Diagnosis of Parkinson’s Disease using Acoustic Analysis of Voice

Chaitanya Gupte¹ , Shruti Gadewar²

¹ Department of ETE, SIES Graduate School of Technology, Nerul, India.
² Department of ETE, SIES Graduate School of Technology, Nerul, India.

Section:Research Paper, Product Type: Journal
Vol.5 , Issue.3 , pp.14-18, Jun-2017

Online published on Jun 30, 2017

Copyright © Chaitanya Gupte, Shruti Gadewar . This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
 

View this paper at   Google Scholar | DPI Digital Library

XML View     PDF Download

How to Cite this Paper

1384 Views    789 Downloads    388 Downloads

Abstract :
Acoustic analysis of voice is one of the cost effective method for detecting Parkinson disease. It is also a noninvasive, reliable and easy to use method. Also voice deviation from normal one is the earliest indicator of Parkinson. Voice data of sustained phonation has been collected from 8 healthy and 23 Parkinson subjects. The voice database is analyzed using PRAAT Software and 26 acoustic features are extracted. Some of the features being Jitters, Shimmers, Harmonic to Noise Ratio (HNR), Noise to Harmonic Ratio (NHR), Autocorrelation (AC). The values of these parameters show variation among two groups. A row vector is prepared using these parameters and fed to the classifiers. Classifiers such as Artificial Neural Network (ANN), Support Vector Machine (SVM), k-nearest neighbors (kNN), Adaboost, Decision trees and Random Forest have been tested and it was found that SVM is the best which gives the accuracy of 90%. Performances of classifiers are evaluated in terms of accuracy, precision, recall and total execution time.

Key-Words / Index Term :
Parkinson’s disease, PRAAT, Acoustic features, Support Vector Machine, Neural Networks

References :
[1]. A. K. Ho, “Speech impairment in a large sample of patients with Parkinson’s disease�, Behav. Neurol., Vol.11, Issue.3, pp. 131-137, 1997
[2]. S. Saloni, R. K. Sharma, Anil K. Gupta, “Disease detection using voice analysis: A reviewâ€�, International Journal of Medical Engg. and Informatics, Vol.6, Issue.3, pp.189-209, 2014.

[3]. M. Shahbakhti, D. Taherifar, A. Sorouri, “Linear and non-linear speech features for detection of Parkinson’s disease�, Biomedical Engineering International Conference, Thailand, pp.1-3, 2013.
[4]. J.A. Logemann, H.B. Fisher, B. Boshes, E.R. Blonsky, “Frequency and co-occurrence of vocal-tract dysfunctions in speech of a large sample of Parkinson patients�, Journal of Speech and Hearing Disorders, Vol.43, Issue.1, pp,.47-57, 1978.
[5]. A. Dastanpour, S. Ibrahim, R. Mashinchi, "Effect of Genetic Algorithm on Artificial Neural Network for Intrusion Detection System", International Journal of Computer Sciences and Engineering, Vol.4, Issue.10, pp.10-18, 2016.
[6]. A. Tsanas, M. A. Little, P. E. McSharry, J. Spielman, L. O. Ramig, “Novel speech signal processing algorithms for high-accuracy classification of Parkinson’s disease�, IEEE Transactions on Biomedical Engineering, Vol.59, Issue.5, pp.1264-1271, 2012.