Classification of Parkinson's disease by using voice dataset

Name: Warisara Asawaponwiput

LCSH: Kasetsart University -- Theses. M.Eng. (Information and Communication Technology for Embedded Systems) 2021

Classification :.LCCS: QA76.87

LCSH: Kasetsart University. -- Department of Electrical Engineering -- Theses

LCSH: Neural networks (Computer science)

LCSH: Parkinson's disease

LCSH: Medicine -- Data processing

LCSH: Data sets

Abstract: Parkinson’s disease (PD) is a long-term neurodegenerative disease of the central nervous system. While most experts agree that the risk factors for PD include heredity and environmental factors, the cause of the disease is currently unknown. The current diagnosis is dependent on clinical observation and the abilities and experience of a trained specialist. One of the symptoms that affect most patients over the course of their illness is voice impairment. Voice is a non-invasive biomarker that can be collected remotely for diagnosis and disease progression monitoring. Therefore, in this study, the objective is to classify the PD based on audio analysis from one of the largest mobile PD datasets, the mPower study. The dataset of 29,798 audio clips from 4,051 participants was used in this study. The audio sample was converted to a spectrogram using a short-time Fourier transform to extract the time and frequency of the signal. Three of the most popular modern convolutional neural network models were then applied as classifiers. The classification performance of LeNet-5, ResNet-50, and VGGNet-16 are 97.7 ± 0.1%, 98.6 ± 0.2%, and 99.3 ± 0.1%, respectively. These accurate results on a large number of participants suggest that vocal analysis could be a promising non-invasive and remotely available biomarker for PD diagnosis.

Kasetsart University. Office of the University Library

Address: Bangkok

Email: tdckulib@ku.ac.th

Name: Denchai Worasawate

Role: Thesis Advisor

Name: Apichart Intarapanich

Role: Thesis CO-Advisor

Name: Natsue Yoshimura

Role: Thesis CO-Advisor

Created: 2021

Modified: 2025-07-17

Issued: 2025-07-17

วิทยานิพนธ์/Thesis

application/pdf

URL: https://www.lib.ku.ac.th/KUthesis/2564/warisara-asa-all.pdf

CallNumber: QA76.87 .W39

eng

DegreeName: Master of Engineering

Level: Master's Degree

Descipline: Information and Communication Technology for Embedded System

Grantor: Kasetsart University

©copyrights Kasetsart University

ลำดับที่.	ชื่อแฟ้มข้อมูล	ขนาดแฟ้มข้อมูล	จำนวนเข้าถึง	วัน-เวลาเข้าถึงล่าสุด
1	warisara-asa-all.pdf	3.84 MB

ใช้เวลา

0.021236 วินาที