Residual-Network -Based Deep Learning for Parkinson's Disease Classification using Vocal Datasets

Abstract

For the diagnosis and early detection of Parkinson's disease, a noninvasive method based on observed abnormal motor signs is desired. Therefore, in this paper, a 10-layered 1-d convolutional neural network (CNN) and novel-residual-network-type 1-d CNN were introduced for Parkinson's disease classification using vocal feature datasets. The resulting residual network provided a good classification result with an accuracy of 0.888, F-measure of 0.928, and MCC of 0.692.