Linear and non-linear speech features for detection of Parkinson´s disease

Author

Shahbakhti, M. ; Taherifar, Danial ; Sorouri, Atefeh

Author_Institution

Dept. of Biomed. Eng., Islamic Azad Univ., Dezful, Iran

fYear

2013

fDate

23-25 Oct. 2013

Firstpage

1

Lastpage

3

Abstract

Parkinson´s disease (PD) was described by James Parkinson first time and it is now recognized as the second common neurological disorder after Alzheimer. Since most of the people with PD suffer form speech disorder, it is believed that speech analysis can be considered as the easiest way for PD detection. In this research, we try to use extracted features by genetic algorithm and ANFC for classifying between healthy and people with PD. Support vector machines (SVM) is applied as the classifier. Results show higher network accuracy of ANFC features compared to genetic algorithm features.

Keywords

diseases; feature extraction; genetic algorithms; medical computing; medical disorders; neurophysiology; patient diagnosis; speech; speech processing; support vector machines; ANFC feature extraction; Alzheimer disease; James Parkinson; Parkinson disease detection; genetic algorithm features; neurological disorder; nonlinear speech features; speech disorder analysis; support vector machines; Accuracy; Feature extraction; Frequency measurement; Genetic algorithms; Kernel; Parkinson´s disease; Support vector machines; ANFC; Genetic algorithms; Parkinson´s disease; SVM; Speech analysis;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Engineering International Conference (BMEiCON), 2013 6th

Conference_Location

Amphur Muang

Print_ISBN

978-1-4799-1466-1

Type

conf

DOI

10.1109/BMEiCon.2013.6687667

Filename

6687667