Dopamine Analysis Using Multiple Machine Learning Techniques

  • G.Prema Arokia Mary, K.Saru Priya, N.Suganthi, S.Sathyavathi

Abstract

Compelling assessment of potential neuroprotective intercessions for Parkinson's disease (PD) requires exact measurement of the engine signs related with this disease. Parkinsonism is the second most regular neurodegenerative issue. It incorporates a few pathologies with comparative indications, what makes the determination extremely troublesome. Parkinson detection framework has been actualized utilizing single machine learning algorithm in the past methodology. The degree of exactness was very low utilizing help vector machine. The low-level detection leaded to more demise rate. Parkinson disease is an anxious issue that influences a great many individuals around the world. The vast majority of the cases go undetected because of lack of standard detection techniques. The point of this examination is to think about and recognize this disease utilizing information mining and machine learning algorithms like decision tree, logistic regression and K-nearest neighbor are actualized in the brain dataset.

Keywords: Decision Tree, Logistic Regression, Knn, PD, DBS, comparison Accuracy

Published
2020-06-07
How to Cite
G.Prema Arokia Mary, K.Saru Priya, N.Suganthi, S.Sathyavathi. (2020). Dopamine Analysis Using Multiple Machine Learning Techniques. International Journal of Advanced Science and Technology, 29(05), 10220 - 10227. Retrieved from https://sersc.org/journals/index.php/IJAST/article/view/21281