دانلود کتاب Adaptive Differential Evolution: A Robust Approach to Multimodal Problem Optimization

فهرست مطالب :

Title Page......Page 2
Preface......Page 7
Contents......Page 13
Part I Techniques for Resource-Intensive Problems......Page 28
Introduction......Page 29
Instance-Based Learning Methods......Page 31
Machine Learning Methods......Page 33
Statistical Learning Methods......Page 35
Existing Research in Multi-surrogate Assisted EAs......Page 37
Comparative Studies for Different Approximate Models......Page 40
Indirect Fitness Approximation Methods......Page 43
Evolution Control......Page 44
Online Model Updating......Page 45
The Welded Beam Design Domain......Page 46
Supersonic Aircraft Design Domain......Page 47
Final Remarks......Page 49
References......Page 50
Introduction......Page 55
Basic Concepts......Page 56
Pareto Optimality......Page 57
Knowledge Incorporation......Page 58
Surrogates......Page 59
Polynomials: Response Surface Methods (RSM)......Page 60
Gaussian Process or Kriging......Page 61
Radial Basis Functions......Page 62
Artificial Neural Networks......Page 63
Support Vector Machines......Page 64
Clustering......Page 66
Fitness Inheritance......Page 67
Real-World Applications......Page 68
Use of Problem Approximation......Page 69
Use of RSM by Polynomial Approximation......Page 71
Use of Artificial Neural Networks......Page 72
Use of a Gaussian Process or Kriging......Page 74
Use of Radial Basis Functions......Page 78
Conclusions and Future Research Paths......Page 79
References......Page 80
Multilevel Optimization Algorithms Based on Metamodel- and Fitness Inheritance-Assisted Evolutionary Algorithms......Page 86
Introduction......Page 87
Metamodel–Assisted EAs and Distributed MAEAs......Page 89
Fitness Inheritance......Page 90
Radial Basis Function (RBF) Networks......Page 91
Assessment of MAEA and DMAEA......Page 92
The Three Multilevel Modes – Defining a HDMAEA......Page 93
Distributed Hierarchical Search – DHMAEA vs. HDMAEA......Page 95
Assessment of Multilevel–Hierarchical Optimization......Page 96
Optimization of an Annular Cascade......Page 100
Conclusions......Page 104
References......Page 105
Introduction......Page 110
Formulation of the Space Mapping Algorithm......Page 113
Space Mapping Surrogate Models......Page 115
Characterization of Space Mapping......Page 116
Space Mapping Illustration......Page 117
Example 1: Microstrip Bandpass Filter......Page 120
Example 2: Ring Antenna b32......Page 124
Exploiting Extra Knowledge: Tuning Space Mapping......Page 126
Tuning Space Mapping Formulation......Page 127
TSM Optimization of Chebyshev Bandpass Filter......Page 128
Conclusions......Page 131
References......Page 132
Introduction......Page 135
Evolutionary Algorithms Using Approximation Models......Page 137
Estimated Comparison Method......Page 138
Potential Model......Page 139
Estimated Comparison......Page 140
Adaptive Control......Page 141
Differential Evolution......Page 142
Adaptive DE with the Estimated Comparison Method......Page 143
Test Problems......Page 144
Experimental Results......Page 146
Discussion......Page 150
References......Page 152
Kriging Is Well-Suited to Parallelize Optimization......Page 154
Where Computational Intelligence and Kriging Meet......Page 155
Towards Kriging-Based Parallel Optimization: Summary of Obtained Results and Outline of the Chapter......Page 157
The Ordinary Kriging Metamodel and Its Gaussian Process Interpretation......Page 158
Kriging-Based Optimization Criteria......Page 160
The Multi-points Expected Improvement (q-EI) Criterion......Page 165
Analytical Calculation of 2-EI......Page 166
q-EI Computation by Monte Carlo Simulations......Page 170
Approximated q-EI Maximization......Page 172
The Kriging Believer (KB) and Constant Liar (CL) Strategies......Page 173
Empirical Comparisons with the Branin-Hoo Function......Page 174
Towards Kriging-Based Parallel Optimization: Conclusion and Perspectives......Page 178
Conditioning Gaussian Vectors......Page 180
Simple Kriging Equations......Page 181
Ordinary Kriging Equations......Page 182
References......Page 183
Analysis of Approximation-Based Memetic Algorithms for Engineering Optimization......Page 186
Memetic Algorithms and Computer-Aided Design......Page 187
Approximation-Based Memetic Algorithms......Page 191
Varying Accuracy in Black-Box Functions......Page 193
Approximation-Based Local Search......Page 194
Convergence Analysis......Page 198
Computational Cost......Page 203
Analytical Problems......Page 205
Electromagnetic Benchmark Problem......Page 208
Final Remarks......Page 211
References......Page 212
Introduction......Page 215
Boltzmann Estimation of Distribution Algorithms......Page 217
Right-Sized Selection......Page 219
Probabilistic Elitism......Page 220
Maximum Entropy......Page 221
Evolutionary Backtracking from Log-Probability Landscapes......Page 222
Selecting a Bayesian EDA Algorithm......Page 223
Partial Evaluation in Boltzmann EDAs......Page 224
A Simple Algorithm for Partial Evaluation with Backtracking......Page 227
Entropic Mutation......Page 230
