Computational Intelligence and Intelligent Systems (eBook)

Preface 5
Organization 6
Table of Contents 8
Section I: Computational Intelligence Applications 8
Omnidirectional Motion Control for the Humanoid Soccer Robot 13
Introduction 13
Preliminaries 14
Nao Model 14
Relations between Joints 14
Motion Control 16
Moving 16
Walking 16
Turning 17
Transverse Move 17
Symmetrical Robot Actions 17
Development Tool 18
Initial Module 18
Walk Module 19
Conclusion and Future Works 19
References 19
Routing Algorithm Based on Gnutella Model 21
Introduction 21
Improvement of Algorithm 22
Search Strategy of Normal Node 23
Search Strategy of Super Node 23
Implementation of Algorithm 25
The Experimental Results 26
Conclusion 27
References 27
Sliding-Window Recursive PLS Based Soft Sensing Model and Its Application to the Quality Control of Rubber Mixing Process 28
Introduction 28
Sliding-Window RPLS Model 29
The Prediction Model Based on RPLS 29
Updating Principle of Sliding-Window 30
Simulation Research 32
Mooney-Viscosity Prediction Based on PLS Model 32
Mooney-Viscosity Prediction Based on Sliding- Window RPLS Model 34
Conclusions 36
References 36
The Research of Method Based on Complex Multi-task Parallel Scheduling Problem 37
Introduction 37
Resource—Constrained Project Scheduling Model 38
Algorithm Design 38
RCPSP Problems 38
Data Structure for the Algorithm 39
The Framework of the Algorithm and the Code of Chromosome 40
Initialization Population 40
Genetic Operators Design 40
Fitness Function 41
Selection Operator 42
Experiments and Analysis 42
Experimental Environment 42
Experimental Data 42
The Experimental Results and Analysis 44
Conclusion 45
References 45
Towards a Bio-inspired Security Framework for Mission-Critical Wireless Sensor Networks 47
Introduction 47
Related Work 48
Proposed Scheme 49
Overview of MMASec 49
Model and Algorithm Selection 50
Architecture and Functions 52
Implementation Issues 53
Evaluations 53
Conclusion and Future Work 54
References 54
Section II: Evolutionary Algorithms 8
A Cluster-Based Orthogonal Multi-Objective Genetic Algorithm 57
Introduction 57
Problem Definition 58
Algorithm 58
Basic Idea 58
Algorithm Framework 59
Initialization 59
Clustering 60
Offspring Generation 62
Selection 62
Experiments and Results 62
Test Instances and Performance Metrics 62
Experimental Results 63
Conclusion 66
References 66
An Analysis of Semantic Aware Crossover 68
Introduction 68
Previous Work 69
Semantic Aware Crossover 70
Experimental Setup 71
Results and Discussion 71
Equivalent Crossovers 71
Semantic Diversity 72
Constructive Effect 74
Code Bloat 75
Conclusions 76
References 76
An Artificial Immune Univariate Marginal Distribution Algorithm 78
Introduction 78
The Univariate Marginal Distribution Algorithm 79
The Artificial Immune Algorithm 80
Principle of the General Artificial Immune Algorithm 80
Affinity Calculating 81
Activating and Suppressing 81
The Artificial Immune UMDA 82
Simulation Results 83
Conclusions 87
References 87
An Multi-objective Evolutionary Algorithm with Lower-Dimensional Crossover and Dense Control 88
Introduction 88
Introducing Dynamically Controlling Diversity Technique 89
Algorithm Description 90
Framework of Algorithm 90
Details of Algorithms 90
Numerical Experiments and Discussion 95
Test Problems 95
Testing Environment 95
Conclusions 97
References 98
Improved Evolutionary Programming and Its Application in Navigation System 100
Introduction 100
Improvements of Evolutionary Programming 101
Encoding Improvements-Hierarchical Evolutionary Programming 101
Mutation Improvements-Evolutionary Programming Based on Legal Individual 101
Prevention of Premature Phenomenon-Combination of Niche Technology and EP Selection 102
Design of BP Neural Network Based on Evolutionary Programming 103
Population Initialization 103
Learning Algorithm 103
Fitness Calculation 104
Mutation Operator 104
Select Operator 105
Hybrid Algorithm Design 105
