Muutke küpsiste eelistusi

E-raamat: Practical Handbook of Genetic Algorithms: Applications, Second Edition 2nd edition [Taylor & Francis e-raamat]

Edited by (Metro Transport Directorate, Perth, Western Australia)
  • Formaat: 544 pages, 68 Tables, black and white; 200 Illustrations, black and white
  • Ilmumisaeg: 07-Dec-2000
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-13: 9780429127809
  • Taylor & Francis e-raamat
  • Hind: 355,44 €*
  • * hind, mis tagab piiramatu üheaegsete kasutajate arvuga ligipääsu piiramatuks ajaks
  • Tavahind: 507,78 €
  • Säästad 30%
  • Formaat: 544 pages, 68 Tables, black and white; 200 Illustrations, black and white
  • Ilmumisaeg: 07-Dec-2000
  • Kirjastus: Chapman & Hall/CRC
  • ISBN-13: 9780429127809
The second edition reflects recent research and new applications with mostly new chapters by an international group of specialists from academic and research settings. Individual chapters include: compact fuzzy models and classifiers through model reduction and evolutionary optimization, the application of reorganization operators for solving a language recognition problem, using GA to optimize the selection and scheduling of road projects, decoupled optimization of power electronics circuits, feature selection and classification in the diagnosis of cervical cancer, algorithms for multidimensional scaling, transportation optimization problems, and job-shop scheduling problems. Annotation c. Book News, Inc., Portland, OR (booknews.com)

Rapid developments in the field of genetic algorithms along with the popularity of the first edition precipitated this completely revised, thoroughly updated second edition of The Practical Handbook of Genetic Algorithms. Like its predecessor, this edition helps practitioners stay up to date on recent developments in the field and provides material they can use productively in their own endeavors.

For this edition, the editor again recruited authors at the top of their field and from a cross section of academia and industry, theory and practice. Their contributions detail their own research, new applications, experiment results, and recent advances. Among the applications explored are scheduling problems, optimization, multidimensional scaling, constraint handling, and feature selection and classification.

The science and art of GA programming and application has come a long way in the five years since publication of the bestselling first edition. But there still is a long way to go before its bounds are reached-we are still just scratching the surface of GA applications and refinements. By introducing intriguing new applications, offering extensive lists of code, and reporting advances both subtle and dramatic, The Practical Handbook of Genetic Algorithms is designed to help readers contribute to scratching that surface a bit deeper.

Rapid developments in the field of genetic algorithms along with the popularity of the first edition precipitated this completely revised, thoroughly updated second edition of The Practical Handbook of Genetic Algorithms: Applications. Like its predecessor, this edition provides practitioners with material they can use productively in their own endeavors. Among the applications explored are scheduling problems, optimization, multidimensional scaling, constraint handling, and feature selection and classification. All of the computer code offered in the book is available for download from the Internet.
Model Building, Model Testing and Model Fitting
1(31)
Uses of Genetic Algorithms
1(2)
Optimizing or Improving the Performance of Operations Systems
1(1)
Testing and Fitting Quantitative Models
2(1)
Maximizing vs. Minimizing
2(1)
Purpose of this
Chapter
2(1)
Quantitative Models
3(3)
Parameters
3(1)
Revising the Model for Revising the Data?
