committee......Page 7
 Technical Program Committee......Page 8
Acknowledgements......Page 11
Contents......Page 12
About the Editors......Page 18
 1 Introduction......Page 20
 2 Hilbert Envelope......Page 21
 3 Proposed Method......Page 22
 4 Results and Discussion......Page 24
 References......Page 28
 1 Introduction......Page 30
  3.1 Data Preprocessing......Page 31
  3.2 Segmentation......Page 34
  3.3 Feature Generation......Page 35
  4.1 Data Preprocessing......Page 36
  4.2 Feature Identification and Selection......Page 37
  4.3 Classification......Page 38
 5 Conclusion......Page 41
 References......Page 42
 1 Introduction......Page 43
 2 Fourier Decomposition Method, BLW, and Power-Line Interference Removal......Page 45
 3 Results and Discussions......Page 47
 References......Page 52
 1 Introduction......Page 55
  2.2 Methodology......Page 57
  3.1 Qualitative Evaluation......Page 58
  3.2 Quantitative Evaluation......Page 62
 References......Page 64
 1 Introduction......Page 66
  1.1 S-Transforms......Page 67
 2 Methodology......Page 68
  2.1 Time–Frequency–Phase Analysis of EEG Signal......Page 69
 3 Results and Discussion......Page 70
 References......Page 74
 1 Introduction......Page 76
 2 Related Work......Page 78
 3 Transfer Boost-Based Transfer Learning......Page 79
 4 Transfer Learning in Substrate–Protease Cleavage Site......Page 81
 5 Results and Discussion......Page 83
 References......Page 86
Rényi’s Entropy and Bat Algorithm Based Color Image Multilevel Thresholding......Page 88
 1 Introduction......Page 89
 2 Rényi’s Entropy-Based Multilevel Thresholding......Page 90
 3 Bat Optimization Algorithm......Page 91
 5 Results and Discussion......Page 93
 6 Conclusion......Page 98
 References......Page 100
 1 Introduction......Page 102
 2 Proposed Source Model......Page 103
 3 Synthesizing Speech Using Proposed Method......Page 104
 4 Subjective Evaluation......Page 106
 5 Conclusion......Page 107
 References......Page 108
Efficient Methodology for Estimation of Vibration Thresholds for Electrical Machines......Page 109
 1 Introduction......Page 110
 2 Relevant Works......Page 111
 3 Proposed Technique for Threshold Estimation......Page 112
  3.1 Algorithm......Page 113
 5 Real-Time Analysis Results of the Algorithm......Page 116
 6 Comparative Study with Joint Time-Frequency Analysis Techniques......Page 118
 7 Conclusion......Page 121
 References......Page 122
Comparison Analysis: Single  and Multichannel EMD-Based Filtering with Application to BCI......Page 123
 1 Introduction......Page 124
 3 EMD and MEMD Algorithm......Page 126
 4 Results and Discussions......Page 128
 5 Conclusion......Page 132
 References......Page 133
 1 Introduction......Page 135
  2.1 Twin Support Vector Machine......Page 137
  2.2 Twin Parametric-Margin Support Vector Machine......Page 138
  2.3 Least Square Twin Support Vector Machine......Page 139
  2.4 Least Squares Twin Parametric-Margin Support Vector Machine......Page 140
  3.1 Linear FLSTPMSVM......Page 141
  3.2 Nonlinear FLSTPMSVM......Page 142
 4 Numerical Experiment......Page 143
 5 Conclusion......Page 146
 References......Page 149
Human Gait State Prediction Using Cellular Automata and Classification Using ELM......Page 151
 1 Introduction......Page 152
  2.1 Design of Atomic Components for CA......Page 153
  2.2 Developing Cellular Automata (CA)......Page 154
  2.3 CA Rules......Page 155
 3 Experiments Results and Verification......Page 157
 4 Error Analysis......Page 158
 References......Page 160
 1 Introduction......Page 162
 2 Anomaly Diagnosis in Traveling Elderly......Page 164
 3 Design of Railway Coach for Assisted Travel......Page 167
 4 Design Evaluation......Page 169
 5 Concluding Remarks......Page 170
 References......Page 171
 1 Introduction......Page 172
  2.1 Preprocessing Phase......Page 175
  2.2 Training Phase......Page 176
  2.3 Rule Generation Phase......Page 178
 3 Brief Explanation of the Proposed System......Page 179
 5 Experiment and Results......Page 180
