DocumentCode :
3399645
Title :
On taxonomy of evolutionary computation problems
Author :
Ashlock, Dan ; Bryden, Kenneth M. ; Corns, Steven
Author_Institution :
Dept. of Math., Iowa State Univ., Ames, IA, USA
Volume :
2
fYear :
2004
fDate :
19-23 June 2004
Firstpage :
1713
Abstract :
Taxonomy is the practice of classifying members of a group based on their measurable characteristics. In evolutionary computation the problem of telling when two problems are similar is both challenging and important. An accurate classification technique would yield large benefits by permitting a researcher to rationally choose algorithm and parameter setting based on past experience. A good classification technique would also permit the selection of diverse test suites that would give a useful sense of the proper domain of application of a new technique. This study uses a standard taxonomic technique, hierarchical clustering, on a set of taxonomic characters derived from a comparative study using graph based evolutionary algorithms. The result is a cladogram that classifies the problems used in a reasonable fashion. Based on this we then argue that the technique given here can be used to provide an objective, automatic, extensible classification tool for any collection of evolutionary problems and discuss possible methods for improving the technique.
Keywords :
data visualisation; evolutionary computation; graph theory; pattern classification; pattern clustering; tree data structures; tree searching; cladogram; classification technique; evolutionary computation problems; graph based evolutionary algorithms; hierarchical clustering; standard taxonomic technique; taxonomy; Cams; Classification tree analysis; Clustering algorithms; Evolutionary computation; Insects; Mathematics; Mechanical engineering; Mechanical variables measurement; Organisms; Taxonomy;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Evolutionary Computation, 2004. CEC2004. Congress on
Print_ISBN :
0-7803-8515-2
Type :
conf
DOI :
10.1109/CEC.2004.1331102
Filename :
1331102
Link To Document :
بازگشت