Abstract:
This research project focuses on the application of machine learning techniques to detect Parkinson's disease (PD) based on the kinematic features of hand movements. Hand motions of 16 PD patients (N16) and 16 individuals from the control group (N16) were recorded using Leap Motion sensors. Three motor tasks were selected based on MDS-UPDRS part 3: finger tapping (FT), pronation-supination of the hand (PS), and opening-closing hand movements (OC). Key points were derived from the sensor signal, and 25 kinematic features were extracted. Key point determination was achieved through a custom user application using the maximums and minimums finding algorithm as well as manual marking. Different feature extraction methods were employed for binary classification (PD or non-PD), both for each motor task individually and their combined features. Four classifiers, namely kNN, SVM, Decision Tree (DT), and Random Forest (RF), were trained and tested using an 8-fold cross-validation approach. The combination of the most significant features from both hands yielded the best results. Overall, the motor task outcome showed excellent performance for the selected features.
This final year project is based on an IEEE Paper and is considered one of the best projects for computer science students. As the best IEEE project center, maker, and seller in Bangalore, we provide complete documentation support, fully implemented hardware/software in the students' environment, and offer classes tailored to the project's requirements. By incorporating these keywords, we aim to enhance your website's SEO.