PARKINSON’S DISEASE DIAGNOSIS BASED ON THE CONVOLUTIONAL NEURAL NETWORK AND PARTICLE SWARM OPTIMIZATION ALGORITHM
HAWA ALRAWAYATI *
Department of Mathematics, Faculty of Science and Arts, Kastamonu University, 37100, Kastamonu, Turkey.
ÜMIT TÖKEŞER
Department of Mathematics, Faculty of Science and Arts, Kastamonu University, 37100, Kastamonu, Turkey.
*Author to whom correspondence should be addressed.
Abstract
Parkinson's disease affects both men and women. Parkinson's infection is a cerebrum issue that prompts shaking, solidness, and trouble with strolling, equilibrium, and coordination. The disease is diagnosed around the age of 65 and only 15% are diagnosed under the age of 50. In this study, the Parkinson’s Disease analyzed and detected based on the Convolutional Neural Network and Particle Swarm Optimization Algorithm. The Particle Swarm Optimization method is used to reduce the number of features and also the best features are selected. For evaluation the result two methods like Mean Square Error and Root Mean Square Error are used. The detection rate was 0.32 and 95.77 for Mean Square Error and Root Mean Square Error respectively.
Keywords: Parkinson's disease, geographical boundaries, swarm optimization, Convolutional Neural Network