Classification of Noisy Signals Using Fuzzy ARTMAP Neural Networks

—This paper describes an approach to classification of noisy signals using a technique based on the fuzzy ARTMAP neural network (FAMNN). The proposed method is a modification of the testing phase of the fuzzy ARTMAP that exhibits superior generalization performance compared to the generalization performance of the standard fuzzy ARTMAP in the presence of noise. An application to textured grayscale image segmentation is presented. The superiority of the proposed modification over the standard fuzzy ARTMAP is established by a number of experiments using various texture sets, feature vectors and noise types. The texture sets include various aerial photos and also samples obtained from the Brodatz album. Furthermore, the classification performance of the standard and the modified fuzzy ARTMAP is compared for different network sizes. Classification results that illustrate the performance of the modified algorithm and the FAMNN are presented.

• Type: Conference
• Year: 2000
• Where: IJCNN
• Authors: Dimitrios Charalampidis, Michael Georgiopoulos, Takis Kasparis
• Keywords: Fuzzy ARTMAP, Generalization Performance, IJCNN 2000, Neural Networks, Standard Fuzzy Artmap