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 convinces that this approach has the ability to handle classification problems with large data dimension.
| Original language | English |
|---|---|
| Pages (from-to) | 1063-1067 |
| Journal | IECON Proceedings (Industrial Electronics Conference) |
| Volume | 3 |
| DOIs | |
| Publication status | Published - 1997 |
| Event | 23rd Annual International Conference on Industrial Electronics, Control, and Instrumentation (IECON '97) - New Orleans, LA, United States Duration: 9 Nov 1997 → 14 Nov 1997 |
UN SDGs
This output contributes to the following UN Sustainable Development Goals (SDGs)
-
SDG 3 Good Health and Well-being
Fingerprint
Dive into the research topics of 'Genetic fuzzy classifier for benchmark cancer diagnosis'. Together they form a unique fingerprint.Cite this
- APA
- Author
- BIBTEX
- Harvard
- Standard
- RIS
- Vancouver