Genetic algorithms and genetic programming modern concepts and practical applications
Genetic Algorithms and Genetic Programming: Modern Concepts and Practical Applications discusses algorithmic developments in the context of genetic algorithms (GAs) and genetic programming (GP). It applies the algorithms to significant combinatorial optimization problems and describes structure iden...
Uloženo v:
| Hlavní autor: | |
|---|---|
| Médium: | E-kniha Kniha |
| Jazyk: | angličtina |
| Vydáno: |
Boca Raton
CRC Press
2009
Chapman & Hall/CRC Taylor & Francis CRC Press LLC |
| Vydání: | 1 |
| Edice: | Numerical Insights |
| Témata: | |
| ISBN: | 1584886293, 9781584886297, 1138114278, 9781138114272, 0429141971, 9780429141973, 9781040044254, 1040044255, 9781420011326, 1420011324 |
| On-line přístup: | Získat plný text |
| Tagy: |
Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
|
Obsah:
- Cover -- Half-title Page -- Series Page -- Title Page -- Copyright Page -- Contents -- List of Tables -- List of Figures -- List of Algorithms -- Introduction -- 1 Simulating Evolution: Basics about Genetic Algorithms -- 1.1 The Evolution of Evolutionary Computation -- 1.2 The Basics of Genetic Algorithms -- 1.3 Biological Terminology -- 1.4 Genetic Operators -- 1.4.1 Models for Parent Selection -- 1.4.2 Recombination (Crossover) -- 1.4.3 Mutation -- 1.4.4 Replacement Schemes -- 1.5 Problem Representation -- 1.5.1 Binary Representation -- 1.5.2 Adjacency Representation -- 1.5.3 Path Representation -- 1.5.4 Other Representations for Combinatorial Optimization Problems -- 1.5.5 Problem Representations for Real-Valued Encoding -- 1.6 GA Theory: Schemata and Building Blocks -- 1.7 Parallel Genetic Algorithms -- 1.7.1 Global Parallelization -- 1.7.2 Coarse-Grained Parallel GAs -- 1.7.3 Fine-Grained Parallel GAs -- 1.7.4 Migration -- 1.8 The Interplay of Genetic Operators -- 1.9 Bibliographic Remarks -- 2 Evolving Programs: Genetic Programming -- 2.1 Introduction: Main Ideas and Historical Background -- 2.2 Chromosome Representation -- 2.2.1 Hierarchical Labeled Structure Trees -- 2.2.1.1 Basics -- 2.2.1.2 Evaluation -- 2.2.1.3 Genetic Operations: Crossover and Mutation -- 2.2.1.4 Advantages -- 2.2.2 Automatically Defined Functions and Modular Genetic Programming -- 2.2.3 Other Representations -- 2.2.3.1 Linear Genetic Programming -- 2.2.3.2 Graphical Genetic Programming -- 2.3 Basic Steps of the GP-Based Problem Solving Process -- 2.3.1 Preparatory Steps -- 2.3.2 Initialization -- 2.3.3 Breeding Populations of Programs -- 2.3.4 Process Termination and Results Designation -- 2.4 Typical Applications of Genetic Programming -- 2.4.1 Automated Learning of Multiplexer Functions -- 2.4.2 The Artificial Ant -- 2.4.3 Symbolic Regression
- The Triangle Inequality -- Euclidean Distances -- 8.1.1.2 Versions of the TSP -- Traveling Salesman Subtour Problems (TSSP) -- Postman Problems -- Time Dependent TSP -- Traveling Salesman Problem with Time Windows (TSPTW) -- 8.1.1.3 Review of Optimal Algorithms -- Total Enumeration -- Integer Programming -- 8.1.2 Review of Approximation Algorithms and Heuristics -- Nearest Neighbor Heuristics -- Partitioning Heuristics -- Local Search -- The 2-Opt Method -- The 3-Opt Method -- The k-opt Method -- 8.1.3 Multiple Traveling Salesman Problems -- 8.1.4 Genetic Algorithm Approaches -- 8.1.4.1 Problem Representations and Operators -- Adjacency Representation -- Ordinal Representation -- Path Representation -- 8.2 The Capacitated Vehicle Routing Problem -- 8.2.1 Problem Statement and Solution Methodology -- 8.2.1.1 Definition of the CVRP -- 8.2.1.2 Exact Algorithms -- 8.2.1.3 Approximation Algorithms and Heuristics -- The Savings Heuristic -- The Sweep Heuristic -- The Push Forward Insertion Heuristic -- Other Methods -- 8.2.2 Genetic Algorithm Approaches -- 8.2.2.1 Crossover Operators -- Sequence-Based Crossover (SBX) -- Route-Based Crossover (RBX) -- Other Crossover Operators -- 8.2.2.2 Mutation Operators -- Relocate -- Exchange -- 2-Opt -- 2-Opt∗ -- Or-Opt -- One Level Exchange (M1) -- Two Level Exchange (M2) -- Local Search (LSM) -- 9 Evolutionary System Identification -- 9.1 Data-Based Modeling and System Identification -- 9.1.1 Basics -- 9.1.2 An Example -- 9.1.2.1 Learning Polynomial Models -- 9.1.2.2 Testing Polynomial Models -- 9.1.2.3 Implementation -- 9.1.3 The Basic Steps in System Identification -- 9.1.4 Data-Based Modeling Using Genetic Programming -- 9.2 GP-Based System Identification in HeuristicLab -- 9.2.1 Introduction -- 9.2.2 Problem Representation -- 9.2.3 The Functions and Terminals Basis -- 9.2.3.1 Motivation, Introduction
- 10.2.2.3 Empirical Results -- 11 Data-Based Modeling with Genetic Programming -- 11.1 Time Series Analysis -- 11.1.1 Time Series Specific Evaluation -- 11.1.2 Application Example: Design of Virtual Sensors for Emissions of Diesel Engines -- 11.1.2.1 Designing Virtual Sensors for Nitric Oxides (NO[sub(x)]) -- 11.1.2.2 Designing Virtual Sensors for Particulate Emissions (Soot) -- 11.1.2.3 NO[sub(x)] Data Sets Used for Further Empirical Studies -- NO[sub(x)] Data Set II -- NO[sub(x)] Data Set III -- 11.2 Classification -- 11.2.1 Introduction -- 11.2.2 Real-Valued Classification with Genetic Programming -- 11.2.3 Analyzing Classifiers -- 11.2.3.1 Classification Rates and Confusion Matrices -- 11.2.3.2 Receiver Operating Characteristic (ROC) Curves -- 11.2.3.3 Sets of Receiver Operating Characteristic Curves and their Use in the Evaluation of Multi-Class Classification -- 11.2.4 Classification Specific Evaluation in GP -- 11.2.4.1 Preprocessing of Estimated Target Values -- 11.2.4.2 Considering Standard Evaluation Functions -- 11.2.4.3 Considering Classification Specific Aspects -- Class Ranges -- Thresholds Analysis -- (M)ROC Analysis -- 11.2.4.4 Combined Classifier Evaluation -- 11.2.5 Application Example: Medical Data Analysis -- 11.2.5.1 Benchmark Data Sets -- 11.2.5.2 Solution Candidate Representation Using Hybrid Tree Structures -- 11.2.5.3 Evaluation of Classification Models -- 11.2.5.4 Finding Appropriate Class Thresholds: Dynamic Range Selection -- 11.2.5.5 First Results, Identification of Optimal Operators and Parameter Settings -- 11.2.5.6 Graphical Classifier Analysis -- 11.2.5.7 Classification Methods Applied in Detailed Test Series -- GP-Based Training of Classifiers -- Linear Modeling -- Neural Networks -- kNN Classification -- Support Vector Machines -- 11.2.5.8 Detailed Test Series Results -- Results for the Wisconsin Data Set
