Ankle foot motion recognition based on wireless wearable sEMG and acceleration sensors for smart AFO

• Published in: Sensors and actuators. A. Physical. Vol. 331; p. 113025
• Main Authors: Zhou, Congcong, Yang, Lilin, Liao, Heng, Liang, Bo, Ye, Xuesong
• Format: Journal Article
• Language: English
• Published: Lausanne Elsevier B.V 01.11.2021; Elsevier BV
• Subjects: Acceleration; Algorithms; Ankle foot; Artificial neural networks; Classification; Data fusion; Data integration; Human motion; Motion perception; Motion recognition; Multisensor fusion; Neural networks; Principal components analysis; Recognition; Sensors; Smart sensors; Studies; Support vector machines; Three axis; Wearable computers; Wireless signal acquisition system (WAS); Wireless signal acquisition system (WAS); Data fusion; Motion recognition; Ankle foot
• DOI: 10.1016/j.sna.2021.113025
• ISSN: 0924-4247

[Display omitted] •A wireless signal acquisition system (WAS) was designed specifically, high precision sEMG signal and three-axis ACC data were acquired simultaneously.•TKEO based signal preprocessing algorithm was proposed to detect the onset of the raw data.•Features from sEMG and ACC data of four kinds of typical motions including dorsiflexion, plantar flexion, eversion and inversion were studied properly.•DT,NB, SVM, ANN and BiLSTM models were proposed, the accuracy results and confusion matrix of typical motion mode were discussed.•The input referred noise of sEMG module in WAS(1 μV) was lower than many other systems, and the classification accuracy of BiLSTM reached 99.8 %. Ankle joint is one of the important anatomical structures of the human body, smart ankle-foot orthosis(AFO) can assist human walking and improve the ankle motion for patients. This study focused on ankle foot movements recognition based on data fusion via sEMG and acceleration sensors. A wireless signal acquisition system (WAS) was designed specifically, forming a platform to demonstrate and record individual sEMG and acceleration data simultaneously. In the experimental tests, three channel sEMG signals from Tibialis Anterior (TA), Gastrocnemius (GM) and Soleus (SO), as well as three-axis acceleration data of the ankle joints, were collected when subjects performed four kinds of typical motions including dorsiflexion, plantar flexion, eversion and inversion. A total of 21,600 frames of sEMG /acceleration action data were constructed and then different kinds of classification algorithms were studied to classify the motions by the principal component analysis (PCA) based data fusion signal features. Results showed that the classification accuracy of bi-directional long short-term memory (BiLSTM) algorithm performed the best compared with traditional networks such as support vector machine(SVM), artificial neural network (ANN) and reached 99.8 %. These results demonstrated the potential application for accurate ankle foot intent identification by sEMG and acceleration sensors, which provided the basis for further implementation of subsequent smart AFO manipulation.