Transcutaneous nerve stimulation (TNS) has the potential to restore sensory feedback in upper-limb prosthetic users. However, its effectiveness is limited by habituation, which is a reduction in the perceived stimulation intensity with prolonged use. This study investigated TNS parameter optimization to maintain consistent sensation, focusing on median and ulnar nerve stimulation through a high-density 2 × 5 electrode grid positioned on the upper arm. Through a systematic evaluation of six experimental conditions varying in block duration, rest intervals, and stimulation patterns, we identified optimal stimulation parameters that significantly reduced habituation while maintaining robust sensory feedback. The most effective protocol demonstrated 37.87% higher sensitivity than the standard protocol while maintaining a low decay rate (0.09 $\pm$ 0.02). During the main protocol, force output stabilized after the initial adaptation and remained significantly above baseline (p $< $ 0.0001). Notably, we observed nerve-specific responses to stimulation parameters, with the median nerve showing significantly heightened sensitivity to parameter variations compared with the ulnar nerve (p = 0.0267). These findings offer a promising approach for maintaining stable sensory feedback in neuroprosthetic applications, with the potential to improve user experience and device adoption. The identified stimulation condition, which features 1-minute blocks and strategic rest intervals, lays the groundwork for more effective TNS-based sensory feedback systems in clinical applications.

Accurate decoding of human motion intention from surface electromyography (sEMG) signals recorded non-invasively from the skin surface is critical for enabling intuitive control in assistive robotics and human–machine interactions. With the advancement of high-density sEMG (HD-sEMG), neural decoding methods based on motor unit (MU) activity have shown promise due to their potential to capture finely controlled movement information. However, the effects of data segmentation parameters on the decomposition and decoding accuracy remain underexplored. In this study, we systematically investigated how the segmentation length and data size of sEMG signals used for decomposition affect the performance of finger force decoding. Specifically, HD-sEMG signals were recorded from eight human participants during single- and multi-finger isometric force tasks. A neural decoding pipeline was developed for finger force predictions. We first evaluated the impact of four segmentation window lengths (10 s, 20 s, 40 s, and 80 s) on decoding accuracy, and found that a 20-second window was sufficient to ensure accurate decoding, with no additional benefit from using longer segments. Using this setting, we further examined the effect of training data size by comparing decoders trained with different data sizes. Our results showed that using the full training dataset significantly improved decoding performance compared to using only half of the training dataset. These findings offer practical guidelines for optimizing data usage in MU-based motion intention decoding systems.

Finger force monitoring has become increasingly prevalent in the field of the Internet of Medical Things (IoMT) as a key indicator of muscle strength and health status, facilitating remote rehabilitation and personalized health monitoring. However, existing methods are limited by inaccurate decoding performance or complex procedures when derived in a supervised manner. To address these challenges, we developed a novel unsupervised approach featuring a robust and lightweight neural-drive decoder for multifinger force predictions. High-density surface electromyogram (sEMG) signals were recorded from the finger extensor muscles during isometric finger extension tasks. Each MU was then assigned a probability indicating its association with the target finger, based on its mean firing rates during the activation periods of individual fingers. MUs with probabilities exceeding a predefined threshold were retained for the final force prediction. Our results demonstrate that the neural-drive decoder achieved a computation time of$68.83\pm 13.63$ms, making it suitable for real-time applications. Furthermore, our decoder outperformed the sEMG-amplitude-based approach ($R^{2}$:$0.79\pm 0.039$versus$0.64\pm 0.080$, root mean-square error (RMSE):$4.89\pm 0.73$versus$7.31\pm 1.88$% of maximum force, Pearson correlation coefficient (PCC):$0.87\pm 0.028$versus$0.76\pm 0.06$, and mean absolute error (MAE):$3.86\pm 0.62$versus$6.08\pm 1.51$% of maximum force). The developed neural decoder demonstrated advantages over the state-of-the-art neural decoders in terms of accuracy, training procedures, and practicality. Additionally, our approach exhibited robust performance across various probability thresholds, data sources, and background noise, highlighting its potential for finger force monitoring applications in diverse IoMT scenarios.

Neural or muscular injuries, such as due to amputation, spinal cord injury, and stroke, can affect hand functions, profoundly impacting independent living. This has motivated the advancement of cutting-edge assistive robotic hands. However, unintuitive myoelectric control of these devices remains challenging, which limits the clinical translation of these devices. Accordingly, we developed a robust motor-intent decoding approach to continuously predict the intended fingertip forces of single and multiple fingers in real time. We used population motor neuron discharge activities (i.e., neural drive from brain to spinal cord) decoded from a high-density surface electromyogram (HD-sEMG) signals as the control signals instead of the conventional global sEMG features. To enable real-time neural-drive prediction, we employed a convolutional neural network model to establish the mapping from global HD-sEMG features to finger-specific neural-drive signals, which were then employed for continuous and real-time control of three prosthetic fingers (index, middle, and ring). As a result, the neural-drive-based approach can decode the motor intent of single-finger and multifinger forces with significantly lower force estimation errors than that obtained using the global HD-sEMG-amplitude approach. Besides, the force prediction accuracy was consistent over time and demonstrated strong robustness to signal interference. Our network-based decoder can also achieve better finger isolation with minimal forces predicted in unintended fingers. Our work demonstrates that the accurate and robust finger force control could be achieved through this new decoding approach. The outcomes offer an efficient intent prediction approach that allows users to have intuitive control of prosthetic fingertip forces in a dexterous way.

