Comparison Study of Different Classifiers for Detecting Parkinson Disease using Machine Learning Language
In Parkinson's disease, dopamine-producing neurons in the brain are disrupted. Communication between brain cells is enabled by it. Dopamine is responsible for the control, adaption and easiness of movements. This disease occurs mainly in aged persons, but in this current scenario Parkinson’s disease symptoms showing after age 35. So researchers try to find more ways to recognize the symptoms of Parkinson’s disease as early as possible. The purpose of this paper is to present different classifiers that use machine learning to diagnose Parkinson's disease. Here I use 3 different classifiers-SVM, KNN and XGBoost. I will build a model for all 3 classifiers and calculate their accuracy of detecting the Parkinson’s disease by giving the same dataset input. From the 3 classifiers I select the more accuracy one. This paper propose select the XGBoost classifiers to detect the Parkinson’s disease person. XGBoost gives 94.7.
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.