An Intelligent Computing Based Approach for Parkinson Disease Detection

In this work various machine learning techniques such as support vector machine (SVM), nearest neighbor (k-NN), artificial neural network (ANN) has been used for detection of Parkinson disease. Input features are collected from the handwriting of various normal and Parkinson persons. The inputs and their corresponding targets are given to machine learning based methods. A comparative study of SVM, k-NN and ANN has been carried out. Accuracy of the proposed method is found to be 100% for all the tested data. Hence machine learning based methods can be put to use in real time scenario.