Accurate control over individual fingers of robotic hands is essential for the progression of human-robot interactions. Accurate prediction of finger forces becomes imperative in this context. The state-of-the-art neural decoders can extract neural signals from surface electromyogram (sEMG) signals. However, these decoders require labeled data for decoder training, which is challenging to obtain in cases such as limb loss and limits decoder generalizability. In our study, we extracted motoneuron firing information by decomposing high-density sEMG signals from both finger flexor and extensor muscles. We assigned each neuron a probability, reflecting its association with the targeted fingers, based on its temporal firing rate distribution. We then employed a probability thresholding and weighting strategy to select and prioritize neurons for finger force predictions. Our results revealed that the unsupervised neural decoder significantly outperformed both the supervised neural decoder and sEMG-amplitude approaches (: 0.74 ± 0.028 vs. 0.70 ± 0.028 vs. 0.63 ± 0.031, root mean square error: 6.74 ± 0.60% vs. 8.41 ± 0.56% vs. 10.33 ± 0.59% of maximum force), thereby offering a promising and practical solution for accurate force controls. Our results also demonstrated high computational efficiency (96.26 ± 24.16 ms), viable for real-time implementations. The outcomes offer an unsupervised decoder with simplified data requirements for decoder training. The decoder boasts enhanced functionality and adaptability in predicting finger flexion and extension forces. In addition, our approach holds promise for broader applications in scenarios where force measurement proves challenging.

Existing electromyographic (EMG) based motor intent detection algorithms are typically user-specific, and a generic model that can quickly adapt to new users is highly desirable. However, establishing such a model remains a challenge due to high inter-person variability and external interference with EMG signals. In this study, we present a feature disentanglement approach, implemented by an autoencoder-like architecture, designed to decompose user-invariant, motor-task-sensitive high-level representations from user-sensitive, task-irrelevant representations in EMG amplitude features. Our method is usergeneric and can be applied to unseen users for continuous multi-finger force predictions. We evaluated our approach on eight subjects, predicting the force of three fingers (index, middle, and ring-pinky) concurrently. We assessed the decoder's performance through a rigorous leave-onesubject-out validation. Our developed approach consistently outperformed both the conventional EMG amplitude method and a commonly used feature projection approach, principal component analysis (PCA), with a lower force prediction error (RMSE: 6.91 ± 0.45% MVC; R 2 : 0.835 ± 0.026) and a higher finger classification accuracy (83.0 ± 4.5%). The comparison with the state-of-the-art neural networks further demonstrated the superior performance of our method in user-generic force predictions. Overall, our methods provide novel insights into the development of user-generic and accurate neural decoding for myoelectric control of assistive robotic hands.

A reliable neural-machine interface is essential for humans to intuitively interact with advanced robotic hands in an unconstrained environment. Existing neural decoding approaches utilize either discrete hand gesture-based pattern recognition or continuous force decoding with one finger at a time. We developed a neural decoding technique that allowed continuous and concurrent prediction of forces of different fingers based on spinal motoneuron firing information. High-density skin-surface electromyogram (HD-EMG) signals of finger extensor muscle were recorded, while human participants produced isometric flexion forces in a dexterous manner (i.e. produced varying forces using either a single finger or multiple fingers concurrently). Motoneuron firing information was extracted from the EMG signals using a blind source separation technique, and each identified neuron was further classified to be associated with a given finger. The forces of individual fingers were then predicted concurrently by utilizing the corresponding motoneuron pool firing frequency of individual fingers. Compared with conventional approaches, our technique led to better prediction performances, i.e. a higher correlation ([Formula: see text] versus [Formula: see text]), a lower prediction error ([Formula: see text]% MVC versus [Formula: see text]% MVC), and a higher accuracy in finger state (rest/active) prediction ([Formula: see text]% versus [Formula: see text]%). Our decoding method demonstrated the possibility of classifying motoneurons for different fingers, which significantly alleviated the cross-talk issue of EMG recordings from neighboring hand muscles, and allowed the decoding of finger forces individually and concurrently. The outcomes offered a robust neural-machine interface that could allow users to intuitively control robotic hands in a dexterous manner.

