Parkinson’s Disease Detection Using Wavelet Packet Absolute Amplitude Deviation (WPAAD) from voice signals

Parkinson’s disease (PD) is a neurodegenerative condition that causes several motor and non-motor defects in human body. As speech is a motor activity, its production affected due to PD progression. It has been studied that PD can be detected by looking at changes in speech signals over time. In this paper an effective feature based on the wavelet packet absolute amplitude deviation (WPAAD) is proposed to classify PD from healthy subjects. To assess the performance of this approach, vowel phonations from PC-GITA database are used. The highest average accuracy of 88% is achieved in the vowel /a/. The results suggest that the proposed approach can be used for automatic detection of PD in practical scenarios.