Objective. Estimation of the discharge pattern of motor units by electromyography (EMG) decomposition has been applied for neurophysiologic investigations, clinical diagnosis, and human-machine interfacing. However, most of the methods for EMG decomposition are currently applied offline. Here, we propose an approach for high-density surface EMG decomposition in real-time. Methods. A real-time decomposition scheme including two sessions, offline training and online decomposition, is proposed based on the convolutional kernel compensation algorithm. The estimation parameters, separation vectors and the thresholds for spike extraction, are first computed during offline training, and then they are directly applied to estimate motor unit spike trains (MUSTs) during the online decomposition. The estimation parameters are updated with the identification of new discharges to adapt to non-stationary conditions. The decomposition accuracy was validated on simulated EMG signals by convolving synthetic MUSTs with motor unit action potentials (MUAPs). Moreover, the accuracy of the online decomposition was assessed from experimental signals recorded from forearm muscles using a signal-based performance metrics (pulse-to-noise ratio, PNR). Main results. The proposed algorithm yielded a high decomposition accuracy and robustness to non-stationary conditions. The accuracy of MUSTs identified from simulated EMG signals was > 80% for most conditions. From experimental EMG signals, on average, 12±2 MUSTs were identified from each electrode grid with PNR of 25.0±1.8 dB, corresponding to an estimated decomposition accuracy > 75%. Conclusion and Significance. These results indicate the feasibility of real-time identification of motor unit activities non-invasively during variable force contractions, extending the potential applications of high-density EMG as a neural interface.

Objective. Surface electromyography (EMG) decomposition techniques can be used to establish human-machine interfacing (HMI), but most investigations are implemented offline due to the computational load of the approach. Here, we generalize the offline decomposition algorithm to identify the motor unit (MU) activities in real time, and we propose a MU-based approach for online simultaneous and proportional control (SPC) of multiple motor tasks. Approach. High-density surface EMG signals recorded from forearm muscles were decomposed into motor unit spike trains (MUSTs) with the proposed decomposition method. The MUSTs were first pooled into clusters in the calibration phase and the cumulative discharges of active MUs in each group were extracted as the control signal for each motor task. Then the subjects were instructed to control a virtual cursor with multiple motor tasks involving grasp and wrist movements. Fifteen able-bodied subjects and two patients with limb deficiency participated in the experiments to validate the proposed control scheme. Main results. On average, over 20 MUSTs were identified in real time with an estimated decomposition accuracy > 85%. The cumulative discharge in each pool was highly correlated with the activation of the specific motion ( R = 0.93 ± 0.05). Moreover, the proposed MU-based method had superior performance in online tests than conventional myo-control methods based on global EMG features. Significance. These results indicate the feasibility of real-time neural decoding in a non-invasive way. Moreover, the superior performance in online tests proves the potential of the MU-based approach for the SPC, promoting the application of EMG decomposition for HMI systems.

Objective . The aim of the study was to characterize the accuracy in the identification of motor unit discharges during natural movements using high-density electromyography (EMG) signals and to investigate their correlation with finger kinematics. Approach . High-density EMG signals of forearm muscles and finger joint angles were recorded concurrently during hand movements of ten able-bodied subjects. EMG signals were decomposed into motor unit spike trains (MUSTs) with a blind-source separation method. The first principle component (FPC) of the low-pass filtered MUST was correlated with finger joint angles. Main results . On average, motor units were identified during each individual finger task with an estimated decomposition accuracy 85%. The FPC extracted from discharge rates was strongly associated to the joint angles ( ), and preceded the joint angles on average by ms. Moreover, the FPC outperformed two time-domain features (the EMG envelop and the root mean square of EMG) in estimating joint angles. Significance . These results indicated the possibility of identifying individual motor unit behavior in dynamic natural contractions. Moreover, the strong association between motor unit discharge behaviors and kinematics proves the potential of the approach for the simultaneous and proportional control of prostheses.

Objective. Surface electromyography (EMG) decomposition techniques have been developed to decode motor neuron activities non-invasively in the past decades, showing superior performance in human-machine interfaces such as gesture recognition and proportional control. However, neural decoding across multiple motor tasks and in real-time remains challenging, which limits its wide application. In this work, we proposed a real-time hand gesture recognition method by decoding motor unit (MU) discharges across multiple motor tasks ( $>$ 10) in a motion-wise way. Methods. The EMG signals were first divided into numerous segments related to motions. The convolution kernel compensation algorithm was applied for each segment individually. The local MU filters, which indicate the MU-EMG correlation for each motion, were calculated iteratively in each segment and reused for global EMG decomposition to trace the MU discharges across motor tasks in real-time. The motion-wise decomposition method was applied on the high-density EMG signals recorded during twelve hand gesture tasks from eleven non-disabled participants. The neural feature of discharge count was extracted for gesture recognition based on five common classifiers. Main results. On average, 164 $\pm$ 34 MUs were identified for twelve motions from each subject, with a pulse-to-noise ratio of 32.1 $\pm$ 5.6 dB. The average time cost of EMG decomposition in a sliding window of 50 ms was less than 5 ms. The average classification accuracy using a linear discriminant analysis classifier was 94.6 $\pm$ 8.1%, which was significantly higher than that of a time-domain feature called root mean square. The superiority of the proposed method was also validated with a previously published EMG database comprising 65 gestures. Conclusion and Significance. These results indicate the feasibility and superiority of the proposed method for MU identification and hand gesture recognition across multiple motor tasks, extending the potential applications of neural decoding in human-machine interfaces.

Simultaneous and proportional control (SPC) using surface electromyography (sEMG) signals has become a prevailing solution for the intuitive control of prosthesis and human–robot interaction. However, only time and frequency domain features are generally involved in conventional SPC algorithms, ignoring the globally spatial information across channels. In this article, we presented an instantaneous sEMG-image-based model for continuous estimation on multiple degrees of freedom wrist torques. Specifically, a convolutional neural network was used to extract features from sEMG-images, and then to estimate wrist torques. The results demonstrated that the sEMG-image-based model outperformed three conventional regression methods and a deep-learning-based method with superior performance on estimation accuracy and smoothness. Furthermore, we found a strong linear correlation between the first two principal components of extracted features and the recorded wrist torques, validating the effectiveness of the proposed approach. The outcomes open up a new perspective for SPC and potentially enhance the performance of myoelectric control in practical application.