Cover Image

A new hybrid intelligent system for accurate detection of Parkinson's disease

Link to publisher's homepage at http://www.elsevier.com

Saved in:
Bibliographic Details
Main Authors: Hariharan, Muthusamy, Kemal, Polat, Sindhu, Ravindran
Other Authors: hari@unimap.edu.my
Format: Article
Language:English
Published: Elsevier 2014
Subjects:
Parkinson's disease
Dysphonia features
Feature weighting
Feature selection
Classification
Online Access:http://dspace.unimap.edu.my:80/dspace/handle/123456789/32775
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.unimap-32775
record_format dspace
spelling my.unimap-327752014-03-15T04:12:42Z A new hybrid intelligent system for accurate detection of Parkinson's disease Hariharan, Muthusamy Kemal, Polat Sindhu, Ravindran hari@unimap.edu.my Parkinson's disease Dysphonia features Feature weighting Feature selection Classification Link to publisher's homepage at http://www.elsevier.com Elderly people are commonly affected by Parkinson's disease (PD) which is one of the most common neurodegenerative disorders due to the loss of dopamine-producing brain cells. People with PD's (PWP) may have difficulty in walking, talking or completing other simple tasks. Variety of medications is available to treat PD. Recently, researchers have found that voice signals recorded from the PWP is becoming a useful tool to differentiate them from healthy controls. Several dysphonia features, feature reduction/selection techniques and classification algorithms were proposed by researchers in the literature to detect PD. In this paper, hybrid intelligent system is proposed which includes feature pre-processing using Model-based clustering (Gaussian mixture model), feature reduction/selection using principal component analysis (PCA), linear discriminant analysis (LDA), sequential forward selection (SFS) and sequential backward selection (SBS), and classification using three supervised classifiers such as least-square support vector machine (LS-SVM), probabilistic neural network (PNN) and general regression neural network (GRNN). PD dataset was used from University of California-Irvine (UCI) machine learning database. The strength of the proposed method has been evaluated through several performance measures. The experimental results show that the combination of feature pre-processing, feature reduction/selection methods and classification gives a maximum classification accuracy of 100% for the Parkinson's dataset. 2014-03-15T04:04:38Z 2014-03-15T04:04:38Z 2014-03 Article Computer Methods and Programs in Biomedicine, vol.113 (3) , 2014, pages 904-913 0169-2607 http://dspace.unimap.edu.my:80/dspace/handle/123456789/32775 http://www.cmpbjournal.com/article/S0169-2607%2814%2900005-4/fulltext en Elsevier
institution Universiti Malaysia Perlis
building UniMAP Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Malaysia Perlis
content_source UniMAP Library Digital Repository
url_provider http://dspace.unimap.edu.my/
language English
topic Parkinson's disease
Dysphonia features
Feature weighting
Feature selection
Classification
spellingShingle Parkinson's disease
Dysphonia features
Feature weighting
Feature selection
Classification
Hariharan, Muthusamy
Kemal, Polat
Sindhu, Ravindran
A new hybrid intelligent system for accurate detection of Parkinson's disease
description Link to publisher's homepage at http://www.elsevier.com
author2 hari@unimap.edu.my
author_facet hari@unimap.edu.my
Hariharan, Muthusamy
Kemal, Polat
Sindhu, Ravindran
format Article
author Hariharan, Muthusamy
Kemal, Polat
Sindhu, Ravindran
author_sort Hariharan, Muthusamy
title A new hybrid intelligent system for accurate detection of Parkinson's disease
title_short A new hybrid intelligent system for accurate detection of Parkinson's disease
title_full A new hybrid intelligent system for accurate detection of Parkinson's disease
title_fullStr A new hybrid intelligent system for accurate detection of Parkinson's disease
title_full_unstemmed A new hybrid intelligent system for accurate detection of Parkinson's disease
title_sort new hybrid intelligent system for accurate detection of parkinson's disease
publisher Elsevier
publishDate 2014
url http://dspace.unimap.edu.my:80/dspace/handle/123456789/32775
_version_ 1643796981549629440
score 13.222552

Similar Items