Application of Improved Evolutionary Neural Network in Navigation System 105
Simulation Results and Conclusions 106
References 107
Multi-objective Emergency Facility Location Problem Based on Genetic Algorithm 109
Introduction 109
Mathematical Model of EFLP 110
How to Solve EFLP by GA 112
The Choice of Original Individuals 112
Fitness Function 112
GA Operators 112
Stopping Criteria 112
Experiments and Results 112
Conclusions 114
References 115
Trigonometric Curve Fitting Based on Genetic Algorithm and the Application of Data Processing in Geography 116
Introduction 116
The Improvement of Genetic Algorithm in the Trigonometric Functions in Curve Fitting 117
The Application of Trigonometric Function Fitting Based on Genetic Algorithm in Geological Data 118
Conclusion 120
References 121
Section III: Evolutionary Design 9
A Novel Crossover Operator in Evolutionary Algorithm for Logic Circuit Design 122
Introduction 122
Representation of Individual 123
Elitist Pool Evolutionary Algorithm 124
Sub-circuit Crossover Operator 124
Adaptive Mutation Strategy 125
Framework of Elitist Pool Evolutionary Algorithm 125
Evaluation 126
Experiment 126
Conclusion 128
References 128
Aptasensors Design Considerations 130
Introduction 130
Surface Modification 130
Transduction Approach 131
Electrochemical 131
Electrical 132
Optical 133
Mass 134
Sensor Performance 136
Summary and Perspective 136
References 137
Latent Semantic Analysis of the Languages of Life 140
Introduction 140
Mathematical Framework 141
Cross Language of Life 142
Empirical Results 143
Organism Motifs and Profiles 145
Phylogeny Using Doubly Singular Value Decomposition 145
Minimal Killer Words 147
Conclusion 148
References 148
Protein Folding Simulation by Two-Stage Optimization 150
Introduction 150
The Two-Stage Optimization 151
Sequence Conversion 152
Constraint-Based Optimal Structure Prediction in HP-Models 153
Local Search 153
Experiments 153
Conclusions 156
References 156
Search Direction Made Evolution Strategies Faster 158
Introduction 158
Function Optimization by Classical and Fast Evolution Strategies 159
Classical Evolution Strategies 160
Fast Evolution Strategies 160
Analysis the Impact of the Genetic Operators in ES 161
The Impact of Selection Operators 161
The Impact of Crossover Operators 161
The Impact of Mutation Operators 162
An Improved Fast Evolution Strategies 162
Experimental Studies 164
Conclusion 165
References 166
Topology Organization in Peer-to-Peer Platform for Genetic Algorithm Environment 168
Introduction 168
Related Works 168
Contribution of This Work 169
Design of Overlay 169
System Overview 169
Super Node Structure 170
Ordinary Node Organization 171
Performance Evaluations 171
Neighbor Distribution 172
SN/ON Partition 173
Conclusion 173
References 173
Section IV: Evolutionary Image Analysis and Signal Processing 9
Almost Periodic Solutions for Shunting Inhibitory Cellular Neural Networks with Time-Varying and Distributed Delays 174
Introduction 174
Existence of Almost Periodic Solutions 176
Exponential Stability of the Almost Periodic Solution 178
Illustrative Example 181
Conclusion 182
References 182
Applications of Computational Intelligence in Remote Sensing Image Analysis 183
Introduction 183
Neural Networks 184
Fuzzy Systems 184
Evolutionary Computation 186
Swarm Intelligence 187
Artificial Immune Systems 188
Conclusions 189
References 189
Association Relation Mining in Multimedia Data 192
Introduction 192
Association and Dependence Mining 193
Mining Instance of Video Strong Association and Dependence Relation 195
Experiment 197
Conclusion 198
References 199
DSA Image Blood Vessel Skeleton Extraction Based on Anti-concentration Diffusion and Level Set Method 200
Introduction 200
Anti-concentration Diffusion to Enhance the Blood Vessels 201
Otsu Local Threshold Segmentation Based on Regional Division 202
Vascular Skeleton Extraction Based on GMM and Fast Sweeping Method 203
Experiment and Analysis 206
