Dynamic feature selection for detecting Parkinson's disease through voice signal

Abstract

Parkinson's disease (PD) is a disorder of the central nervous system and about 89% of the people with PD suffering from speech and voice disorders. In this paper, we adopted a dynamic feature selection based on fuzzy entropy measures for speech pattern classification of Parkinson's diseases. To investigate the effect of feature selection, Linear Discriminant Analysis (LDA) was applied to distinguish voice samples between PD patients and health people. The data set of this research is composed of voice signals from 40 people, 20 with Parkinson's disease and 20 health people. The results show that various voice samples need different feature selection. We applied dynamic feature selection can get higher rate of classification accuracy than all features selected.

Cite this paper

@article{Su2015DynamicFS, title={Dynamic feature selection for detecting Parkinson's disease through voice signal}, author={Meilin Su and Keh-Shih Chuang}, journal={2015 IEEE MTT-S 2015 International Microwave Workshop Series on RF and Wireless Technologies for Biomedical and Healthcare Applications (IMWS-BIO)}, year={2015}, pages={148-149} }