Online pattern recognition of lower limb movements based on sEMG signals and its application in real-time rehabilitation training

• Published in: Robotica Vol. 42; no. 2; pp. 389 - 414
• Main Authors: Ye, Ye, Zhu, Ming-xia, Ou, Chang-wei, Wang, Bing-zhu, Wang, Lu, Xie, Neng-gang
• Format: Journal Article
• Language: English
• Published: Cambridge, UK Cambridge University Press 01.02.2024
• Subjects: Accuracy; Algorithms; Artificial neural networks; Classifiers; Comparative analysis; Control equipment; Customization; Decomposition; Dynamical systems; Electrodes; Electromyography; Intelligence in Robotics; K-nearest neighbors algorithm; Machine learning; Motion perception; Muscle contraction; Nonlinear dynamics; Particle swarm optimization; Patients; Pattern recognition; Principal components analysis; Real time; Rehabilitation; Rehabilitation robots; Robot dynamics; Support vector machines; rehabilitation training; online pattern recognition; optimization of feature channel; surface electromyography signals
• ISSN: 0263-5747; 1469-8668
• DOI: 10.1017/S0263574723001509

An online pattern recognition method of lower limb movements is proposed based on the personalized surface electromyography (sEMG) signals, and the corresponding experimental researches are performed in the rehabilitation training. Further, a wireless wearable acquisition instrument is used. Based on this instrument, a host computer for the personal online recognition and real-time control of rehabilitation training is developed. Three time-domain features and two features in the nonlinear dynamics are selected as the joint set of the characteristic values for the sEMG signals. Then a particle swarm optimization (PSO) algorithm is used to optimize the feature channels, and a k-nearest neighbor (KNN) algorithm and the extreme learning machine (ELM) algorithm are combined to classify and recognize individual sample data. Based on the multi-pose lower limb rehabilitation robot, the real-time motion recognition and the corresponding rehabilitation training are carried out by using the online personalized classifier. The experimental results of eight subjects indicate that it takes only 6 min to build an online personalized classifier for the four types of the lower limb movements. The recognition between switches of different rehabilitation training movements is timely and accurate, with an average recognition accuracy of more than 95%. These results demonstrate that this system has a strong practicability.