COMPUTATIONAL RESEARCH PROGRESS IN APPLIED SCIENCE &ENGINEERING (CRPASE) CRPASE: TRANSACTIONS OF ELECTRICAL, ELECTRONIC AND COMPUTER ENGINEERING Journal homepage: http://www.crpase.com CRPASE: Transactions of Electrical, Electronic and Computer Engineering, Vol. 06(03), 141-145, September 2020 ISSN 2423-4591 Research Article Parkinson’s Disease Detection Based on Signal Processing Algorithms and Machine Learning Atiqur Rahman 1 , Aurangzeb Khan 1 , Arsalan Ali Raza 2 1 Department of Computer Science, University of Sciences & Technology Bannu, Paksitan 2 Kohat University of Science and Technology (KUST), Kohat, Pakistan Keywords Abstract Parkinson’s disease, Feature Extraction, Machine Learning, Voice Data, Tele diagnosis, Tele-monitoring. There is more interest in the speech model applications for analysis of Parkinson’s diseases to predictively construct tele diagnosis and telemonitoring models. This motivated us to use a relatively large database of voice samples having different types of vowel phonations, compiled from a series of verbal trials for people suffering from Parkinson's disease. Two main problems are observed in learning from a dataset of this type that contains multiple discourse registration by subject: a) How to foresee such different kinds vowel samples in the diagnosis of Parkinson's disease (PD)? b) How aptly the main inclination and dispersal the metrics can be used as representatives of all example recordings of a subject? This article examines the multiple types of vowel samples collected from PD patients and healthy subjects and utlize state-of-the-art signal processing algorithms like Perceptual Linear Prediction (PLP) and ReAlitive SpecTrAl PLP (RASTA-PLP) for feature extraction purposes. The extracted set of features are classified using SVM model with four different types of kernels. Results show that our algorithm performs 74% accurately. 1. Introduction Parkinson's disease (PD) is a nervous system disease that yields some or total damage of speech, conduct, intellectual and other roles of the body [1]. It is generally observed in the elderly and causes motor and speech impairments [3]. PD comes the second biggest neurological healthiness problem in the elderly people and it is projected that around ten- million individuals all over the world are perturbed by this disease [4], [5]. In particular, PD is usually found in one person out of one hundred people over 60 years old. At present, PD is incurable [6], [7]. Though, there are some drugs to reduce its effects. PD is typically detected and treated with intrusive methods [8]. Hence, it complexes the diagnosis and treatment of bereaved patients of the disease. In this study, the use of subject speech data should assist in the development of a non-invasive diagnosis. There are important examples of this type of studies on Alzheimer's  Corresponding Author: Atiqur Rahman E-mail address: atiqrehman37@gmail.com Received: 12 July 2020; Revised: 10 August 2020; Accepted: 12 August 2020 Please cite this article as: A. Rahman, A. Khan, A. A.Raza, Parkinson’s disease Detection Based on Signal Processing Algorithms and Machine Learning, Computational Research Progress in Applied Science & Engineering, CRPASE: Transactions of Electrical, Electronic and Computer Engineering 6 (2020) 141–145. disease and PD around the world. PM-based studies focus on symptoms like slow movement, weak balance, tremors or toughness of certain parts of the body [9] - [12] but mainly voice problems. The chief cause for the acceptance of the diagnosis of PD speech disorders is that remote diagnosis and remote monitoring systems using voice signals are inexpensive and easy self-use [7], [13]. Thus, such a system not only reduces the disadvantages and the cost of the physical appointments of the patients to the medical clinic, but also allow timely detection of the disease and in addition to the reduction in the load of medical staff [7], [13] - [15]. People with parkinsonism (PWP) also have speech disorders such as dysphonia (faulty voice), hypophonia (low volume), monotonous (low tonal amplitude) and dysarthria (problem with joint sounds or syllables). In spite of the presence of a lot of studies to diagnose and monitor PD based on these deficiencies. these studies rely on basic diagnostics of the voice. the troubles. Speech disorders can be scaled simply by