Medical image classification and symptoms detection using fuzzy NARX technique

Abstract

In this paper the novel neural NARX technique was applied for classification and detection purposes. Decision making was performed in two stages: feature extraction using the principal component analysis (PCA) and the neural NARX model trained with the backpropagation method. The performance of the neural NARX-based classifier was evaluated in terms of training and classification accuracies. The results confirmed that the proposed neural NARX-based classifier has potential in detecting the tumors. © 2013 IFMBE.