A Low-Cost End-to-End sEMG-Based Gait Sub-Phase Recognition System

• Published in: IEEE transactions on neural systems and rehabilitation engineering Vol. 28; no. 1; pp. 267 - 276
• Main Authors: Luo, Ruiming, Sun, Shouqian, Zhang, Xianfu, Tang, Zhichuan, Wang, Weide
• Format: Journal Article
• Language: English
• Published: United States IEEE 01.01.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Classification; Electromyography; Force; Gait; Gait recognition; Hardware; Human motion; Human performance; Long short-term memory; Low cost; LSTM; Motion perception; Multilayer perceptrons; Muscles; Neural networks; Plantar pressure; Real-time systems; Recognition; sEMG; Short term; Signal classification; Terrain; Thigh; Walking
• ISSN: 1534-4320; 1558-0210; 1558-0210
• DOI: 10.1109/TNSRE.2019.2950096

As surface electromyogram (sEMG) signals have the ability to detect human movement intention, they are commonly used to be control inputs. However, gait sub-phase classification typically requires monotonous manual labeling process, and commercial sEMG acquisition devices are quite bulky and expensive, thus current sEMG-based gait sub-phase recognition systems are complex and have poor portability. This study presents a low-cost but effective end-to-end sEMG-based gait sub-phase recognition system, which contains a wireless multi-channel signal acquisition device simultaneously collecting sEMG of thigh muscles and plantar pressure signals, and a novel neural network-based sEMG signal classifier combining long-short term memory (LSTM) with multilayer perceptron (MLP). We evaluated the system with subjects walking under five conditions: flat terrain at 5 km/h, flat terrain at 3 km/h, 20 kg backpack at 5 km/h, 20 kg shoulder bag at 5 km/h and 15° slope at 5 km/h. Experimental results show that the proposed method achieved average classification accuracies of 94.10%, 87.25%, 90.71%, 94.02%, and 87.87%, respectively, which were significantly higher than existing recognition methods. Additionally, the proposed system had a good real-time performance with low average inference time in the range of 3.25 ~ 3.31 ms.