While most wearable gesture recognition approaches focus on the forearm or fingers, the wrist may a more suitable location for practical use. We present the design and validation of a real-time gesture recognition wristband based on surface electromyography (sEMG) and inertial measurement unit (IMU) sensing fusion, which can recognize 8 air gestures and 4 surface gestures with 2 distinct force levels. Ten healthy subjects performed an initial gesture recognition experiment, followed by a second experiment 1 hour later and a third experiment 1 day later. Classification accuracies for the initial experiment were 92.6% and 88.8% for air and surface gestures, respectively, and there were no changes in accuracy results during testing 1 hour and 1 day later (p>0.05). These results demonstrate the feasibility of wrist-based gesture recognition paving the way for potential future integration in to a smart watch or other wrist-worn wearable for intuitive human computer interaction.

Objective. Recent studies have reported that the classification performance of electromyographic (EMG) signals degrades over time without proper classification retraining. This problem is relevant for the applications of EMG pattern recognition in the control of active prostheses. Approach. In this study we investigated the changes in EMG classification performance over 11 consecutive days in eight able-bodied subjects and two amputees. Main results. It was observed that, when the classifier was trained on data from one day and tested on data from the following day, the classification error decreased exponentially but plateaued after four days for able-bodied subjects and six to nine days for amputees. The between-day performance became gradually closer to the corresponding within-day performance. Significance. These results indicate that the relative changes in EMG signal features over time become progressively smaller when the number of days during which the subjects perform the pre-defined motions are increased. The performance of the motor tasks is thus more consistent over time, resulting in more repeatable EMG patterns, even if the subjects do not have any external feedback on their performance. The learning curves for both able-bodied subjects and subjects with limb deficiencies could be modeled as an exponential function. These results provide important insights into the user adaptation characteristics during practical long-term myoelectric control applications, with implications for the design of an adaptive pattern recognition system.

Advanced myoelectric prosthetic hands are currently limited due to the lack of sufficient signal sources on amputation residual muscles and inadequate real-time control performance. This paper presents a novel human-machine interface for prosthetic manipulation that combines the advantages of surface electromyography (EMG) and near-infrared spectroscopy (NIRS) to overcome the limitations of myoelectric control. Experiments including 13 able-bodied and three amputee subjects were carried out to evaluate both offline classification accuracy (CA) and online performance of the forearm motion recognition system based on three types of sensors (EMG-only, NIRS-only, and hybrid EMG-NIRS). The experimental results showed that both the offline CA and realtime performance for controlling a virtual prosthetic hand were significantly (p <; 0.05) improved by combining EMG and NIRS. These findings suggest that fusion of EMG and NIRS is feasible to improve the control of upper-limb prostheses, without increasing the number of sensor nodes or complexity of signal processing. The outcomes of this study have great potential to promote the development of dexterous prosthetic hands for transradial amputees.

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.