This study presents a progressive FastICA peel-off (PFP) framework for high-density surface electromyogram (EMG) decomposition. The novel framework is based on a shift-invariant model for describing surface EMG. The decomposition process can be viewed as progressively expanding the set of motor unit spike trains, which is primarily based on FastICA. To overcome the local convergence of FastICA, a peel-off strategy, i.e., removal of the estimated motor unit action potential trains from the previous step, is used to mitigate the effects of the already identified motor units, so more motor units can be extracted. A constrained FastICA is applied to assess the extracted spike trains and correct possible erroneous or missed spikes. These procedures work together to improve decomposition performance. The proposed framework was validated using simulated surface EMG signals with different motor unit numbers (30, 70, 91) and SNRs (20, 10, and 0 dB). The results demonstrated relatively large numbers of extracted motor units and high accuracies (high F1-scores). The framework was tested with 111 trials of 64-channel electrode array experimental surface EMG signals during the first dorsal interosseous muscle contraction at different intensities. On average 14.1 ±5.0 motor units were identified from each trial of experimental surface EMG signals.

Recent advances in high-density surface electromyogram (EMG) decomposition have made it a feasible task to discriminate single motor unit activity from surface EMG interference patterns, thus providing a noninvasive approach for examination of motor unit control properties. In the current study, we applied high-density surface EMG recording and decomposition techniques to assess motor unit firing behavior alterations poststroke. Surface EMG signals were collected using a 64-channel 2-D electrode array from the paretic and contralateral first dorsal interosseous (FDI) muscles of nine hemiparetic stroke subjects at different isometric discrete contraction levels between 2 to 10 N with a 2 N increment step. Motor unit firing rates were extracted through decomposition of the high-density surface EMG signals and compared between paretic and contralateral muscles. Across the nine tested subjects, paretic FDI muscles showed decreased motor unit firing rates compared with contralateral muscles at different contraction levels. Regression analysis indicated a linear relation between the mean motor unit firing rate and the muscle contraction level for both paretic and contralateral muscles (p <; 0.001), with the former demonstrating a lower increment rate (0.32 pulses per second (pps)/N) compared with the latter (0.67 pps/N). The coefficient of variation (averaged over the contraction levels) of the motor unit firing rates for the paretic muscles (0.21 ± 0.012) was significantly higher than for the contralateral muscles (0.17 ± 0.014) (p <; 0.05). This study provides direct evidence of motor unit firing behavior alterations poststroke using surface EMG, which can be an important factor contributing to hemiparetic muscle weakness.

Objective: Myoelectric pattern recognition has been successfully applied as a human-machine interface to control robotic devices such as prostheses and exoskeletons, significantly improving the dexterity of myoelectric control. This study investigates the feasibility of applying myoelectric pattern recognition for controlling a robotic hand in stroke patients. Methods: Myoelectric pattern recognition of six hand motion patterns was performed using forearm electromyogram (EMG) signals in paretic side of 8 stroke subjects. Both the random cross validation (RCV) and the chronological handout validation (CHV) were applied to assess the offline myoelectric pattern recognition performance. Experiments on real-time myoelectric pattern recognition control of an exoskeleton robotic hand were also performed. Results: An average classification accuracy of 84.1% (the mean value from two different classifiers) and individual subject differences were observed in the offline myoelectric pattern recognition analysis using the RCV, while the accuracy decreased to 65.7% when the CHV was used. The stroke subjects achieved an average accuracy of 61.3-20.9% for controlling the robotic hand. However, our study did not reveal a clear correlation between the real-time control accuracy and the offline myoelectric pattern recognition performance, or any specific characteristics of the stroke subjects. Conclusion: The findings suggest that it is feasible to apply myoelectric pattern recognition to control the robotic hand in some but not all of the stroke patients. Each stroke subject should be individually online tested for the feasibility of applying myoelectric pattern recognition control for robot-assisted rehabilitation.

To develop multi-functionalhuman-machine interfaces that can help disabled people reconstruct lost functions of upper-limbs, machine learning (ML) and deep learning (DL) techniques have been widely implemented to decode human movement intentions from surface electromyography (sEMG) signals. However, due to the high complexity of upper-limb movements and the inherent non-stable characteristics of sEMG, the usability of ML/DL based control schemes is still greatly limited in practical scenarios. To this end, tremendous efforts have been made to improve model robustness, adaptation, and reliability. In this article, we provide a systematic review on recent achievements, mainly from three categories: multi-modal sensing fusion to gain additional information of the user, transfer learning (TL) methods to eliminate domain shift impacts on estimation models, and post-processing approaches to obtain more reliable outcomes. Special attention is given to fusion strategies, deep TL frameworks, and confidence estimation. Research challenges and emerging opportunities, with respect to hardware development, public resources, and decoding strategies, are also analysed to provide perspectives for future developments

This study presents automatic decomposition of high density surface electromyogram (EMG) signals through a progressive FastICA peel-off (PFP) framework. By incorporating FastICA, constrained FastICA and a peel-off strategy, the PFP can progressively expand the set of motor unit spike trains contributing to the EMG signal. A series of signal processing techniques were applied and integrated in this study to automatically implement the two tasks that often require human operator interaction during application of the PFP framework, including extraction of motor unit spike trains from FastICA outputs and reliability judgement of the extracted motor units. Based on these advances, an automatic PFP (APFP) framework was consequently developed. The decomposition performance of APFP was validated using simulated high density surface EMG signals. The APFP was also evaluated with experimental surface EMG signals, and the decomposition results were comparable to those achieved from the PFP with human operator interaction.

Myoelectric pattern recognition with a large number of electromyogram (EMG) channels provides an approach to assessing motor control information available from the recorded muscles. In order to develop a practical myoelectric control system, a feature dependent channel reduction method was developed in this study to determine a small number of EMG channels for myoelectric pattern recognition analysis. The method selects appropriate raw EMG features for classification of different movements, using the minimum Redundancy Maximum Relevance (mRMR) and the Markov random field (MRF) methods to rank a large number of EMG features, respectively. A k-nearest neighbor (KNN) classifier was used to evaluate the performance of the selected features in terms of classification accuracy. The method was tested using 57 channels' surface EMG signals recorded from forearm and hand muscles of individuals with incomplete spinal cord injury (SCI). Our results demonstrate that appropriate selection of a small number of raw EMG features from different recording channels resulted in similar high classification accuracies as achieved by using all the EMG channels or features. Compared with the conventional sequential forward selection (SFS) method, the feature dependent method does not require repeated classifier implementation. It can effectively reduce redundant information not only cross different channels, but also cross different features in the same channel. Such hybrid feature-channel selection from a large number of EMG recording channels can reduce computational cost for implementation of a myoelectric pattern recognition based control system.