Linear and non-linear speech features for detection of Parkinson's disease

Parkinson's disease (PD) was described by James Parkinson first time and it is now recognized as the second common neurological disorder after Alzheimer. Since most of the people with PD suffer form speech disorder, it is believed that speech analysis can be considered as the easiest way for PD detection. In this research, we try to use extracted features by genetic algorithm and ANFC for classifying between healthy and people with PD. Support vector machines (SVM) is applied as the classifier. Results show higher network accuracy of ANFC features compared to genetic algorithm features.