Cover Image

Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]

Parkinson's disease (PI)) is the second commonest late life neurodegenerative disease after Alzheimer's disease. It is prevalent throughout the world and predominantly affects patients above 60 years old. It is caused by progressive degeneration of dopamine containing cells (neurons) withi...

Full description

Saved in:
Bibliographic Details
Main Authors: Abu Bakar, Zahari, Ibrahim, Nur Farahiah, Ispawi, Dzufi Iszura, Md. Tahir, Nooritawati
Format: Thesis
Language:English
Published: 2012
Subjects:
RZ Other systems of medicine
Online Access:http://ir.uitm.edu.my/id/eprint/41423/1/41423.pdf
http://ir.uitm.edu.my/id/eprint/41423/
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.uitm.ir.41423
record_format eprints
spelling my.uitm.ir.414232021-02-11T07:41:18Z http://ir.uitm.edu.my/id/eprint/41423/ Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.] Abu Bakar, Zahari Ibrahim, Nur Farahiah Ispawi, Dzufi Iszura Md. Tahir, Nooritawati RZ Other systems of medicine Parkinson's disease (PI)) is the second commonest late life neurodegenerative disease after Alzheimer's disease. It is prevalent throughout the world and predominantly affects patients above 60 years old. It is caused by progressive degeneration of dopamine containing cells (neurons) within the deep structures of the brain called the basal ganglia and substantia nigra. Therefore, accurate prediction of PD need to be done in order to assist medical or bio-informatics practitioners for initial diagnose of PD based on variety of test results. This paper described the analysis conducted based on two training algorithms namely Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) of Multilayer Perceptrons (MLPs) Neural Network in diagnosing PD with Analysis of Variance (ANOVA) as a feature selection. The dataset information of this project has been taken from the Parkinson Disease Data Set. Results attained confirmed that the LM performed well with accuracy rate of above 90% before and after feature selection whilst SSG attained above 85% subsequent to implementation of ANOVA as feature selection. 2012-12 Thesis NonPeerReviewed text en http://ir.uitm.edu.my/id/eprint/41423/1/41423.pdf Abu Bakar, Zahari and Ibrahim, Nur Farahiah and Ispawi, Dzufi Iszura and Md. Tahir, Nooritawati (2012) Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]. Masters thesis, Universiti Teknologi MARA, Cawangan Sarawak.
institution Universiti Teknologi Mara
building Tun Abdul Razak Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Mara
content_source UiTM Institutional Repository
url_provider http://ir.uitm.edu.my/
language English
topic RZ Other systems of medicine
spellingShingle RZ Other systems of medicine
Abu Bakar, Zahari
Ibrahim, Nur Farahiah
Ispawi, Dzufi Iszura
Md. Tahir, Nooritawati
Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]
description Parkinson's disease (PI)) is the second commonest late life neurodegenerative disease after Alzheimer's disease. It is prevalent throughout the world and predominantly affects patients above 60 years old. It is caused by progressive degeneration of dopamine containing cells (neurons) within the deep structures of the brain called the basal ganglia and substantia nigra. Therefore, accurate prediction of PD need to be done in order to assist medical or bio-informatics practitioners for initial diagnose of PD based on variety of test results. This paper described the analysis conducted based on two training algorithms namely Levenberg-Marquardt (LM) and Scaled Conjugate Gradient (SCG) of Multilayer Perceptrons (MLPs) Neural Network in diagnosing PD with Analysis of Variance (ANOVA) as a feature selection. The dataset information of this project has been taken from the Parkinson Disease Data Set. Results attained confirmed that the LM performed well with accuracy rate of above 90% before and after feature selection whilst SSG attained above 85% subsequent to implementation of ANOVA as feature selection.
format Thesis
author Abu Bakar, Zahari
Ibrahim, Nur Farahiah
Ispawi, Dzufi Iszura
Md. Tahir, Nooritawati
author_facet Abu Bakar, Zahari
Ibrahim, Nur Farahiah
Ispawi, Dzufi Iszura
Md. Tahir, Nooritawati
author_sort Abu Bakar, Zahari
title Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]
title_short Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]
title_full Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]
title_fullStr Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]
title_full_unstemmed Classification of Parkinson's Disease (PD) Based on Multilayer Perception (MLPs) Neural Network and Anova as a feature extraction / Zahari Abu Bakar ... [et al.]
title_sort classification of parkinson's disease (pd) based on multilayer perception (mlps) neural network and anova as a feature extraction / zahari abu bakar ... [et al.]
publishDate 2012
url http://ir.uitm.edu.my/id/eprint/41423/1/41423.pdf
http://ir.uitm.edu.my/id/eprint/41423/
_version_ 1691735795985022976
score 13.211869

Similar Items