Genetic fuzzy classifier for benchmark cancer diagnosis
J.Y. Ke, K.S. Tang, K.F. Man · 2002
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.