1st Edition

The Practical Handbook of Genetic Algorithms New Frontiers, Volume II

Edited By Lance D. Chambers Copyright 1995

    The mathematics employed by genetic algorithms (GAs)are among the most exciting discoveries of the last few decades. But what exactly is a genetic algorithm? A genetic algorithm is a problem-solving method that uses genetics as its model of problem solving. It applies the rules of reproduction, gene crossover, and mutation to pseudo-organisms so those "organisms" can pass beneficial and survival-enhancing traits to new generations. GAs are useful in the selection of parameters to optimize a system's performance. A second potential use lies in testing and fitting quantitative models. Unlike any other book available, this interesting new text/reference takes you from the construction of a simple GA to advanced implementations. As you come to understand GAs and their processes, you will begin to understand the power of the genetic-based problem-solving paradigms that lie behind them.

    Contents
    Introduction
    Multi-Niche Crowding for Multi-modal Search
    Introduction
    Genetic Algorithms for Multi-modal Search
    Application of MNC to Multi-modal Test Functions
    Application to DNA Restriction Fragment Map Assembly
    Results and Discussion
    Conclusions
    Previous Related Work and Scope of Present Work
    Appendix
    Artificial Neural Network Evolution: Learning to Steer a Land Vehicle
    Overview
    Introduction to Artificial Neural Networks
    Introduction to ALVINN
    The Evolutionary Approach
    Task Specifics
    Implementation and Results
    Conclusions
    Future Directions
    Locating Putative Protein Signal Sequences
    Introduction
    Implementation
    Results of Sample Applications
    Parametrization Study
    Future Directions
    Selection Methods for Evolutionary Algorithms
    Fitness Proportionate Selection (FPS)
    Windowing
    Sigma Scaling
    Linear Scaling
    Sampling Algorithms
    Ranking
    Linear Ranking
    Exponential Ranking
    Tournament Selection
    Genitor or Steady State Models
    Evolution Strategy and Evolutionary Programming Methods
    Evolution Strategy Approaches
    Top-n Selection
    Evolutionary Programming Methods
    The Effects of Noise
    Conclusions
    References
    Parallel Cooperating Genetic Algorithms: An Application to Robot Motion Planning
    Introduction
    Principles of Genetic Algorithms
    The Search Algorithm
    The Explore Algorithm
    The Ariadne’s CLEW Algorithm
    Parallel Implementation
    Conclusion, Results, and Perspective
    The Boltzmann Selection Procedure
    Introduction
    Empirical Analysis
    Introduction to Boltzmann Selection
    Theoretical Analysis
    Discussion and Related Work
    Conclusion
    Structure and Performance of Fine-Grain Parallelism in Genetic Search
    Introduction
    Three Fine-Grain Parallel GA Topologies
    Performance of fgpGAs and cgpGAs
    Future Directions
    Parameter Estimation for a Generalized Parallel Loop Scheduling Algorithm
    Introduction
    Current Scheduling Algorithms
    A New Scheduling Methodology
    Results
    Conclusion
    Controlling a Dynamic Physical System Using Genetic-based Learning Methods
    Introduction
    The Control Task
    Previous Learning Algorithms for the Pole-Cart Problem
    Genetic Algorithms (GA)
    Generating Control Rules Using a Simple GA
    Implementation Details
    Experimental Results
    Difficulties with GAPOLE Approach
    A Different Genetic Approach for the Problem
    The Structured Genetic Algorithm
    Evolving Neuro-controllers Using sGA
    Fitness Measure and Reward Scheme
    Simulation Results
    Discussion
    A Hybrid Approach Using Neural Networks, Simulation, Genetic Algorithms, and Machine Learning for Real-time Sequencing and Scheduling Problems
    Introduction
    Hierarchical Generic Controller
    Implementing the Optimization Function
    An Example
    Remarks
    Chemical Engineering
    Introduction
    Case Study 1: Best Controller Synthesis Using Qualitative Criteria
    Case Study 2: Optimization of Back Mix Reactors in Series
    Case Study 3: Solution of Lattice Model to Predict Adsorption of Polymer Molecules
    Comparison with Other Techniques
    Vehicle Routing with Time Windows Using Genetic Algorithms
    Introduction
    Mathematical Formulation for the VRPTW
    The GIDEON System
    Computational Results
    Summary and Conclusions
    Evolutionary Algorithms and Dialogue
    Introduction
    Methodology
    Evolutionary Algorithms
    Natural Language Processing
    Dialogue in LOLITA
    Tuning the Parameters
    Target Dialogues
    Application of EAs to LOLITA
    Results
    Improving the Fitness Function
    Discussion
    Summary
    References
    Incorporating Redundancy and Gene Activation Mechanisms in Genetic Search for Adapting to Non-Stationary Environments
    Introduction
    The Structured GA
    Use of sGA in a Time-varying Problem
    Experimental Details
    Conclusions
    Input Space Segmentation with a Genetic Algorithm for Generation of Rule-based Classifier Systems
    Introduction
    A Heuristic Method
    Genetic Algorithm Based Method
    Results
    Appendix I: An Indexed Bibliography of Genetic Algorithms
    Appendix II: Publications Contract

    Biography

    Chambers, Lance D.