Parkinson’s Disease Detection Using Machine Learning

IEEE BASE PAPER ABSTRACT:

Firstly, Parkinson delineates Parkinson’s sickness as a neurologic syndrome, it affects the central system, as a result, the patients face difficulty talking, strolling, tremor throughout the motion. Parkinson’s sickness patient generally encompasses a low-volume noise with a monotone quality, this method explores the classification of audio signals feature dataset to diagnose Parkinson’s sickness (PD), the classifiers we tend to use during this system area unit from Machine Learning. Our model tends to utilize provision regression and XGboost classifiers, and therefore the audio feature dataset from the UCI dataset repository. The system has achieved a much better end up in predicting the palladium patient is healthy or not, XGBoost provided the height accuracy of 96% and therefore the Matthews parametric statistic (MCC) of 89%.

OUR PROPOSED ABSTRACT:

Parkinson’s disease is a neurodegenerative disorder that affects millions of people worldwide. Parkinson’s disease (PD) affects 60% of persons over age 50. The patients of Parkinson’s disease struggle with speech impairment and movement issues, which makes it difficult for them to travel for appointments for treatment and monitoring. Early discovery of PD enables treatment, allowing patients to live normal lives.

The necessity to identify PD early, remotely, and correctly is highlighted by the world’s ageing population. In recent years, machine learning techniques have shown great potential in the early detection and diagnosis of Parkinson’s disease. In this project, we propose a novel approach for the detection of Parkinson’s disease using machine learning techniques and Xception architecture.

Specifically, we focus on the detection of Parkinson’s disease from spiral and wave drawings, which are commonly used in clinical practice as part of the diagnosis process. We collected a dataset of spiral and wave drawings from individuals with and without Parkinson’s disease. We preprocessed the data and used Xception architecture to train our machine learning models.

Our models achieved impressive performance, with a training accuracy of 95.34% and a validation accuracy of 93.00% for the detection of Parkinson’s disease from spiral drawings, and a training accuracy of 93.34% and a validation accuracy of 86.00% for the detection of Parkinson’s disease from wave drawings.

Our results demonstrate the potential of machine learning and Xception architecture in the early detection and diagnosis of Parkinson’s disease. Our approach has the potential to improve the accuracy and efficiency of Parkinson’s disease diagnosis, leading to better patient outcomes and quality of life.

PROJECT OUTPUT VIDEO:

ALGORITHM / MODEL USED:

Xception Architecture.

SYSTEM REQUIREMENTS:

HARDWARE REQUIREMENTS:

System : Pentium i3 Processor.
Hard Disk : 500 GB.
Monitor : 15’’ LED
Input Devices : Keyboard, Mouse
Ram : 4 GB

SOFTWARE REQUIREMENTS:

Operating System : Windows 10 / 11.
Coding Language : Python 3.8.
Web Framework : Flask.
Frontend : HTML, CSS, JavaScript.

REFERENCE:

M.S. Roobini, Yaragundla Rajesh Kumar Reddy, Udayagiri Sushmanth Girish Royal, Amandeep Singh K, Babu.K, “Parkinson’s Disease Detection Using Machine Learning”, 2022 International Conference on Communication, Computing and Internet of Things (IC3IoT), IEEE Conference, 2022.

Python IEEE Projects

Parkinson’s Disease Detection Using Machine Learning