- 2.4.4 Other GP Applications -- 2.5 GP Schema Theories -- 2.5.1 Program Component GP Schemata -- 2.5.2 Rooted Tree GP Schema Theories -- 2.5.3 Exact GP Schema Theory -- 2.5.4 Summary -- 2.6 Current GP Challenges and Research Areas -- 2.7 Conclusion -- 2.8 Bibliographic Remarks -- 3 Problems and Success Factors -- 3.1 What Makes GAs and GP Unique among Intelligent Optimization Methods? -- 3.2 Stagnation and Premature Convergence -- Classical Measures for Diversity Maintenance -- Limitations of Diversity Maintenance -- 4 Preservation of Relevant Building Blocks -- 4.1 What Can Extended Selection Concepts Do to Avoid Premature Convergence? -- 4.2 Offspring Selection (OS) -- 4.3 The Relevant Alleles Preserving Genetic Algorithm (RAPGA) -- 4.4 Consequences Arising out of Offspring Selection and RAPGA -- 5 SASEGASA - More than the Sum of All Parts -- Dynamic Migration Intervals -- From Islands to Growing Villages -- 5.1 The Interplay of Distributed Search and Systematic Recovery of Essential Genetic Information -- 5.2 Migration Revisited -- 5.3 SASEGASA: A Novel and Self-Adaptive Parallel Genetic Algorithm -- 5.3.1 The Core Algorithm -- 5.4 Interactions among Genetic Drift, Migration, and Self-Adaptive Selection Pressure -- 6 Analysis of Population Dynamics -- 6.1 Parent Analysis -- 6.2 Genetic Diversity -- 6.2.1 In Single-Population GAs -- 6.2.2 In Multi-Population GAs -- 6.2.3 Application Examples -- 7 Characteristics of Offspring Selection and the RAPGA -- 7.1 Introduction -- 7.2 Building Block Analysis for Standard GAs -- 7.3 Building Block Analysis for GAs Using Offspring Selection -- 7.4 Building Block Analysis for the Relevant Alleles Preserving GA (RAPGA) -- 8 Combinatorial Optimization: Route Planning -- 8.1 The Traveling Salesman Problem -- 8.1.1 Problem Statement and Solution Methodology -- 8.1.1.1 Definition of the TSP -- Symmetry
- 9.2.3.2 Definition of the Evaluation of Terminals -- 9.2.3.3 Definition of the Evaluation of Functions -- 9.2.3.4 String Representations of Terminals and Functions -- 9.2.3.5 Parametrization of Terminals and Functions -- 9.2.4 Solution Representation -- 9.2.4.1 Representing Formulas by Structure Trees -- 9.2.4.2 Initialization, Crossover, and Mutation -- 9.2.5 Solution Evaluation -- 9.2.5.1 Standard Solution Evaluation Operators -- 9.2.5.2 Combined Solution Evaluation -- 9.2.5.3 Adjusted Solution Evaluation -- 9.2.5.4 Runtime Consumption Considerations -- 9.2.5.5 Early Stopping of Model Evaluation -- 9.3 Local Adaption Embedded in Global Optimization -- 9.3.1 Parameter Optimization -- 9.3.2 Pruning -- 9.3.2.1 Basics and Method Parameters -- 9.3.2.2 Pruning a Structure Tree -- 9.3.2.3 Exhaustive Pruning -- 9.3.2.4 ES-Inspired Pruning -- 9.4 Similarity Measures for Solution Candidates -- 9.4.1 Evaluation-Based Similarity Measures -- 9.4.2 Structural Similarity Measures -- 10 Applications of Genetic Algorithms: Combinatorial Optimization -- 10.1 The Traveling Salesman Problem -- 10.1.1 Performance Increase of Results of Different Crossover Operators by Means of Offspring Selection -- 10.1.2 Scalability of Global Solution Quality by SASEGASA -- 10.1.3 Comparison of the SASEGASA to the Island-Model Coarse-Grained Parallel GA -- 10.1.4 Genetic Diversity Analysis for the Different GA Types -- 10.2 Capacitated Vehicle Routing -- 10.2.1 Results Achieved Using Standard Genetic Algorithms -- 10.2.1.1 Quality Progress of the Genetic Algorithm -- 10.2.1.2 Diversity Progress of the Genetic Algorithm -- 10.2.1.3 Empirical Results -- 10.2.2 Results Achieved Using Genetic Algorithms with Offspring Selection -- 10.2.2.1 Improvement in Quality Progress with Offspring Selection -- 10.2.2.2 Improved Diversity Progress with Offspring Selection
- Results for the Melanoma Data Set