Automatic detection of Parkinson’s disease based on Hybrid Binary Grey Wolf Optimizer and K Nearest Neighbor algorithms

Parkinson s disease (PD) is one of the common neurodegenerative disorder around the world. This paper propose intelligent tools to detect early signs of Parkinson’s disease (PD) through free-speech. A Hybrid approach of machine learning algorithms is introduced for identifying important feature and diagnosing of Parkinson’s disease that a state-of-the-art hybrid algorithm Binary Grey Wolf Optimizer and weighted K-nearest neighbor has been implemented for feature selection. The performance of the proposed method is evaluated on Parkinson’s disease dataset of UCI. Binary Grey Wolf Optimizer identify 10 feature and weighted K nearest neighbor classified 98.5% accuracy. The experimental results exhibition that hybridization of optimization algorithm and machine learning for feature selection help to improving the performance of classification.