Acoustic feature selection utilizing multiple kernel learning for classification of children with autism spectrum and typically developing children

Abstract

This paper reports the result of a classification experiment carried out using acoustic features for children with autism spectrum, where a new featureweighting method using a multiple kernel learning (MKL) algorithm is proposed for classification between children with autism spectrum and typically developing children. Our MKL-SVM simultaneously estimates both the classification boundary and weight of each acoustic feature, where 484 acoustic features are used in our experiments. The estimated weight indicates how acoustic features are useful for classification. Our results show the large weight acoustic features mainly for line spectral frequencies in the classification experiment using acoustic features for children with autism spectrum.

Normalization of Behavioral Features in Autism Spectrum Disorder With Influencing Attributes

“…The fusion of Conditional Mutual Information Maximization and the SVM Recursive Feature Elimination give raise to a hybrid feature selection method using optimal SNP subset for higher accuracy [15]. A feature weighting method using a multiple kernel learning (MKL) algorithm using acoustic features for ASD children to classify [16].…”