Early diagnosis of Parkinson’s disease from multiple voice recordings by simultaneous sample and feature selection

作者：

Highlights：

• We validate the hypothesis that multiple samples per subject might degrade the accuracy.

• To enhance the accuracy, two dimensional data selection approach has been proposed.

• The proposed method selects samples and features simultaneously, and outperforms the existing methods.

摘要

•We validate the hypothesis that multiple samples per subject might degrade the accuracy.•To enhance the accuracy, two dimensional data selection approach has been proposed.•The proposed method selects samples and features simultaneously, and outperforms the existing methods.

论文关键词：Deep neural network,Feature selection,Hyper-parameters optimization,Parkinson’S disease,Sample selection

论文评审过程：Received 14 November 2018, Revised 4 March 2019, Accepted 24 June 2019, Available online 28 June 2019, Version of Record 4 July 2019.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.06.052