
Genetic Algorithms and Genetic Programming
Modern Concepts and Practical Applications
Preview
Book Description
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 identification using HeuristicLab as a platform for algorithm development.
The book focuses on both theoretical and empirical aspects. The theoretical sections explore the important and characteristic properties of the basic GA as well as main characteristics of the selected algorithmic extensions developed by the authors. In the empirical parts of the text, the authors apply GAs to two combinatorial optimization problems: the traveling salesman and capacitated vehicle routing problems. To highlight the properties of the algorithmic measures in the field of GP, they analyze GP-based nonlinear structure identification applied to time series and classification problems.
Written by core members of the HeuristicLab team, this book provides a better understanding of the basic workflow of GAs and GP, encouraging readers to establish new bionic, problem-independent theoretical concepts. By comparing the results of standard GA and GP implementation with several algorithmic extensions, it also shows how to substantially increase achievable solution quality.
Table of Contents
Introduction
Simulating Evolution: Basics about Genetic Algorithms
The Evolution of Evolutionary Computation
The Basics of Genetic Algorithms (GAs)
Biological Terminology
Genetic Operators
Problem Representation
GA Theory: Schemata and Building Blocks
Parallel Genetic Algorithms
The Interplay of Genetic Operators
Bibliographic Remarks
Evolving Programs: Genetic Programming
Introduction: Main Ideas and Historical Background
Chromosome Representation
Basic Steps of the Genetic Programming (GP)-Based Problem Solving Process
Typical Applications of GP
GP Schema Theories
Current GP Challenges and Research Areas
Conclusion
Bibliographic Remarks
Problems and Success Factors
What Makes GAs and GP Unique Among Intelligent Optimization Methods?
Stagnation and Premature Convergence
Preservation of Relevant Building Blocks
What Can Extended Selection Concepts Do to Avoid Premature Convergence?
Offspring Selection (OS)
The Relevant Alleles Preserving Genetic Algorithm (RAPGA)
Consequences Arising out of Offspring Selection and RAPGA
SASEGASA—More Than the Sum of All Parts
The Interplay of Distributed Search and Systematic Recovery of Essential Genetic Information
Migration Revisited
SASEGASA: A Novel and Self-Adaptive Parallel Genetic Algorithm
Interactions between Genetic Drift, Migration, and Self-Adaptive Selection Pressure
Analysis of Population Dynamics
Parent Analysis
Genetic Diversity
Characteristics of Offspring Selection and the RAPGA
Introduction
Building Block Analysis for Standard GAs
Building Block Analysis for GAs Using Offspring Selection
Building Block Analysis for the RAPGA
Combinatorial Optimization: Route Planning
The Traveling Salesman Problem
The Capacitated Vehicle Routing Problem
Evolutionary System Identification
Data-Based Modeling and System Identification
GP-Based System Identification in HeuristicLab
Local Adaption Embedded in Global Optimization
Similarity Measures for Solution Candidates
Applications of Genetic Algorithms: Combinatorial Optimization
The Traveling Salesman Problem
Capacitated Vehicle Routing
Data-Based Modeling with Genetic Programming
Time Series Analysis
Classification
Genetic Propagation
Single Population Diversity Analysis
Multi-Population Diversity Analysis
Code Bloat, Pruning, and Population Diversity
Conclusion and Outlook
Symbols and Abbreviations
References
Index
Author(s)
Biography
Michael Affenzeller is Professor for Applied Computer Science at the Department of Software Engineering of the Upper Austrian University of Applied Sciences in Hagenberg, Austria, as well as head of the Hueristic and Evolutionary Algorithms Laboratory research group. His interests include Heuristic Algorithms, Evolutionary Algorithms, Algorithm Theory and Development, Production Planning and Logistics Optimization, Nonlinear Systems Identification, Structure Identification, Regression and Time Series, Heuristic Optimization Techniques in Bioinformatics / Chemoinformatics.
Stefan Wagner is an associate professor of strategy (with tenure). Stefan joined ESMT Berlin in February 2011 as an assistant professor and was the TUSIAD/TCCI Chair in European Economic Integration from 2014 to 2015. Previously he was an assistant professor in the Institute of Innovation Research, Technology Management, and Entrepreneurship (INNO-tec) at the Ludwig Maximilian University of Munich, Germany. Stefan received his Habilitation in 2010 and his Doctorate in Management (summa cum laude) in 2005 from LMU. Stefan's research interests cover the intersection of firm strategy, technological innovation, industrial organization and law. Currently, he is primarily interested in the interaction of the changing landscape of intellectual property rights (in particular patent systems) and firms' long term strategy regarding their innovative activities. From a more practical perspective, he is also interested in venture creation and growth strategies for young firms.
Stephan Winkler is head of the Bioinformatics Research Group at University of Applied Sciences, Upper Austria. His research interests include Theory and Application of Genetic Algorithms and Genetic Programming, Machine Learning and Data Mining, Bioinformatics, Grey Box Identification of Nonlinear Systems (especially in the context of mechatronic applications), Software Development.
Andreas Beham is a senior researcher at the School of Informatics, Communications and Media at the University of Applied Sciences, Upper Austria. His research interests include the development and analysis of solution methods and their application to real-world relevant problems. In particular, he is interested in developing a guidance system for choosing and parameterizing metaheuristic methods.