Title :
A GA-based optimal gene subset selection method
Author :
Ding, Sheng-Chao ; Liu, Juan ; Yang, Qing
Author_Institution :
Sch. of Comput., Wuhan Univ., China
Abstract :
In tissue diagnosis with microarray data, selecting the optimal gene subset is very essential for various merits. Different from existing methods, we propose a novel optimal gene subset selection method based on genetic algorithms (GAs). Special fitness function is applied in this scheme. This GA-based method automatically determines the size of a predictive gene group, as well as the members in such a group. The evaluation experiments are applied to two popular data sets. The results and some discussions are presented too.
Keywords :
biological tissues; genetic algorithms; patient diagnosis; pattern classification; GA based method; fitness function; gene size prediction; genetic algorithms; microarray technology; optimal gene subset selection method; tissue diagnosis; two class classification problem; Cancer; Gene expression; Genetic algorithms; Mathematics; Microscopy; Modems; Statistics; Support vector machine classification; Support vector machines; Training data;
Conference_Titel :
Machine Learning and Cybernetics, 2004. Proceedings of 2004 International Conference on
Print_ISBN :
0-7803-8403-2
DOI :
10.1109/ICMLC.2004.1378505