3(1)
Hierarchic or Stepwise Model Building: The Role of Theory
4(1)
Significance and Meaningfulness
4(2)
Analytical Optimization
6(1)
An Example: Linear Regression
6(1)
Iterative Hill-Climbing Techniques
7(7)
Iterative Incremental Stepping Method
8(1)
An Example: Fitting the Continents Together
9(2)
Other Hill-Climbing Methods
11(1)
The Danger of Entrapment on Local Optima and Saddle Points
12(1)
The Application of Genetic Algorithms to Model Fitting
13(1)
Assay Continuity in a Gold Prospect
14(14)
Description of the Problem
14(1)
A Model of Data Continuity
15(3)
Fitting the Data to the Model
18(1)
The Appropriate Misfit Function
19(2)
Fitting Models of One or Two Parameters
21(4)
Fitting the Non-homogeneous Model 3
25(3)
Conclusion
28(3)
Reference
29(2)
Compact Fuzzy Models and Classifiers through Model Reduction and Evolutionary Optimization
31(30)
Introduction
31(2)
Fuzzy Modeling
33(4)
The Takagi-Sugeno Fuzzy Model
34(1)
Data-Driven Identification by Clustering
35(2)
Estimating the Consequent Parameters
37(1)
Transparency and Accuracy of Fuzzy Models
37(4)
Rule Base Simplification
38(1)
Genetic Multi-objective Optimization
39(2)
Genetic Algorithms
41(3)
Fuzzy Model Representation
41(1)
Selection Function
42(1)
Genetic Operators
42(1)
Crossover Operators
42(1)
Mutation Operators
43(1)
Constraints
43(1)
Examples
44(2)
Nonlinear Plant
44(2)
Proposed approach
46(1)
TS Singleton Model
46(3)
TS Linear Model
49(7)
Iris Classification Problem
51(1)
Solutions in the literature
52(1)
Proposed Approach
52(4)
Conclusion
56(5)
Reference
56(5)
On the Application of Reorganization Operators for Solving a Language Recognition Problem
61(38)
Introduction
61(2)
Performance across a New Problem Set
62(1)
Previous Work
62(1)
Reorganization Operators
63(11)
The Jefferson Benchmark
64(3)
MTF
67(2)
SFS
69(4)
Competition
73(1)
The Experimentation
74(9)
The Languages
75(3)
Specific Considerations for the Language Recognition Problem
78(5)
Data Obtained from the Experimentation
83(4)
General Evaluation Criteria
87(1)
Evaluation
88(3)
Machine Size
88(1)
Convergence Rates
89(2)
Performance of MTF
91(1)
Conclusions and Further Directions
91(8)
Reference
93(6)
Using GA to Optimise the Selection and Scheduling of Road Projects
99(36)
Introduction
99(1)
Formulation of the Genetic Algorithm
100(6)
The Objective
100(1)
The Elements of the Project Schedule
100(1)
The Genetic Algorithm
100(6)
Mapping the GA String into a Project Schedule and Computing the Fitness
106(11)
Data Required
107(1)
Imposing Constraints
107(2)
Calculation of Project Benefits
109(5)
Calculating Trip Generation, Route Choice and Link Loads
114(3)
Results
117(15)
Convergence of Solutions to the Problem
117(2)
The Solutions
119(3)
Similarity and Dissimilarity of Solutions: Euclidean Distance
122(10)
Conclusions: Scheduling Interactive Road Projects by GA
132(3)
Dissimilar Construction Schedules with High and Almost Equal Payoffs
133(1)
Similar Construction Schedules with Dissimilar Payoffs
133(1)
References
133(2)
Decoupled Optimization of Power Electronics Circuits Using Genetic Algorithms
135(32)
Introduction
135(2)
Decoupled Regulator Configuration
137(3)
Optimization Mechanism of GA
139(1)
Chromosome and Population Structures
139(1)
Fitness Functions
140(1)
Fitness Functions for PCS
140(4)
OF1 for Objective (1)
141(2)
OF2 for Objective (2)
143(1)
OF3 for Objective (3)
144(1)
OF4 for Objective (4)
144(1)
Fitness function for FN
144(4)
OF5 for Objective (1)
145(1)
OF6 and OF8 for Objective (2) and Objective (4)
145(3)
OF8 of Objective (3)
148(1)
Steps of Optimization
148(3)
Design Example
151(14)
Conclusions
165(2)
References
165(2)
Feature Selection and Classification in the Diagnosis of Cervical Cancer
167(36)
Introduction
167(2)
Feature Selection
169(1)
Feature Selection by Genetic Algorithm
170(4)
GA Encoding Schemes
171(1)
GAs and Neural Networks
172(1)
GA Feature Selection Performance
172(1)
Conclusions
173(1)
Developing a Neural Genetic Classifier
174(4)
Algorithm Design Issues
174(1)
Problem Representation
175(2)
Objective Function
177(1)
Selection Strategy
177(1)
Parameterization
178(1)
Validation of the Algorithm
178(8)
The Dataset
178(1)
Experiments on Two-Dimensional Data
179(1)
Results of Two-Dimensional Data Experiments
180(4)
Lessons from Artificial Data
184(1)
Experiments on a Cell Image Dataset
184(2)
Parameterization of the GA
186(3)
Parameterization Experiments
186(1)
Results of Parameterization Experiments
187(1)
Selecting the Neural Network Architecture
188(1)
Experiments with the Cell Image Dataset
189(14)
Slide-Based vs. Cell-Based Features
189(5)
Comparison with the Standard Approach
194(4)
Discusison
198(1)
References
199(4)
Algorithms for Multidimensional Scaling
203(32)
Introduction
203(6)
Scope of This
Chapter
203(1)
What is Multidimensional Scaling?
