The explosion of DNA and protein sequence data in public and private databases has been encouraging interdisciplinary research on biology and information technology. Gene expression profiles are just sequences of numbers, and the necessity of tools analyzing them to get useful information has risen significantly. In order to predict the cancer class of patients from the gene expression profile, this paper presents a classification framework that combines a pair of classifiers trained with mutually exclusive features. The idea behind feature selection with nonoverlapping correlation is to encourage classifier ensemble, which consists of multiple classifiers, to leam different aspects of training data, so that classifiers can search in a wide solution space. Experimental results show that the classifier ensemble produces higher recognition accuracy than conventional classifiers.
Bibliographical noteFunding Information:
Manuscript received March 15, 2002; revised July 15, 2002. This work was supported by Brain Science and Engineering Research Program sponsored by Korean Ministry of Science and Technology. The authors are with the Department of Computer Science, Yonsei University, Seoul 120-749, Korea (e-mail: email@example.com; rjungwon@ yahoo.com). Digital Object Identifier 10.1109/JPROC.2002.804682
All Science Journal Classification (ASJC) codes
- Electrical and Electronic Engineering