Abstract
Gait phase recognition can improve the control of lower limb exoskeleton robot and promote human-machine collaboration. One of the current mainstream methods is to use electromyogram (EMG) to recognize gait phase, but the EMG signal has shortcomings such as weak signal, difficult to wear, easy to be affected by noise and sweat. Therefore, we designed a novel air-pressure mechanomyograph (PMMG) sensor, and further made a wearable PMMG-based sensing system composed of PMMG-based thighrings and inertial measurement units (IMUs). In order to improve the performance of gait phase recognition, we used five popular machine learning algorithms to fuse the data from PMMG-based thighrings and IMUs. We recruited three experimental subjects and constructed two datasets for different walking conditions: constant speed walking and variable speed walking. Experimental results show that the proposed PMMG sensor is effective, and the gait phase recognition accuracy reached 96.25% by using only the PMMG-based thighrings. In addition, we found that the performance of multi-modal sensor fusion is better than that of single-modal sensor fusion through three comparative experiments. Among the five machine learning algorithms, the SVM fusion model got the highest average accuracy of 98.82%.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call