Title :
Genetic fuzzy classifier for benchmark cancer diagnosis
Author :
Ke, J.Y. ; Tang, K.S. ; Man, K.F.
Author_Institution :
Dept. of Electron. Eng., City Univ. of Hong Kong, Kowloon, Hong Kong
Abstract :
An effective fuzzy classifier is proposed for solving a benchmark cancer diagnosis problem. This system comprises the use of optimized fuzzy membership functions through genetic algorithms, while the associated rules are generated from numerical data. In addition, a modified nearest-neighbour method is recommended to remedy the drawback of rules confinement. The end result shows that this approach has the ability to handle classification problems with large data dimension
Keywords :
fuzzy set theory; genetic algorithms; patient diagnosis; associated rules; benchmark cancer diagnosis; genetic fuzzy classifier; modified nearest-neighbour method; optimized fuzzy membership functions; rules confinement; Cancer; Data structures; Diseases; Electronic mail; Fuzzy logic; Fuzzy systems; Genetic algorithms; Medical diagnosis; Medical diagnostic imaging; Shape measurement;
Conference_Titel :
Industrial Electronics, Control and Instrumentation, 1997. IECON 97. 23rd International Conference on
Conference_Location :
New Orleans, LA
Print_ISBN :
0-7803-3932-0
DOI :
10.1109/IECON.1997.668428