Enhancement Effect of Vessel Using Anti-concentration Diffusion 206
Effect of Regional Division Otsu Local Threshold Segmentation 207
Effect of Skeleton Extraction 208
Conclusion 210
References 210
Space Camera Focusing Forecast Based on RBF Network 211
Introduction 211
Analysis of Network Model 212
Training of RBF Network 214
Result of Focusing Forecast Experiments 216
Conclusions 218
References 218
Wood Defect Identification Based on Artificial Neural Network 219
Introduction 219
Material and Method 219
Artificial Neural Network Damage Detection 220
Damage Detection Based on Wavelet Packet Energy Changes in the Artificial Neural Network 220
Based on the Frequency of Types of Structural Damage Detection Indicators 223
Damage Detection Based on the Frequency in the Neural Network 224
Conclusion 226
References 226
Section V: Evolutionary Optimization 10
An Improved Self-adaptive Control Parameter of Differential Evolution for Global Optimization 227
Introduction 227
Differential Evolution 228
Our Approach: ISADE 230
Improved Self-adaptive Control Parameter 230
Handling the Boundary Constraint of Variables 230
Experimental Results 231
Experimental Setup 232
Performance Criteria 232
General Performance of ISADE 233
Conclusion and Future Work 235
References 235
Distributed Evolutionary Algorithms to TSP with Ring Topology 237
Introductin 237
Distributed Evolutionary Algorithms 238
PVM 238
Algorithm Model of dEAs 238
Ring Topology 238
Master-Slave Model 238
Migration Strategy 239
Load Balancing 239
Experiments and Outcome Analysis 240
Conclusions 242
References 243
Self-adaptation in Fast Evolutionary Programming 244
Introduction 244
Function Optimization by Classical Evolutionary Programming 245
Experimental Studies 246
Benchmark Functions and Experimental Setup 246
Self-adaptation of Strategy Parameters 246
Conclusions 250
References 250
Solving SAT Problem Based on Hybrid Differential Evolution Algorithm 252
Introduction 252
SAT Problem and Its Transformation 253
SAT Problem 253
SAT Problem Is Translated into an Optimization Problem Based on {0,1} 253
Solving SAT Problem with Hybrid Differential Evolution Algorithm 254
Chromosome Structure 254
Differential Evolution Algorithm 254
The Hill-Climbing Algorithm 256
Hybrid Differential Evolution Algorithm 256
Experiment 257
Conclusion 257
References 258
The Application of Evolution-Branching Algorithm on Earth-Mars Transfer Trajectory 259
Introduction 259
Evolution Programming 261
Generate an Initial Population by Orthogonal Design 261
Migration 261
Mutation 262
Mating 262
Filtering 263
Branching Technique 263
Branching Procedure 263
Node Branching 264
Node Evaluate 264
Node Deletion 266
Experiments 266
Conclusions 267
References 268
The Research of Solution to the Problems of Complex Task Scheduling Based on Self-adaptive Genetic Algorithm 269
Introduction 269
Resource-Constrained Project Scheduling Model 269
Using Self-adaptive Genetic Algorithm to Solve the Problems of Complex Task Scheduling 270
RCPSP Problems 270
Self-adaptive Genetic Algorithm Design 271
Experiments and Analysis 274
Experimental Description 274
The Experimental Results and Analysis 275
Conclusion 276
References 277
Section VI: Fuzzy Logic Systems 10
A Novel Approach on Designing Augmented Fuzzy Cognitive Maps Using Fuzzified Decision Trees 278
Introduction 278
Main Aspects of Fuzzy Decision Trees 279
Fuzzy Cognitive Mapping Causal Algebra 280
Novel Approach on Designing Augmented Fuzzy Cognitive Maps 282
An Illustrative Generic Example 284
Conclusion 286
References 287
Computation of Uncertain Parameters by Using Fuzzy Synthetic Decision and D-S Theory 288
Introduction 288
The Solution Method of Uncertain Parameter $p$ Based on Fuzzy Comprehensive Decision 289
The Instruction of Principle 289
An Example of Application 292
The Solution Method of Uncertain Parameter Based on D-S Rule 293
Conclusion 295
References 296
FAHP-Based Fuzzy Comprehensive Evaluation of M& S Credibility
