Gait Anomaly Detection of Subjects With Parkinson’s Disease Using a Deep Time Series-Based Approach

Parkinson’s disease (PD) is a cognitive degenerative disorder of the central nervous system that mainly affects the motor system. The earliest symptoms evidence a general deficit of coordination and an unsteady gait. Current approaches for the evaluation and assessment of gait disturbances in PD have proved to be expensive, inconvenient and ineffective in the detection of anomalous walking patterns. In this paper, we address these issues by defining a deep time series-based approach for the detection of anomalous walking patterns in the gait dynamics of elderly people by analyzing the acceleration values of their movements. The results show a training accuracy and testing accuracy of over 90% with an accuracy improvement of 4.28% in comparison with related works.