Gaussian mixture model based hierarchical clustering in prediction of autism spectrum disorder

Abstract

Autism is one of the most complex and divergent class disorders which accompany various lacking in symptoms needed for classification, societal interaction, abridged verbal communication, and monotonous behavior. Timely and proper diagnosis of Autism Spectrum Disorder can ensure the offering of medical treatment and guidance to get cure. In this paper, Gaussian Mixture Model based Hierarchical Clustering is proposed for efficiently predicting the Autism Spectrum Disorder. Also, Flexible splitting concept was proposed for hierarchical clustering in order to increase the quality of guessing and classification accuracy. The proposed algorithm is validated to check the performance against the existing method. The results shows that the proposed algorithm outperforms the existing algorithm in terms of classification accuracy.