Introduction 297
Hierarchical Evaluation Model of M& S Credibility
M& S Credibility
Hierarchical Evaluation Model of M& S Credibility
FAHP-Based FCE Model 300
Triangular Fuzzy Number and Its Operation Laws 300
FAHP-Based FCE Model 301
Case Study 302
Conclusions 304
References 305
Indirect Dynamic Recurrent Fuzzy Neural Network and Its Application in Identification and Control of Electro-Hydraulic Servo System 307
Introduction 307
ADRFNN 308
Indirect ADRFNNC 309
Design of Indirect ADRFNNC 309
Analysis on Stability of Indirect ADRFNNC 310
Modified Algorithm Preventing Parameters from Drifting 311
Analysis on Experiment Results 313
Experiment Results by Indirect ADRFNNC 313
Discussions on Experiment Results 314
Conclusion 316
Reference 316
Logistics Distribution Center Location Evaluation Based on Genetic Algorithm and Fuzzy Neural Network 317
Introduction 317
Fuzzy Neural Networks Structure of Logistics Distribution Center Location 318
Description of Fuzzy Neural Network 318
Network Design of Logistics Distribution Center Location 318
Model Construction 319
Fuzzy Neural Networks Optimized by GA 319
Basic Idea 319
Training Algorithm 320
Application Example 321
Comparative Analysis of Algorithm 323
Conclusion 323
References 323
Mean-VaR Models and Algorithms for Fuzzy Portfolio Selection 325
Introduction 325
Preliminaries 326
Credibilistic Mean-VaR Model 327
Hybrid Intelligent Algorithm for Solving Mean-VaRModel 328
Examples 329
Conclusions 330
References 330
MOEA-Based Fuzzy Control for Seismically Excited Structures 332
Introduction 332
Integration of Fuzzy Controller and NSGA-II 333
Definition of Control Performance Indices 333
Multi-Objective Switching Fuzzy Control Strategy 333
Multi-Objective Optimization Algorithm-NSGA-II 335
Numerical Simulation Analysis Using Optimization Method 336
Establishment of Seismic Loading and Structure-Damper Model 336
Optimization Result Analysis 336
Robustness Test with Nonlinear Numerical Simulation 339
Conclusions 339
References 340
Section VII: Hybrid Methods 11
A Hybrid E-Institution Model for VOs 341
Introduction 341
The Hybrid Model 342
Facilitation to VO 348
Comparison and Conclusion 353
References 354
An Optimal Class Association Rule Algorithm 356
Introduction 356
Basic Concept and Theory 357
OCARA Algorithm 358
Discovering the Optimal Rules Set 358
Sorting Rules 360
Matching Rules 360
Experimental Results 361
Conclusion 361
References 361
Multiple Sequence Alignment Based on Chaotic PSO 363
Introduction 363
Description of the Problem 364
Multiple Sequence Alignment (MSA) 364
The Standard for Judging Multiple Sequence Alignment 365
Chaotic Particle Swarm Optimization 365
Particle Swarm Optimization and Its Premature to Determine 365
Chaos and Chaotic Particle Swarm Optimization 367
Multiple Sequence Alignment Based on Chaotic PSO 368
Relevant Definition 368
Several Problems to Be Solved 368
The Specific Steps of the Algorithm 369
Simulation and Results 370
Conclusions 371
References 371
Model Checking Algorithm Based on Ant Colony Swarm Intelligence 373
Introduction 373
Model Checking and Testing 374
Ant Colony Swarm Intelligence 375
Proposed Algorithm 375
Architecture and Assumptions 375
The Artificial Ants Deposit Pheromone on Traces 376
Locating Causes of the Errors According to Pheromone 377
Illustrating the Algorithm by Serving an Example 378
Experimental Results and Conclusions 380
References 380
QPSO-MD: A Quantum Behaved Particle Swarm Optimization for Consensus Pattern Identification 381
Introduction 381
DNA Motif Discovery 383
Problem Definition 384
QPSO-MD: The Proposed Framework 384
Particle Encoding 385
Fitness Function 386
Overall Dynamic of QPSO-MD 386
Experimental Results 387
Conclusion 388
References 389
Section VIII: Neural Network Architectures 11
Prediction of Hydrocarbon Reservoir Parameter Using a GA-RBF Neural Network 391
Introduction 391
GA-RBF Neural Network 392
Encode 393
Evaluation Function 393
