Research of Parkinson's Disease Diagnosis Based on Improved PSO-SVM Algorithm
ZHANG Qiong
DING Weiping
JING Wei
YU Liguo
Abstract：The doctors easily give wrong judgments because of the etiology of Parkinson's disease unclear and diverse clinical manifestations. In this paper,a support vector machines algorithm based on improved particle swarm optimization(IMPSO-SVM)is proposed to improve the accuracy of recognition of Parkinson's disease. This algorithm assigns inertia weights and learning factors to different properties of particles to optimize the penalty coefficients and kernel functions of support vector machines. Finally,the pro?posed IMPSO-SVM algorithm is applied to the clinical data of Parkinson's disease. The experimental result shows that this algorithm has improved the prediction accuracy and the execution efficiency,compared with the support vector machine optimized by the tradi?tional particle swarm optimization(PSO-SVM)and the support vector machine optimized by genetic algorithm(GA-SVM). There?fore,this algorithm can be used as an effective method for assisting doctors to diagnose Parkinson's disease.
Keywords：improved particle swarm optimizationsupport vector machinesinertia weightlearning factor
Publication Date：2019-01-01
Online Publishing Date：2025-08-15(First online date of this platform, not the publication date of the document)
Pages：5( 1851-1855 )