  5.1 Result and Analysis......Page 181
 6 Conclusion......Page 182
 References......Page 184
 1 Introduction......Page 186
  2.1 EMD......Page 188
  2.2 Variational Mode Decomposition (VMD)......Page 189
  2.3 Condition Indicators (CIs)......Page 190
  3.1 Test Setup......Page 191
 4 Result and Discussions......Page 192
 References......Page 196
CA-DE: Hybrid Algorithm Based on Cultural Algorithm and DE......Page 199
 1 Introduction......Page 200
 2 Cultural Algorithm......Page 201
 3 Differential Evolution......Page 202
 4 Propose CA-DE......Page 203
 6 Simulation Results and Analysis......Page 205
 7 Conclusion......Page 206
 References......Page 209
Optimal Design of Three-Band Orthogonal Wavelet Filter Bank  with Stopband Energy for Identification of Epileptic Seizure EEG Signals......Page 211
 1 Introduction......Page 212
 2 Parameterized M-Band Wavelet Filter Banks......Page 213
  2.2 Degree One Dyadic Factorization of Polyphase Matrix......Page 214
 3 Results and Discussion......Page 215
 4 Conclusion......Page 219
 References......Page 220
Identification of Epileptic Seizures  from Scalp EEG Signals Based on TQWT......Page 222
 1 Introduction......Page 223
  3.1 Tunable-Q Wavelet Transform......Page 225
  3.2 Area Computation from Reconstructed Phase Space......Page 226
 4 Results and Discussion......Page 227
 References......Page 232
 1 Introduction......Page 235
  2.1 Particle Swarm Optimization......Page 237
  2.2 Teaching–Learning-Based Optimization......Page 238
 3 Proposed Algorithm......Page 239
 4 Experimental Results......Page 240
  4.1 Results......Page 242
 References......Page 244
A New Method for Classification of Focal and Non-focal EEG Signals......Page 246
 1 Introduction......Page 247
  2.1 Database Description......Page 248
  2.2 Empirical Mode Decomposition......Page 249
  2.3 Feature Extraction......Page 250
 3 Results and Discussion......Page 251
 4 Conclusion......Page 255
 References......Page 256
 1 Introduction......Page 258
  2.1 Subjects......Page 259
  2.2 Experiment Setup......Page 260
  2.4 Block Diagram of the Proposed Method......Page 262
  2.6 Support Vector Machine (SVM)......Page 263
 3 Results and Discussion......Page 265
 4 Conclusion and Future Scope......Page 266
 References......Page 267
 1 Introduction......Page 269
 2 Methodology......Page 270
  2.2 Classification......Page 271
 3 Model Selection......Page 273
 4 Performance Versus Data Size......Page 274
 References......Page 275
Estimation of Sampling Time Offsets in an N-Channel Time-Interleaved ADC Network Using Differential Evolution Algorithm and Correction Using Fractional Delay Filters......Page 277
 1 Introduction......Page 278
 3 Sampling Time Offsets in TI-ADC Network......Page 279
 4 Estimation of Sampling Time Offsets Using Differential Evolution Algorithm......Page 280
  4.4 Selection......Page 282
 5 Correction of Sampling Time Offsets......Page 283
  6.1 Estimation of Sampling Time Offsets......Page 284
 7 Correction of Sampling Time Offsets......Page 285
 8 Conclusion......Page 287
 References......Page 288
Double Density Dual-Tree Complex Wavelet Transform-Based Features  for Automated Screening of Knee-Joint Vibroarthrographic Signals......Page 289
 1 Introduction......Page 290
 2 Method and Material......Page 291
  2.2 Denoising and Filtering......Page 292
  2.4 Feature Extraction......Page 293
  2.5 Feature Ranking and Feature Selection......Page 294
 3 Results and Discussion......Page 295
 4 Conclusion......Page 298
 References......Page 299
 1 Introduction......Page 301
 2 Selection of Mother Wavelet for Ball Bearing......Page 303
  3.1 ANN with Multilayer Perception......Page 304
 4 Experimental Setup and Data Preparation......Page 305
  4.1 Extraction of Features......Page 306
  4.2 Selection of Features......Page 307
 5 Results and Discussion......Page 308
 References......Page 310
 1 Introduction......Page 312
 2 Restricted Boltzmann Machine......Page 314
 3 Deep Neural Network Using Kaldi ASR Tool......Page 315