RBF Neural Network Model Based on GA 394
Case Study 394
Network Input and Sample 394
Comparative Researches on Neural Network Prediction 395
Conclusions 397
References 397
Qualitative Simulation of Teachers Group Behaviors Based on BP Neural Network 399
Introduction 399
Description of Gravitation 400
Describing Gravitation Using BP Neural Network 400
Obtaining Inputs of BP Neural Network 401
The Model 403
Qualitative Simulation Methods 404
Variables and Their Description 404
Transition Rules 404
Filter Theory 406
Qualitative Simulation Engine 406
Applications 406
Conclusion 408
References 408
Stabilization of Switched Dynamic Neural Networks with Discrete Delays 410
Introduction 410
Preliminaries 411
Main Results 412
Numerical Example 415
Conclusions 416
References 417
ANN Designing Based on Co-evolutionary Genetic Algorithm with Degeneration 418
Introduction 418
Degeneration and Co-evolutionary Genetic Algorithm 419
Gene Coding for ANN and Fitness Function 420
ANN Training Based on CGA 422
Experiments and Results 422
Conclusion 424
References 424
Research on ACA-BP Neural Network Model 425
Introduction 425
ACA-BP Network Model 425
Basic Principle 425
Algorithm Realization 426
Simulation 428
Conclusion 430
References 430
Section IX: Predictive Modeling for Classification 11
A Text-Independent Speaker Verification System Based on Cross Entropy 431
Introduction 431
Speaker Verification System 432
Baseline System 432
Score Normalization 433
Approximated Cross Entropy (ACE) 434
Experiments 436
Database 436
Evaluation Measure 436
System Description 436
Experimental Results 437
Conclusion 438
References 438
An Improved Algorithm of Apriori 439
Introduction 439
Definition of Association Rule Mining 440
Association Rule 440
$Support$ of Association Rule 440
$Confidence$ of Association Rule 440
$Strong$ Association Rule, Minimum Support Threshold, Minimum ConfidenceThreshold 440
Synopsis and Property of Apriori Algorithm 441
Basic Idea of Apriori Algorithm 441
Deficiency of Apriori Algorithm 441
Improvement of Apriori Algorithm 441
Improvement of Apriori Algorithm 441
Improved Algorithm 442
Experiments and Result 443
Conclusions 443
References 444
An Incremental Clustering with Attribute Unbalance Considered for Categorical Data 445
Introduction 445
Related Works 446
Our Algorithm 447
Problem Formulation 447
ICUAC Algorithm 449
Experiments 450
Evaluation of Clustering Result 451
Real Data Sets and Results 451
Synthetic Data Sets and Results 453
Conclusions 453
References 454
Decision Tree Classifier for Classification of Plant and Animal Micro RNA’s 455
Introduction 455
Materials and Methods 456
Software 457
Classifier 457
Evaluation 458
Training Set 460
Results and Discussion 461
Conclusion 462
References 463
Embedded Classification Learning for Feature Selection Based on K-Gravity Clustering 464
Introduction 464
Related Work 466
Feature Selection Based on Clustering 466
Feature Density Estimation 467
Proposed Methods 467
K-Gravity Clustering 467
Embedded Classification Learning 469
Experimental Results 470
Conclusion and Future Work 471
References 472
Evaluation Measures of the Classification Performance of Imbalanced Data Sets 473
Introduction 473
Commonly Performance Evaluation Measures 474
Numerical Value Performance Measure 474
Graphical Performance Analysis with Probabilistic Classifiers 475
Shortcomings of Some Performance Metrics 479
Shortcomings of Accuracy 479
Shortcomings of Precision/Recall 479
Shortcomings of ROC 480
Complex Numerical Evaluation Measures 481
F-Measure 481
G-Mean 481
Youden’s Index 482
Likelihoods 482
Discriminatory Power 482
Conclusions 482
References 483
Hybrid Classification of Pulmonary Nodules 484
Introduction 484
Existing Clustering-Based Classification Approaches 486
Proposed Random Forest Classification Aided by EM Clustering on Pulmonary Nodules 487
Experiment I 488
Experiment II 489
Experiment III 489
Discussions 490
Conclusion 491
References 491
Author Index 494