This research focuses on applying machine learning techniques to identify Parkinson's disease (PD) from the kinematic features of hand movements. Leap Motion sensors were used to record the hand motions of 16 PD patients (N16) and 16 members of the control group (N16). On the basis of MDS-UPDRS part 3, the following three motor tasks were selected: finger tapping (FT), pronation-supination of the hand (PS), and opening-closing hand movements (OC). 25 kinematic characteristics for the signal from the sensor were derived using key points. Utilizing a specifically created user application, the key point determination was done using the maximums and minimums finding algorithm as well as manual marking. Different feature extraction methods were employed for the binary classification (PD or non-PD), for each motor task separately and for the three combined. The following four classifiers were trained: kNN, SVM, Decision Tree (DT), and Random Forest (RF). In the 8-fold cross-validation mode, testing was done. The combination of the most important traits of both hands produced the best results. . The overall motor task resultwill be good for features. final year project is based on IEEE Paper.this will be one of the best Final year engineering project for computer science. Components that we will provide are.
1.complete documentation support
2.complete working hardware/software implemented in students environment
3.classes will held accordingly.