|
Abstract:
|
At present, it is intensely discussed which type of experimental research methodologies should be used to improve the acceptance and quality of evolutionary algorithms (EA). SPO combines methods from classical Design of Experiments (DOE) and modern stochastical tools, e.g., Design and Analysis of Computer Experiments (DACE). SPO has been applied in the following domains: - Machine engineering: Design of mold temperature control - Aerospace industry: Airfoil design optimization - Simulation and optimization: Elevator group control - Algorithm engineering: Graph drawing - Computational Intelligence: Algorithmic chemistry - Technical Thermodynamics: Non-sharp separation sequences - Economy: Agri-environmental policy-switchings - Statistics: Selection under uncertainty for Particle Schwarm Optimization - Evolution strategies: Threshold selection und step-size adaptation - Particle swarm optimization: Analysis und application - Numerics: Comparison and analysis of classical and modern optimization algorithms [Bart06a] provides a comprehensive introduction. An SPO-toolbox, which complements the book, is freely available (http://ls11-www.cs.uni- dortmund.de/people/tom/ExperimentalResearch.html). Literature: [Eibe02a] Eiben, A. and Jelasity, M. (2002) A critical note on experimental research methodology in EC. In Proceedings of the 2002 Congress on Evolutionary Computation (CEC'2002), pages 582-587, IEEE Press [Bart06a] Thomas Bartz-Beielstein. Experimental Research in Evolutionary Computation - The New Experimentalism. Natural Computing Series. Springer, Berlin, 2006.
|