Shrinkage Estimation of Distribution Algorithms......Page 232
Summary and Conclusions......Page 235
Appendix......Page 236
References......Page 238
Introduction......Page 241
Surrogate-Assisted Evolutionary Optimization......Page 243
Similarity-Based Surrogate Models (SBSMs)......Page 244
Surrogate-Assisted Framework......Page 246
The Surrogate-Assisted Evolutionary Algorithm......Page 247
Computational Experiments......Page 249
Single-Objective Optimization......Page 251
Multi-objective Optimization......Page 257
Concluding Remarks......Page 266
References......Page 267
Multi-objective Model Predictive Control Using Computational Intelligence......Page 271
Meta-modeling Using Computational Intelligence......Page 272
Aspiration Level Approach to Interactive Multi-objective Optimization......Page 277
Multi-objective Model Predictive Control......Page 279
References......Page 285
Introduction......Page 287
Fitness Approximation......Page 289
Particle Swarms......Page 290
Speciated Particle Swarms......Page 291
mQSO......Page 292
Using Regression to Locate Optima......Page 293
Experimental Setup......Page 296
Static Functions......Page 297
Moving Peaks......Page 299
Static Functions......Page 303
Moving Peaks......Page 305
References......Page 313
Part II Techniques for High-Dimensional Problems......Page 316
Introduction......Page 317
Differential Evolution......Page 319
Population Size Reduction......Page 321
Scale Factor Local Search......Page 322
Numerical Results......Page 325
Results in 100 Dimensions......Page 327
Results in 500 Dimensions......Page 330
Results in 1000 Dimensions......Page 333
Discussion about the Algorithmic Components......Page 336
Conclusion......Page 340
References......Page 341
Introduction......Page 344
Optimization of Electric Power Distribution Networks......Page 346
Evolutionary Approach......Page 349
Working within the Feasibility Domain......Page 350
Lamarckian Hybridization......Page 354
Application Examples and Illustration......Page 356
References......Page 361
Introduction......Page 363
Genetic Algorithm......Page 365
Reinforcement Learning: Q-Learning Algorithm......Page 366
Hybrid Methods Using Metaheuristic and Reinforcement Learning......Page 367
GRASP-Learning......Page 368
Genetic-Learning......Page 369
Methodology......Page 370
Experimental Results......Page 372
The Traveling Salesman Problem......Page 373
Computational Test......Page 374
References......Page 386
An Evolutionary Approach for the TSP and the TSP with Backhauls......Page 388
The Traveling Salesman Problem......Page 389
Conventional TSP Heuristics......Page 390
Evolutionary TSP Algorithms......Page 391
The TSP with Backhauls......Page 392
The First Evolutionary Algorithm for the TSP......Page 393
Nearest Neighbor Crossover (NNX)......Page 394
Greedy Crossover (GX)......Page 396
Proposed Mutation Operators......Page 397
Other Settings of the First Evolutionary Algorithm......Page 398
Computational Results for the TSP......Page 400
More Than Two Parents and Multiple Offspring......Page 404
Improved Mutation Operators......Page 406
Computational Results for the TSP......Page 407
Computational Results for the TSPB......Page 408
Conclusion......Page 411
References......Page 412
Introduction......Page 414
The Takagi-Sugeno Fuzzy Systems......Page 416
Time Complexity......Page 417
Fast Identification of Consequent Parameters......Page 419
Reuse in the Application of Mating Operators......Page 420
Speeding Up the Calculus of the Output through Reuse......Page 422
The Used MOEA to Learn TS Rules......Page 423
Experimental Results......Page 424
Regression Problem......Page 426
Time Series Forecasting Problem......Page 430
Conclusions......Page 437
References......Page 438
Introduction......Page 440
Problem Definition......Page 441
Solution Approaches......Page 442
Knowledge-Based Evolutionary Algorithm (KEA)......Page 446
Phases of KEA......Page 447
Benchmark Algorithms......Page 449
Performance Indicators......Page 450
Numerical Results......Page 451
Experimental Complexity of KEA and NSGA2......Page 454
Scalability of KEA......Page 457
Tri-Criterion Instances......Page 458
Alternative Algorithms Based on KEA......Page 459
Discussions and Analysis......Page 464
Conclusions......Page 465
References......Page 466
Introduction......Page 470
The Estimation Road Map......Page 472
Estimator Selection Procedure......Page 473
Parametrization......Page 474
Constraints......Page 475
Size of the Parameter Space......Page 476
Evolutionary Algorithms as Risk Optimization Procedures......Page 479
Proposed EA......Page 480
Simulation Study Design......Page 485
Simulation Study Results......Page 487
Data Analysis for a Diabetes Study......Page 493
Conclusion......Page 498
Appendix......Page 499
References......Page 500
Part III Real-World Applications......Page 502
Introduction......Page 503
Particle Swarm Optimisation......Page 505
PSO Algorithm......Page 506
Choice of PSO Algorithmic Parameters......Page 508
MIMO System Model......Page 509
Semi-blind Joint ML Channel Estimation and Data Detection......Page 510