204(4)
Standard Multidimensional Scaling Techniques
208(1)
Multidimensional Scaling Examined in More Detail
209(6)
A Simple One-Dimensional Example
209(2)
More than One Dimension
211(2)
Using Standard Multidimensional Scaling Methods
213(2)
A Genetic Algorithm for Multidimensional Scaling
215(6)
Random Mutation Operators
216(2)
Crossover Operators
218(1)
Selection Operators
219(1)
Design and Use of a Genetic Algorithm for Multidimensional Scaling
219(2)
Experimental Results
221(4)
Systematic Projection
221(1)
Using the Genetic Algorithm
222(1)
A Hybrid Approach
223(2)
The Computer Program
225(7)
The External Model
225(1)
Definition of Parameters and Variables
226(1)
The Main Program
227(1)
Procedures and Functions
228(3)
Adapting the Program for C or C++
231(1)
Using the Extended Program
232(3)
References
233(2)
Genetic Algorithm-Based Approach for Transportation Optimization Problems
235(40)
GA-Based Solution Approach for Transport Models
236(15)
Introduction
236(1)
GAB Approach for Single-Objective Bilevel Programming Models
236(8)
GAB Approach for Multi-Objective Bilevel Programming Models
244(6)
Summary
250(1)
GAB Calibration Approach for Transport Models
251(16)
Introduction
251(1)
Review of TFS
251(2)
Clibration Measures
253(3)
GAB Calibration Procedure
256(1)
Clibration of TFS
257(1)
Case Study
258(9)
Summary
267(1)
Concluding Remarks
267(8)
References
268(3)
Appendix I: Notation
271(4)
Solving Job-Shop Scheduling Problems by Means of Genetic Algorithms
275(20)
Introduction
275(1)
The Job-Shop Scheduling Constraint Satisfaction Problem
276(1)
The Genetic Algorithm
277(2)
Fitness Refinement
279(3)
Variable and Value Ordering Heuristics
280(2)
Heuristic Initial Population
282(2)
Experimental Results
284(7)
Conclusons
291(4)
References
292(3)
Applying the Implicit Redundant Representation Genetic Algorithm in an Unstructured Problem Domain
295(46)
Introduction
295(1)
Motivation for Frame Synthesis Research
296(1)
Modeling the Conceptual Design Process
296(1)
Research in Frame Optimization
297(1)
The Implicit Redundant Representation Genetic Algorithm
297(2)
Implementation of the IRR GA Algorithm
299(1)
Suitabilty of the IRR GA in Conceptual Design
299(1)
The IRR Genotype/Phenotype Representation
299(4)
Provision of Dynamic Redundancy
301(1)
Controlling the Level of Redundancy in the IRR GA Initial Population
302(1)
Applying the IRR GA to Frame Design Synthesis in an Unstructured Domain
303(20)
Unstructured Design Problem Formulation
303(1)
IRR GA Genotype/Phenotype Representation for Frame Design Synthesis
304(7)
Use of Repair Strategies on Frame Design Alternatives
311(6)
Generation of Horizontal Members in Design Synthesis Alternatives
317(2)
Specification of Loads on Unstructured Frame design Alternatives
319(4)
Finite-Element Analysis of Frame Structures
323(1)
Deletion of Dynamically Allocated Nodal Linked Lists
323(1)
IRR GA Fitness Evaluation of Frame Design Synthesis Alternatives
323(8)
Statement of Frame Design Objectives Used as Fitness Functions
323(2)
Application of Penalty Terms in IRR GA Fitness Evaluation
325(6)