 5 Comparative Performance......Page 316
 6 Conclusion and Future Work......Page 318
 References......Page 319
 1 Introduction......Page 321
  2.2 Loss Function......Page 325
  3.3 Accuracy......Page 327
  3.4 Gross Error Sensitivity (GER)......Page 328
 References......Page 329
Distinguishing Two Different Mental States of Human Thought Using Soft Computing Approaches......Page 331
 2 Feature Extraction......Page 332
  2.2 Parametric Feature Vector Construction......Page 333
  3.1 Pearson's Correlation......Page 334
  3.3 Fisher Discriminant Ratio......Page 335
  4.1 Dataset and Constructing Feature Vector......Page 336
  4.2 Results and Discussion......Page 337
  4.3 Friedman Statistical Test......Page 339
 References......Page 340
 1 Introduction......Page 342
  3.1 Face Detection......Page 344
  3.2 Face Recognition......Page 346
  4.1 Experiments on LFW......Page 347
  4.3 Transfer Learning on Classroom Data......Page 349
  5.1 On LFW Dataset......Page 350
  5.2 On Classroom Dataset......Page 351
 References......Page 352
 1 Introduction......Page 354
  2.1 Lung Segmentation......Page 355
  2.2 Airway Detection......Page 356
 3 Results......Page 358
 4 Conclusion and Discussion......Page 359
 References......Page 361
 1 Introduction......Page 362
  2.2 ADMET Prediction......Page 364
  3.1 ADMET Prediction......Page 365
 4 Conclusion......Page 367
 References......Page 368
Sentiment Score Analysis for Opinion Mining......Page 370
 1 Introduction......Page 371
  3.1 Framework......Page 372
  3.2 Framework......Page 373
  3.3 Classification......Page 375
  3.4 Proposed Method......Page 376
  4.1 Accuracy......Page 377
  4.2 National Average Sentiment......Page 378
  4.3 Sector-Wise Analysis......Page 379
  4.5 Time Series Analysis......Page 380
 References......Page 381
 1 Introduction......Page 382
 2 Segmentation......Page 383
 3 Existing Methods......Page 384
 4 Performance Analysis......Page 387
 5 Conclusions......Page 391
 References......Page 392
 1 Introduction......Page 393
 3 Steps for Designing of OFDM Transmitter and Receiver......Page 395
  3.1 Steps for Designing of OFDM Transmitter......Page 396
  3.2 Steps for Designing of OFDM Receiver......Page 398
 4 Results and Discussion......Page 399
 References......Page 400
 1 Introduction......Page 401
  2.1 ε—Support Vector Regression......Page 404
  3.1  Linear Penalizing ε-Generalized SVR......Page 405
  3.2 Nonlinear Penalizing ε-Generalized SVR......Page 407
 4 Experimental Results......Page 408
  4.2 Artificial Datasets......Page 409
  4.3 UCI Datasets......Page 410
 References......Page 414
 1 Introduction......Page 416
  2.1 Keyframe Extraction......Page 418
  2.2 Extracting Optimal Keyframes......Page 419
  3.1 Qualitative Analysis......Page 421
  3.2 Quantitative Results......Page 423
 4 Conclusion......Page 425
 References......Page 426
Computationally Efficient ANN Model for Small-Scale Problems......Page 427
 1 Introduction......Page 428
  2.1 Deep Learning Using CNN......Page 430
  2.2 Spatial Transforming Artificial Neural Network (ST-ANN)......Page 434
 3 Experiment and Results......Page 435
 References......Page 438
Investigating the Influence of Prior Expectation in Face Pareidolia using Spatial Pattern......Page 440
 1 Introduction......Page 441
  2.3 Data Acquisition and Preprocessing......Page 442
  2.4 Feature Extraction......Page 444
  2.5 Single-Trial Classification......Page 447
  3.1 Comparison of CSP and RCSP Analysis......Page 448
  3.2 Frequency Band-Wise Spatial Pattern Analysis......Page 450
 4 Discussion......Page 451
 References......Page 452
 1 Introduction......Page 455
 2 Problem Formulation......Page 456
  2.1 Video Lectures Summarization Through Clustering......Page 457
  3.1 Qualitative Analysis......Page 458
  3.2 Quantitative Analysis......Page 459
  3.3 Computational Complexity......Page 460
 References......Page 461
 1 Introduction......Page 462
  2.1 Entropy......Page 464
  2.2 Rule of Thirds......Page 465
