An Efficient Approach for the Design of Transparent Fuzzy Rule-Based Classifiers

摘要: In the last few years a number of studies have proposed algorithms that can obtain fuzzy systems which are simple and easy to read, while maintaining quite high level accuracy. Following this philosophy, paper presents simple, new approach based on Genetic Algorithms, with aim selecting features tuning parameters classification algorithm. From results obtained by optimized classifier transparent, efficient system is generated using heuristic methods. The main accuracy, scalability, adaptability expandability. Comparative examples three data sets well known in pattern field given, showing leads classifiers small readable rules, less complex than those reported literature comparable or better