Voice Analysis for Telediagnosis of Parkinson Disease Using Artificial Neural Networks and Support Vector Machines

Full Text (PDF, 426KB), PP.41-47

Views: 0 Downloads: 0

Author(s)

Saloni 1,* R. K. Sharma 1 Anil K. Gupta 1

1. Department of Electronics and Communication Engineering, National Institute of Technology, Kurukshetra, India

* Corresponding author.

DOI: https://doi.org/10.5815/ijisa.2015.06.04

Received: 22 Jun. 2014 / Revised: 2 Nov. 2014 / Accepted: 14 Jan. 2015 / Published: 8 May 2015

Index Terms

Parkinson Disease, Voice Analysis, Feature Selection, Feature Classifier

Abstract

Parkinson is a neurological disease and occurs due to lack of dopamine neurons. These dopamine neurons manage all body movements. Parkinson patients have difficulty in doing all daily routine activities, and also have disturbed vocal fold movements. Using voice analysis disease can be diagnosed remotely at an early stage with more reliability and in an economic way. In this paper, we have used 23 features dataset, all the features are analyzed and 15 features are selected from the total dataset. As in Parkinson tremor is present in the voice box muscles, so the variation in the period and amplitude of consecutive vocal cycles is present. The feature dataset selected consist of jitter, shimmer, harmonic to noise ratio, DFA, spread1 and PPE. Various classifiers are used and their comparison is done to find out which classifier is perfect in this environment. It is concluded that support vector classifiers as the best one with an accuracy of 96%. In the neural network classifiers with different transfer functions, there is tradeoff among the performance parameters.

Cite This Paper

Saloni, R. K. Sharma, Anil K. Gupta, "Voice Analysis for Telediagnosis of Parkinson Disease Using Artificial Neural Networks and Support Vector Machines", International Journal of Intelligent Systems and Applications(IJISA), vol.7, no.6, pp.41-47, 2015. DOI:10.5815/ijisa.2015.06.04

Reference

[1]A. David Gill and B. Magnus Johnson, “Diagnosing Parkinson by using Artficial Neural Network and Support Vector Machines,” Global Journal of Computer Science and technology, vol. 9, pp. 63-71, 2009.

[2]F. S. Gharehchopogh and P. Mohammadi, “A Case Study of Parkinson Disease using Artificial Neural Network, vol. 73, 2013, pp.1-6.

[3]C.O. sakar and O. Kursun, “Telediagnosis of Parkinson’s Disease Using Measurements of Dysophonia, J Med Syst, Vol 34, 2010, pp. 591-599.

[4]A. Khemphila and V. Boonjing, “Parkinson Disease Classification Using Neural Network and Feature Selection” WASET, Vol 6, 2012, pp.15-18.

[5]H. K. Rouzbahani and M. R. Daliri, “Diagnosis of Parkinson’s Disease in Human using Voice Signals,” Neuroscience, Vol 2, pp 12-19, 2011.

[6]U. Rani and M. S. Holi, “Analysis of speech characteristics of neurological disease and their classification” Computing Communication & Networking Technologies (ICCCNT), pp.1-6, 2012.

[7]I. Rustempasic and M. Can, “Diagnosis of parkinson’s disease using fuzzy C-means clustering and pattern recognition” Southeast Europe Journal of Soft Computing, pp.42-49, 2013.

[8]M. Shahbakhi, D. T. Far and E. Tahami, “ Speech Analysis for Diagnosis of Parkinson’s Disease Using Genetic Algorithm and Support Vector Machine,” J. Biomedical Science and Engineering, vol. 7, pp. 147-156, 2014.

[9]R. A. Shirvan and E. Tahami, “Voice Analysis for Detecting Parkiinson’s Disease using Genetic Algorithm and KNN Classification Method”IEEE, 2011,pp 278-283. M. Shahbakhi, D. T.Far, “Linear and Non-linear speech Features for Detection of Parkinson’s Disease” BMEiCON,2013.

[10]M. Shahbakhi, D. T.Far, “Linear and Non-linear speech Features for Detection of Parkinson’s Disease” BMEiCON,2013.

[11]H. L. Chen, C. C. Huang, X. G. Yu, X. Xu, X. Sun,G. Wang, S. J. Wang, “An Efficient diagnosis system for detection of Parki nson’s disease using fuzzy K- nearest neighbor approach” Expert System With Application,40, pp-263-271, 2013.

[12]A. Tsanas, Max A. Little, P. E. Macsharry, “Novel Speech Signal Processing Algorithm for High-Accuracy Classification of Parkinson’s Disease, IEEE Transaction on biomedical engg,Vol. 59,2012, pp 1264-1271.

[13]Max A. Little, P. E. Macsharry, E. J. Hunter, J.Sielman, L. O. Raming, “Suitability Of Dysophonia Measurements for Telemonitoring of Parkinson’s Disease, IEEE Transaction on biomedical engg,Vol. 56,2009, pp 1015-1022.

[14]D. Reby, S. Lek, I.Dimopoulos, J. Joachim, J. Lauga, S. Aulagnier, “ Artficial neural networks as a classification method in behavioural sciences” Behavioural Processes, 40, 1997,pp 35-43.

[15]Saloni, R.K. Sharma and A.K. Gupta, “ Disease detection using voice analysis: a review” International Journal of Medical Engineering and Informatics (IJMEI), Vol. 6, No. 3, 2014, pp 189-210.

[16]Saloni, R.K. Sharma and A.K. Gupta, “ Classification of High Blood Pressure Persons VsNormal Blood Pressure Persons Using Voice Analysis” I.J. Image, Graphics and Signal Processing, 2014, 1, 47-52.