Combination of PSO Algorithm and Naive Bayesian Classification for Parkinson Disease Diagnosis

Abstract

Parkinson is a neurological disease which quickly affects human’s motor organs. Early diagnosis of this disease is very important for its prevention. Using optimum training data and omitting noisy training data will increase the classification accuracy. In this paper, a new model based on the combination of PSO algorithm and Naive Bayesian Classification has been presented for diagnosing the Parkinson disease, in which optimum training data are selected by PSO algorithm and Naive Bayesian Classification. In this paper, according to the obtained results, Parkinson disease diagnosis accuracy has been 97.95% using the presented method, which is indicative of the superiority of this method to the previous models of Parkinson disease diagnosis.