Paper Title
Parkinson Disease Classification Using Modified Grey Wolf Optimization Algorithm

Abstract
This paper presents a Modified Grey Wolf Optimization (MGWO) Algorithm for the early detection of Parkinson’s Disease. Parkinson’s is a disorder of the central nervous system caused by the death of brain cells. Parkinson’s disease is incurable and may eventually result in death, but medications can help control symptoms and extend the patient’s life to a certain extent if detected on time. In this work, MGWO is used as an algorithm to generate weights for an ensemble model comprising 5 base classifiers - XGBoost, Decision Tree, Random Forest, K-Nearest Neighbor (KNN), and Support Vector Machine (SVM). A publicly available voice dataset is used to provide data for our study. The model is evaluated on measures like Accuracy, precision, recall, and F1-score. Our proposed model gave an accuracy of 98.3%. The experimental results show that the model is efficient in the detection of Parkinson’s disease. Keywords - Parkinson Disease, Modified Grey Wolf Opti- mization, Ensemble Learning, Weighted Majority Voting, Ma- chine learning