OBJECTIVE: Functional electrical stimulation (FES) is a common technique to elicit muscle contraction and help improve muscle strength. Traditional FES over the muscle belly typically only activates superficial muscle regions. In the case of hand FES, this prevents the activation of the deeper flexor muscles which control the distal finger joints. Here, we evaluated whether an alternative transcutaneous nerve-bundle stimulation approach can activate both superficial and deep extrinsic finger flexors using a high-density stimulation grid. METHODS: Transverse ultrasound of the forearm muscles was used to obtain cross-sectional images of the underlying finger flexors during stimulated finger flexions and kinematically-matched voluntary motions. Finger kinematics were recorded, and an image registration method was used to capture the large deformation of the muscle regions during each flexion. This deformation was used as a surrogate measure of the contraction of muscle tissue, and the regions of expanding tissue can identify activated muscles. RESULTS: The nerve-bundle stimulation elicited contractions in the superficial and deep finger flexors. Both separate and concurrent activation of these two muscles were observed. Joint kinematics of the fingers also matched the expected regions of muscle contractions. CONCLUSIONS: Our results showed that the nerve-bundle stimulation technique can activate the deep extrinsic finger flexors, which are typically not accessible via traditional surface FES. SIGNIFICANCE: Our nerve-bundle stimulation method enables us to produce the full range of motion of different joints necessary for various functional grasps, which could benefit future neuroprosthetic applications.

Estimation of joint kinematics plays an important role in intuitive human-machine interactions. However, continuous and reliable estimation of small (e.g., the finger) joint angles is still a challenge. The objective of this study was to continuously estimate finger joint angles using populational motoneuron firing activities. Multi-channel surface electromyogram (sEMG) signals were obtained from the extensor digitorum communis muscles, while the subjects performed individual finger oscillatory extension movements at two different speeds. The individual finger movement was first classified based on the EMG signals. The discharge timings of individual motor units were extracted through high-density EMG decomposition, and were then pooled as a composite discharge train. The firing frequency of the populational motor unit firing events was used to represent the descending neural drive to the motor unit pool. A second-order polynomial regression was then performed to predict the measured metacarpophalangeal extension angle using the derived neural drive based on the neuronal firings. Our results showed that individual finger extension movement can be classified with >96% accuracy based on multi-channel EMG. The extension angles of individual fingers can be predicted continuously by the derived neural drive with R2values >0.8. The performance of the neural-drive-based approach was superior to the conventional EMG-amplitude-based approach, especially during fast movements. These findings indicated that the neural-drive-based interface was a promising approach to reliably predict individual finger kinematics.

The human hand is capable of producing versatile yet precise movements largely owing to the complex neuromuscular systems that control our finger movement. This study seeks to quantify the spatial activation patterns of the forearm flexor muscles during individualized finger flexions. High-density (HD) surface electromyogram (sEMG) signals of forearm flexor muscles were obtained, and individual motor units were decomposed from the sEMG. Both macro-level spatial patterns of EMG activity and micro-level motor unit distributions were used to systematically characterize the forearm flexor activation patterns. Different features capturing the spatial patterns were extracted, and the unique patterns of forearm flexor activation were then quantified using pattern recognition approaches. We found that the forearm flexor spatial activation during the ring finger flexion was mostly distinct from other fingers, whereas the activation patterns of the middle finger were least distinguishable. However, all the different activation patterns can still be classified in high accuracy (94-100%) using pattern recognition. Our findings indicate that the partial overlapping of neural activation can limit accurate identification of specific finger movement based on limited recordings and sEMG features, and that HD sEMG recordings capturing detailed spatial activation patterns at both macro- and micro-levels are needed.

In motor tasks with redundancy neuromotor noise can lead to variations in execution while achieving relative invariance in the result. The present study examined whether humans find solutions that are tolerant to intrinsic noise. Using a throwing task in a virtual set-up where an infinite set of angle and velocity combinations at ball release yield throwing accuracy, our computational approach permitted quantitative predictions about solution strategies that are tolerant to noise. Based on a mathematical model of the task expected results were computed and provided predictions about error-tolerant strategies (Hypothesis 1). As strategies can take on a large range of velocities, a second hypothesis was that subjects select strategies that minimize velocity at release to avoid costs associated with signal- or velocity-dependent noise or higher energy demands (Hypothesis 2). Two experiments with different target constellations tested these two hypotheses. Results of Experiment 1 showed that subjects chose solutions with high error-tolerance, although these solutions also had relatively low velocity. These two benefits seemed to outweigh that for many subjects these solutions were close to a high-penalty area, i.e. they were risky. Experiment 2 dissociated the two hypotheses. Results showed that individuals were consistent with Hypothesis 1 although their solutions were distributed over a range of velocities. Additional analyses revealed that a velocity-dependent increase in variability was absent, probably due to the presence of a solution manifold that channeled variability in a task-specific manner. Hence, the general acceptance of signal-dependent noise may need some qualification. These findings have significance for the fundamental understanding of how the central nervous system deals with its inherent neuromotor noise.