  3.1 Salient Object Database......Page 467
  3.3 Quantitative Evaluation......Page 468
 References......Page 472
An Automated Alcoholism Detection Using Orthogonal Wavelet Filter Bank......Page 474
 1 Introduction......Page 475
  2.1 EEG Data Collection and Noise Removal......Page 476
  2.2 Design of Daubechies Orthogonal Wavelet Filter Bank......Page 477
  2.3 Extracting and Ranking the Features......Page 478
  2.4 Classification Using Ensemble Subspace KNN  and LS-SVM......Page 480
 3 Results and Discussion......Page 481
 4 Conclusion......Page 482
 References......Page 483
An Efficient Brain Tumor Detection  and Segmentation in MRI Using Parameter-Free Clustering......Page 485
 1 Introduction......Page 486
  2.1 Cluster Validation with Silhouette Coefficient......Page 490
  3.1 Data Selection......Page 491
  3.3 Results......Page 492
 References......Page 494
 1 Introduction......Page 496
  2.3 IITG-Stress Database......Page 498
  3.1 Fourier Parameter (FP)......Page 499
  3.2 Mel-Frequency Cepstral Coefficient......Page 500
  3.4 Features Extraction......Page 501
  3.5 Features Normalization......Page 502
  4.2 Result Analysis Using One-vs-One Multi-Class Classification......Page 503
 5 Conclusion......Page 505
 References......Page 506
 1 Introduction......Page 508
 2 Related Work......Page 509
 3 Material and Methodology......Page 510
  3.2 Preprocessing......Page 511
  3.3 Description of Discretization Technique......Page 512
  3.4 Description of Classification Models......Page 513
  3.5 Performance Measure......Page 514
 4 Results and Discussion......Page 515
  4.1 Evaluation of Proposed Method......Page 516
  4.3 Comparison Between SVM and Fuzzy SVM......Page 517
 References......Page 519
 1 Introduction......Page 521
 2 Related Work......Page 522
  3.1 Individual Classifiers......Page 523
  3.2 Ensemble Classifier......Page 524
 4 Evaluation Metrics......Page 525
 5 Experimental Verification......Page 526
  5.2 Results......Page 527
 6 Conclusion......Page 528
 References......Page 530
 1 Introduction......Page 531
 3 Methodology......Page 532
  3.3 Feature Matrix......Page 533
  3.4 Proposed Model......Page 534
 4 Performance Index......Page 535
  4.2 Separation......Page 536
 5 Results and Discussion......Page 537
 6 Conclusion and Future Work......Page 540
 References......Page 541
 1 Introduction......Page 543
 3 Methodology......Page 545
  3.3 CLIQUE Algorithm......Page 546
 4 Experimental Results......Page 547
 References......Page 549
Keystroke Rhythm Analysis Based  on Dynamics of Fingertips......Page 552
 1 Introduction......Page 553
 2 System Overview......Page 554
  3.1 Data Acquisition......Page 556
 4 Experiment......Page 557
  5.1 Interpersonal Keystroke Rhythm Analysis......Page 558
  5.2 Intrapersonal Keystroke Rhythm Analysis......Page 562
 References......Page 563
 1 Introduction......Page 565
  2.1 Universum Support Vector Machine (USVM)......Page 567
  2.2 Universum Twin Support Vector Machine (UTSVM)......Page 568
  3.1 Fuzzy Universum Support Vector Machine (FUSVM)......Page 569
  3.2 Fuzzy Universum Twin Support Vector Machine (FUTSVM)......Page 570
  3.3 Calculation of Fuzzy Membership......Page 571
 4 Numerical Experiments......Page 572
 5 Conclusions and Future Work......Page 576
 References......Page 577
 1 Introduction......Page 579
  2.2 FAWT: Overview......Page 581
  2.3 Fractal Dimension Computation......Page 582
 3 RELS-TSVM-based Classification......Page 587
 4 Experimental Results and Discussion......Page 588
 5 Conclusions and Future Work......Page 589
 References......Page 590
 1 Introduction......Page 593
  2.2 Preprocessing and Beat Segmentation......Page 595
  2.3 Improved Eigenvalue Decomposition of Hankel Matrix and Hilbert Transform (IEVDHM-HT)......Page 596
  2.4 Extracted Features......Page 597
  2.5 Classification......Page 598
 3 Results and Discussion......Page 599
 4 Conclusion......Page 601
 References......Page 602
 1 Introduction......Page 605
  2.2 Two-Photon Excited Fluorescence (TPEF) Microscopy......Page 607
