Expert System for Diagnosing Parkinson Disease Using Two Stage Feature Selection Algorithms

Parkinson’s syndrome is a common issue with mass calculation in public health. Machine-based technology issued to distinguish between those with healthy dementia and those with Parkinson’s disease. In this paper a two stage feature selection is applied for selecting the best features. In the first stage, correlation feature selection is applied and in the second stage, the selected features are then given to Particle Swarm Optimization and Ant Colony Optimization technique for feature selection. Then the selected features are used by KNN, RF, NB, SVM and MLP classifiers.