|
 |
Bimonthly Since 1986 |
ISSN 1004-9037
|
|
 |
|
|
Publication Details |
Edited by: Editorial Board of Journal of Data Acquisition and Processing
P.O. Box 2704, Beijing 100190, P.R. China
Sponsored by: Institute of Computing Technology, CAS & China Computer Federation
Undertaken by: Institute of Computing Technology, CAS
Published by: SCIENCE PRESS, BEIJING, CHINA
Distributed by:
China: All Local Post Offices
|
|
|
|
|
|
|
|
|
|
|
09 May 2023, Volume 38 Issue 3
|
|
|
Abstract
Neurodegenerative disease patients have been increasing in number over the years. Parkinson’s is one of these diseases that has a severe impact on the patient’s life. There is no specific test to detect this disease but to do various tests based on which the patient is then diagnosed. Handwriting of a Parkinson's patient is different from that of a normal patient and this could be used to detect the disease. There have been many attempts to detect Parkinson's disease using various datasets and different approaches. Deep learning has been the most popular approach that has been used extensively. Deep learning models being a “black-box” give accurate predictions but with no justification as to why the prediction has been made. Machine learning models that achieve the same results as the deep learning models will be beneficial in giving justifications for the predictions of the models. This work uses a few popular machine learning algorithms that are known to be explainable such as Logistic Regression, Support Vector Machines, Decision Trees, Random Forest and Naive Bayes Classifier to reach the same level of accuracy as those of deep learning models.
Keyword
Logistic Regression, Support Vector Machines, Decision Trees, Random Forest, Naive Bayes Classifier, Machine Learning, Neurodegenerative Disease, Parkinson’s Disease.
PDF Download (click here)
|
|
|
|
|