  2.3 Second-Harmonic Generation (SHG) Microscopy......Page 608
 3 Analysis of the NLO Modalities Parameters by Combining CARS, SHG and PTEF in Tumorigenesis......Page 609
  3.3 Tumor-Associated Collagen Signature (TACS)......Page 610
  3.5 Gray Level Co-occurrence Matrix (GLCM) Analysis......Page 611
 4 Future Direction......Page 612
 References......Page 613
 1 Introduction......Page 616
  2.1 Genetic Susceptibility......Page 618
  2.2 Mild Cognitive Impairment (MCI)......Page 620
  2.4 CSF Biomarkers—Amyloid β1–42 (Aβ42), Phosphorylated Tau (P-tau181) and Total Tau (T-tau)......Page 621
  2.5 Cerebral Blood Flow (CBF) Analysis......Page 622
  2.8 Memory Impairment as an Early Sign for Probable AD......Page 623
 References......Page 624
  1.1 Cancer and Tumorigenesis......Page 628
 3 Diagnostic Techniques......Page 629
 4 Immunohistochemistry......Page 630
 5 Flow Cytometry......Page 632
  5.2 Fluorescence Imaging......Page 633
  5.4 Early Diagnosis......Page 634
  5.6 Enhanced Cancer Isolation by Nanotextured Polymer Substrate......Page 635
  6.1 Cancer Detection by Nanowire Sensor Assays......Page 636
 References......Page 637
 1 Introduction......Page 639
 2 Background Review......Page 641
  2.1 Odd–Even Filter Design Approach......Page 642
  3.1 Proposed Odd–Even Technique......Page 643
 4 Design Example......Page 646
 5 Image Denoising Application......Page 648
 References......Page 649
 1 Introduction......Page 651
  2.1 Overview of the Proposed Model......Page 653
  2.2 Preliminaries......Page 654
  2.3 Hidden Layer Learning......Page 656
  2.4 Formation of Output Layer......Page 659
  3.2 Experimental Setup......Page 660
 4 Conclusion......Page 663
 References......Page 664
Electromyogram Signal Analysis Using Eigenvalue Decomposition of the Hankel Matrix......Page 665
 1 Introduction......Page 666
 3 Methodology......Page 667
  3.1 MUAP Extraction......Page 668
  3.2 IEVDHM Method......Page 669
  3.3 Features Extraction......Page 671
 4 Results and Discussion......Page 672
 References......Page 674
Machine Learning Toward Infectious Disease Treatment......Page 677
 1 Introduction......Page 678
 2 Challenges and Opportunities Toward Infectious Disease Treatment......Page 679
  3.2 Unsupervised Learning......Page 680
 4 Support Vector Machines......Page 681
 5 Artificial Neural Network......Page 682
 6 Fuzzy Logic......Page 684
 References......Page 685
 1 Introduction......Page 688
  2.1 Discrete Wavelet Transform......Page 690
 3 Case Study......Page 692
 4 Result and Discussion......Page 693
 5 Conclusion......Page 697
 References......Page 698
 1 Introduction......Page 700
 2 Noise Model for Medical Images......Page 701
  3.2 Statistical Approach......Page 702
  3.3 Filtering Domain......Page 703
 4 Result Analysis......Page 704
 References......Page 707
 1 Introduction......Page 709
 2 Current Diagnostic Techniques Available......Page 710
 References......Page 717
 1 Introduction......Page 719
 2 Experimental Setup and Database Description......Page 720
  3.1 Acoustic Analysis of Oral Speech......Page 721
  3.2 Acoustic Analysis on Nasal Speech......Page 723
 4 Signal Processing Techniques......Page 724
  4.1 Formant Detection......Page 725
  4.2 Log-Spectral Distance......Page 726
  4.3 Cross Correlation......Page 727
 References......Page 728
 1 Introduction......Page 730
 2 Kernel Ridge Regression (KRR) for Multi-Class Classification......Page 732
  3.2 Active Learning for the Unlabelled Stream......Page 733
  3.3 Retraining of the Classifier KRRMC......Page 735
  4.1 Performance Analysis......Page 736
  4.2 Efficiency Analysis......Page 740
 5 Conclusion......Page 741
 References......Page 742
Automatic Segmentation of Intracerebral Hemorrhage from Brain CT Images......Page 743
 2 Related Work......Page 744
  3.1 Skull Removal......Page 746
  3.2 ICH Segmentation......Page 748
 4 Results......Page 749
 5 Conclusion......Page 752
 References......Page 753
Author Index......Page 755