Freezing of Gaits Detection for Parkinson's Disease Patients Using Fast Time-Frequency Analysis Methods and Onset Detection

Parkinson's disease (PD) patients often suffer from the freezing of gait (FOG) problem, which interferes their daily life. In this paper, we develop an algorithm which uses fast time-frequency analysis methods and onset detection to detect FOG in real time. Simulations show that the specificity, the sensitivity, and the accuracy of the proposed algorithm is 81.83%, 82.66%, and 82.83%, respectively, which are better than existing FOG detection algorithms. Furthermore, since the asymmetric and shorter response smooth filter is applied, the time latency of the proposed algorithm is only 0.95 second, which is less than other methods. Our algorithm can help PD patients overcome the difficulty of walking and is easier to be implemented in hardware.