Design of an EP-based neuro-fuzzy classification model
Nai Ren Guo, Chao‐Lin Kuo, Tzong-Jiy Tsai · 2009
A new method for design of a classification system using the feature extraction and evolutionary programming (EP) are discussed. In this paper, a neuro-fuzzy classification model (NFCM) is proposed. The optimal fuzzy membership functions of the NFCM are extracted from the training data using EP. The NFCM contains the feature extraction unit and the inference unit. In order to improve the proposed NFCM, the Weight Revised Algorithm (WRA) is used to regulate the weight grade of the principal output node of the inference unit. The WRA is utilized for generating new weight to be added when additions are required. The performance is also compared to other classifiers tested on the same databases. Computer simulation results demonstrate that the proposed classification model can provide a sufficiently high classification rate in comparison with other models.