Discussion of the Genetic Control Operators Used by the IRR GA
331(3)
Fitness Sharing among Individuals in the Population
331(1)
Tournament Selection of New Population Individuals
332(1)
Multiple Point Crossover of Binary Strings
333(1)
Single-Bit Mutation of Binary Strings
334(1)
Results of the Implicit Redundant Representation Frame Synthesis Trials
334(5)
Evolved Design Solutions for the Frame Synthesis Unstructured Domain
335(1)
Synthesis versus Optimization of Frame Design Solutions Using IRR GA
335(4)
Conclcuding Remarks
339(2)
References
339(2)
How to Handle Constraints with Evolutionary Algorithms
341(22)
Introduction
342(1)
Constraint Handling in EAs
342(3)
Evolutionary CSP Solvers
345(6)
Heuristic Genetic Operators
345(1)
Knowledge-Based Fitness and Genetic Operators
346(1)
Glass-Box Approach
347(1)
Genetic Local Search
348(1)
Co-evolutionary Approach
349(1)
Heuristic-Based Microgenetic Method
350(1)
Stepwise Adaptation to Weights
350(1)
Discussion
351(1)
Assessment of EAs for CSPs
352(3)
Conclusion
355(8)
References
356(7)
An Optimized Fuzzy Logic Controller for Active Power Factor Corrector Using Genetic Algorithm
363(28)
Introduction
363(2)
FLC for the Boost Rectifier
365(6)
Switching Rule for the Switch SW
366(1)
Fuzzy Logic Controller (FLC)
367(3)
Defuzzification
370(1)
Optimization of FLC by the Genetic Algorithm
371(8)
Structure of the Chromosome
371(1)
Initialization of Si
371(4)
Formulation of Multi-objective Fitness Function
375(1)
Selection of Chromosomes
376(1)
Crossover and Mutation Operations
376(2)
Validation of SI: Recovery of Valid Fuzzy Subsets
378(1)
Illustrative Example
379(10)
Conclusions
389(2)
References
389(2)
Multilevel Fuzzy Process Control Optimized by Genetic Algorithm
391(52)
Introduction
391(1)
Intelligent Control
392(1)
Multilevel Control
393(6)
Optimal Control Concept
393(3)
Process Stability during Genetic Algorithm Optimizing
396(1)
Optimizing Criteria
397(2)
Opitimizing Aided by Genetic Algorithm
399(2)
Genetic Algorithm Parameter
399(2)
Laboratory Cascaded Plant
401(11)
Multilevel Control Using Genetic Algorithm
412(7)
Non-coordinated Multilevel Control Using a PID Controller
412(7)
Fuzzy Multilevel Coordinated Control
419(15)
Decision Control Table
421(13)
Conclusions
434(9)
References
436(7)
Evolving Neural Networks for Cancer Radiotherapy
443(41)
Introduction and
Chapter Overview
443(1)
An Introduction to Radiotherapy
444(11)
Radiation Therapy Treatment Planning (RTP)
444(1)
Volumes
445(1)
Treatment Planning
446(1)
Recent Developments and Areas of Active Research
447(4)
Treatment Planning
451(4)
Evolutionary Artificial Neural Networks
455(8)
Evolving Network Weights
456(2)
Evolving Network Architectures
458(2)
Evolving Learning Rules
460(1)
EPNet
461(1)
Addition of Virtual Samples
462(1)
Summary
463(1)
Radiotherapy Treatment Planning with EANNs
463(17)
The Backpropogation ANN for Treatment Planning
463(3)
Development of an EANN
466(5)
EANN Results
471(6)
Breast Cancer Treatment Planning
477(3)
Summary
480(2)
Discussion and Future Work
482(2)
Acknowledgments
484(1)
References
485(4)
Index 489
Lance D. Chambers