PSO Aided Semi-blind Joint ML Scheme......Page 512
Simulation Study......Page 513
PSO Based MBER Multiuser Transmitter Design......Page 515
Downlink of SDMA Induced MIMO System......Page 516
MBER MUT Design......Page 517
PSO Aided MBER MUT Design......Page 518
Simulation Study......Page 519
References......Page 524
Presentation......Page 528
Introduction......Page 529
Automatic Definition of the Computational Mesh......Page 531
Single-objective and Multi-objective Approaches......Page 537
Optimization Algorithms......Page 539
Implementations on Computation Platform and Grids......Page 540
Test Case......Page 541
Problem Specifications......Page 542
Engine Simulation Code......Page 543
HIPEGEO......Page 544
Analysis of the Results......Page 549
Conclusions......Page 552
References......Page 554
Introduction......Page 557
Uncertainties in Space Mission Design......Page 559
Frame of Discernment U, Power Set 2U and Basic Probability Assignment......Page 560
Belief and Plausibility Functions......Page 562
Cumulative Functions: CBF, CCBF, CPF, CCPF......Page 563
Problem Formulation......Page 565
Direct Solution through a Population-Based Genetic Algorithm......Page 567
Indirect Solution Approach......Page 569
Spacecraft Mass Model......Page 573
The BPA Structure......Page 576
Results and Comparisons......Page 577
Direct Solution Simulations......Page 578
Indirect Solution Simulations......Page 580
References......Page 582
Introduction......Page 585
Progressive Design Methodology......Page 587
Synthesis Phase of PDM......Page 589
System Requirements Analysis......Page 590
Determination of Performance Criterion/Criteria......Page 591
Selection of Variables and Sensitivity Analysis......Page 592
Development of System Model......Page 593
Deciding on the Optimization Strategy......Page 594
Intermediate Analysis Phase of PDM......Page 596
Linguistic Term Set......Page 598
Aggregation Operator for Linguistic Weighted Information......Page 599
Model Suitable for PDM......Page 603
Requirement Analysis......Page 604
Determining of Performance Criteria......Page 605
Development of System Model......Page 606
Results of Multiobjective Optimisation......Page 608
Intermediate Analysis Phase of PDM for Design of a BLDC Motor Drive......Page 609
Identification of New Set of Objectives......Page 611
The Semantic of Linguistic Term Set......Page 612
The Screening Process......Page 613
Independent Design Variables and Objectives......Page 614
Set of Solutions......Page 616
Conclusions......Page 618
References......Page 619
Reliable Network Design......Page 622
Problem Formulation......Page 624
Reliability Metrics......Page 625
Reliability Estimation......Page 626
Ant Colony Optimization......Page 628
Hybrid Heuristics......Page 629
Multi-Ring Encoding......Page 630
Contraction Model......Page 631
Hybrid Genetic Algorithm......Page 633
Representation and Initialization......Page 634
Fitness Evaluation......Page 635
Parent Selection and Offspring Generation......Page 636
Mutation......Page 637
Local Search Ant Colony System......Page 638
Numerical Results......Page 640
References......Page 645
Neural Engineering Speech Recognition Using the Genetic Algorithm......Page 649
Input Description......Page 654
Synapse Connectivity: The Dynamic Synapse Neural Network......Page 656
DSNN Architecture......Page 658
Synapse Functionality......Page 659
Synapse Optimization......Page 662
Biased Selection: Word Micro-environment......Page 663
Objective Function: Fitness Evaluation......Page 664
Score Function Rational......Page 666
Genetic Algorithm: Mutation, Elitism, and Micro-environment......Page 669
Integrated Responses......Page 670
Dynamic Model Emergence Via Cost-Weighted Classification......Page 673
System Output Visualization......Page 676
Discussion......Page 677
Sound Processing Via the Dorsal Cochlear Nucleus......Page 679
References......Page 680
Introduction......Page 683
The Image Registration Problem......Page 685
High Performance Computing......Page 688
A Grid Computing Framework for Medical Imaging......Page 690
Case Study: Automatic Subtraction Radiography Using Distributed Evolutionary Algorithms......Page 692
Parametric Transformations......Page 693
Similarity Measure......Page 694
Search Strategy......Page 696
Algorithms Distribution......Page 698
Algorithms Validation......Page 699
The Subtraction Service......Page 704
Discussion and Conclusions......Page 706
Appendix......Page 707
References......Page 710
Introduction......Page 713
Related Work......Page 715
Design Space Exploration with Multi-Objective Evolutionary Computation......Page 716
Design Space Exploration Core......Page 717
Genetic Algorithm Design......Page 718
Solution Evaluation......Page 719
Building Cost Models......Page 721
Cost Models......Page 722
Experimental Evaluation......Page 723
Accuracy of Models......Page 724
Performance of the Methodology......Page 725
Fitness Inheritance......Page 726
Inheritance Model......Page 727
Experimental Evaluation......Page 728
Weighting Functions......Page 729
Parameter Analysis......Page 732
References......Page 733
Index......Page 736