In this paper, a neuron-fuzzy classification model (NFCM) is proposed that enables the extraction the feature variable and infers the classification results. The NFCM automatically generates the rules from the numerical data and triangular functions are used as the membership functions both in the feature extraction unit and the inference unit. To improve the proposed NFCM, one modificatory algorithm is applied. We utilize the Evolutionary Programming (EP) to determine the distribution of the fuzzy sets for each feature variable of the feature extraction unit. Finally, the proposed NFCM has been validated using one benchmark data set that is the Wine database.
Relation:
The 16th Natinal Conference on Fuzzy Theory and Its Applications, pp.591-596 中華民國第16屆模糊理論及其應用研討會會議手冊 模糊理論及其應用研討會
