BROWSE
Detail
Journal Article
Feature Selection in Genetic Fuzzy Discretization for the Pattern Classification Problems
Cited 16 time in 
Share 
Share
- Authors
- Yoon-Seok Choi, Byung-Ro Moon
- Issue Date
- 2007-07
- Citation
- IEICE Transactions on Information and Systems, v.E90-D, no.7, pp.1047-1054
- ISSN
- 0916-8532
- Publisher
- 일본, 전자정보통신학회 (IEICE)
- Language
- English
- Type
- Journal Article
- Abstract
- We propose a new genetic fuzzy discretization method with feature selection for the pattern classification problems. Traditional discretization methods categorize a continuous attribute into a number of bins. Because they are made on crisp discretization, there exists considerable information loss. Fuzzy discretization allows overlapping intervals and reflects linguistic classification. However, the number of intervals, the boundaries of intervals, and the degrees of overlapping are intractable to get optimized and a discretization process increases the total amount of data being transformed. We use a genetic algorithm with feature selection not only to optimize these parameters but also to reduce the amount of transformed data by filtering the unconcerned attributes. Experimental results showed considerable improvement on the classification accuracy over a crisp discretization and a typical fuzzy discretization with feature selection. Copyright © 2007 The Institute of Electronics, Information and Communication Engineers.
- KSP Keywords
- Classification problems, Continuous attribute, Discretization method, Feature selection(FS), Fuzzy discretization, Genetic Algorithm, Information Loss, Information and communication, Pattern classification, classification accuracy, number of bins