Pattern recognition based on weighted and supervised ART2

It is crucial for TCM (traditional chinese medicine) post-hepatitis cirrhosis diagnosis to accurately identify the syndrome. Meanwhile, the selection of features which are relevant to a certain TCM post-hepatitis cirrhosis syndrome not only improves the performance of the classifiers, but also provides well measure for treatment. Therefore, in this paper, we analyze the classical ART2(adaptive resonance theory 2) neural network, such as the problem of pattern drifting and the same phase data with different amplitudes. Based on this, here, a novel network named SWART2 is proposed by taking dispersion testing and centroid computation learning, and introducing the weighted and supervised mechanism, which aims at improving ART2¿s ability of classification greatly for post-hepatitis cirrhosis diagnosis. Experimental results in this paper showed that the new SWART2 performed better than classical ART2.