diagnosis of parkinson's disease via support vector machine optimized by optimal particle swarm algorithm

Parkinson's disease (pd) is one of the most common diseases in the world and it is crucial to identify in the early stages of the disease. if the reliable diagnosis is available, the patient can be treated at the right time. therefore, artificial intelligent algorithms play an important role in the early proper treatment of the disease. in this study, parkinson's disease is detected by support vector machine and dimension of data is reduced using particle swarm optimization algorithm. the data are the voice recordings of patients consist of 22 features. the proposed method diagnoses pd with 97% accuracy when the number of features is reduced to 7 attributes. comparing the method with other state of the art studies shows the superiority of proposed method