Skip to main content Skip to main navigation menu Skip to site footer
Bulletin of Abai KazNPU. Series of Physical and mathematical sciences

DETECTION OF PARKINSON'S DISEASE PATIENTS BASED ON VOICE RECORDING USING CONVOLUTION NEURAL NETWORK

Published June 2023

159

75

Karabuk University, Karabuk
##plugins.generic.jatsParser.article.authorBio##
×

S.M. Hashim

She is Phd Student in the Department of Computer Engineering at Karabuk University.

Karabuk University, Karabuk
##plugins.generic.jatsParser.article.authorBio##
×

H. Kutucu

Hakan Kutucu  received one of his master degree from International Computer Institute in 2004 from Department of Mathematics at Ege University in 2008. He completed doctoral programme of Department of Mathematics at Ege University in 2011. At the present time, he has focused on network design problems, machine learning, combinatorial optimization and mathematical modeling. He has been working in the Department of Software Engineering at Karabuk University as an Associate Professor since 2020.

Atyrau State University, Atyrau
##plugins.generic.jatsParser.article.authorBio##
×

B. Assanova

Asanova Baktygul Ungarsinovna was born on September 13, 1981 in the village of Taisoygan, Kyzylkoginsky district, Guryev region. From 1987 to 1998 he studied at the G. Slanov Secondary School. In 1998, he entered the Faculty of Mechanics and Mathematics of the Al-Farabi Kazakh National University with a degree in applied mathematics, from which he graduated in 2002. In 2002, he entered this university for a master's degree and in 2004 graduated with a qualification and an academic master's degree in applied mathematics and computer science 510250. In 2004, he joined the Atyrau State University named after H. Dosmukhamedov. Since 2004 – Lecturer (2006-2011), Senior Lecturer (2011-2017) of the Department of Mathematical Analysis of the Faculty of Physics, Mathematics and Information Technologies of Atyrau State University named after H.Dosmukhamedov. 2008-2014 Deputy Dean for Educational Work and Educational Work of the Dean of the Faculty of Physics, Mathematics and Information Technology, 2014-2016 Dean of the Preparatory Faculty, 2016-2017 He worked as a senior lecturer at the Department of Software Engineering.2017-2020 Graduated from the Eurasian National University in Astana, Faculty of Information Technology, specialty 6D070300-Information Systems, and in 2020 successfully defended his doctoral dissertation and received a PhD in information systems. About 30 scientific articles have been published. Since 2021 he has been working as the dean of the faculty.

Atyrau State University, Atyrau
##plugins.generic.jatsParser.article.authorBio##
×

N. Shazhdekeyeva

At Atyrau State University named after H. Dosmukhamedov, he works as a senior lecturer at the Department of Mathematical Analysis, since 2011 head of the Department of Mathematics and Methods of Teaching Mathematics. In 2010, a PhD thesis was defended at the Al-Farabi Kazakh National University in Almaty on the topic "further improvement of the habit of restoring filtration capacity indicators in effective layers". More than 50 scientific and methodological articles have been published in scientific journals of the Republic and abroad, 8 scientific papers in international scientific journals with an impact factor. The owner of 5 textbooks, 1 monograph in English, 3 copyright certificates. For significant achievements in the education and upbringing of the younger generation, he was awarded the badge "S.Altynsarin" (2010). In 2016 he received the title of "Best teacher" of the university. According to the Erasmus + program, he completed an internship in 2015 at Voronezh State University (Russia), in 2018 at the University of Poitiers (France). The family has 3 children, 2 grandchildren.

Atyrau State University, Atyrau
##plugins.generic.jatsParser.article.authorBio##
×

A Taishiyeva

In 2005, she graduated from the Gagarin Secondary School of the Beineu district and entered the Faculty of Physics, Mathematics and Information Technologies of the Atyrau State University named after H. Dosmukhamedov, majoring in mathematics. In 2009 he graduated from the University with honors, from 2009 to 2011 he studied for a master's degree in mathematics, from 2018 to 2022 - for a doctoral degree in Mathematical and Computer Modeling at the L. Gumilev Eurasian National University.
From 2009 to 2012, a mathematics teacher at the A. Kunanbayev secondary school in Atyrau, from 2012 to 2018, a teacher of the Department of Mathematics and Methods of Teaching Mathematics at the Atyrau State University named after H. Dosmukhamedov, in the 2020-2021 academic year, a mathematics teacher at secondary school No. 40 in Atyrau, in the 2022-2023 academic year at the school -M. Shokaya Gymnasium in Astana worked as a mathematics teacher.

Abstract

Parkinson's disease is a commonly observed neurological disorder that affects the nervous system and hinders, people's essential functions. The primary goal of this study is to identify the presence of Parkinson's disease by utilizing spectrogram images from voice recordings through the implementation of Convolutional Neural Networks (CNN). We conducted our research using a dataset from the Argentina. Our research made a significant contribution by performing various audio preprocessing operations. We split the audio samples into multiple segments of the same duration (2 seconds) and then implement audio augmentation techniques to increase the dataset. Finally, we converted these audio samples into spectrogram images to train our model. K-fold cross-validation method was used, set by (k=10) for further analysis. The model underwent 150 epochs of training, resulting in an Average Training Accuracy of 99.3% and an Average Testing Accuracy of 97.9%. The effectiveness of the proposed model is compared with five state-of-art models (AlexNet, VGG16, Inception V3, ResNet50, SqueezeNet) and the local binary pattern descriptors which were applied to the same dataset. As a result, the proposed model was found to be superior.

pdf
Language

English

How to Cite

[1]
Hashim, S., Kutucu, H., Assanova, B., Shazhdekeyeva, N. and Taishiyeva, A. 2023. DETECTION OF PARKINSON’S DISEASE PATIENTS BASED ON VOICE RECORDING USING CONVOLUTION NEURAL NETWORK. Bulletin of Abai KazNPU. Series of Physical and mathematical sciences. 82, 2 (Jun. 2023), 202–211. DOI:https://doi.org/10.51889/2959-5894.2023.82.2.022.