Parkinson’s Disease Diagnosis with Gait Characteristics Extracted Using Wavelet Transforms

The objective of this study is to propose a methodology for early detection of Parkinson's disease based on gait patterns. A set of novel features are developed based on self-similar, correlation, and compressibility properties extracted by multiscale features of gait data in the wavelet domain. The dataset used in this study is available in the physionet repository. This study considers only the VGRF data collected from subjects while walking at their normal pace for 2 minutes on a flat surface.