Combination of PCA and SVM for diagnosis of Parkinson´s disease

Parkinson´s disease (PD) is a neurodegenerative brain disorder that occurs when approximately 60% to 80% of the dopamine-producing cells are damaged. PD is the second common neurodegenerative disorder after Alzheimer. PD could be diagnosed by various signals such as EEG, gait and speech. Approximately, 90 percent of people with PD suffer from speech disorder, thus it might be considered as the easiest way to this aim. This paper investigates a new method for detection of Parkinson form speech signals at which PCA combines extracted features form the data and the classification is done using SVM network. The classification accuracy percent of 91.5 per 3 optimized features is obtained.