Self-supervised representation learning with continuous training data improves the feel and performance of myoelectric control.

Pattern recognition-based myoelectric control is traditionally trained with static or ramp contractions, but this fails to capture the dynamic nature of real-world movements. This study investigated the benefits of training classifiers with continuous dynamic data, encompassing transitions between various movement classes. We employed both conventional (LDA) and deep learning (LSTM) classifiers, comparing their performance when trained with ramp data, continuous dynamic data, and an LSTM pre-trained with a self-supervised learning technique (VICReg).

(Un)supervised (Co)adaptation via Incremental Learning for Myoelectric Control: Motivation, Review, and Future Directions.

This paper presents a narrative review of incremental learning methods for myoelectric control, outlining both the historical trajectory and potential of adaptive prosthetic systems. Traditional myoelectric control has evolved from direct control techniques to advanced pattern recognition, yet persistent challenges such as signal non-stationarities and, consequently, the need for frequent recalibration remain. Incremental learning may enable a paradigm shift by continuously updating control models based on real-time, user-in-the-loop data, thereby addressing user-specific variations, environmental changes, and challenges from screen-guided-training based calibration.

A dataset of high-resolution plantar pressures for gait analysis across varying footwear and walking speeds.

Gait refers to the patterns of limb movement generated during walking, which are unique to each individual due to both physical and behavioural traits. Walking patterns have been widely studied in biometrics, biomechanics, sports, and rehabilitation. While traditional methods rely on video and motion capture, advances in plantar pressure sensing technology now offer deeper insights into gait.

Variability-based assessment of assisted gait using a multi-sensor instrumented cane.

The biomechanics of walking with assistive canes are not well understood clinically, despite their long history. Canes are also often misused or not used at all once taken home, despite the known benefits of proper use. To help clinicians and users evaluate and monitor cane use at home and in the community, a multi-sensor instrumented cane and interpretable gait performance metrics have been proposed.

A Qualitative Exploration of EMG Visual Feedback for Spinal Cord Injury Rehabilitation.

Sustaining motivation during hand function rehabilitation after a Spinal cord injury (SCI) can be challenging, particularly when natural movement feedback is impaired. Augmented feedback, such as through visual feedback of electromyography (EMG) muscle activity, may support motor (re-) learning and user motivation, but its impact on SCI rehabilitation remains underexplored. This study involved the design of an EMG-based visual feedback tool and an exploration of its suitability in rehabilitation and potential impact on user motivation.

Efficient Multi-Positioned Training for Regression-Based Myoelectric Control: Exploring Transformer Models with Transfer Learning.

State-of-the-art upper-limb myoelectric prostheses are typically controlled using classification-based models that do not offer simultaneous control of wrist and hand movements (degrees of freedom or DOFs). Regression-based alternatives are being studied because they do offer simultaneous DOF control, yielding more natural movements, but generally require longer training routines. We investigated methods to reduce the training burden for regression-based myoelectric control.

Context-Informed Incremental Learning Improves Throughput and Reduces Drift in Regression-Based Myoelectric Control.

Despite decades of research, commercially available powered myoelectric prostheses continue to use sequential, classification-based control. While regression-based approaches can improve the dexterity offered through simultaneous, independent, and proportional control, current training protocols lack consistency across studies and fail to capture realistic user behaviours, resulting in robustness issues. To address these challenges, this work employs context-informed incremental learning (CIIL) in an unconstrained, velocity-based environment for regression-based myoelectric control.

Covariate Analysis for Footstep Recognition Using Unsupervised Hierarchical Clustering.

Footstep recognition is an emerging biometric that identifies or verifies users based on footstep pressure patterns obtained while walking. However, the impact of covariates on footstep recordings is not well understood, unlike more established biometric traits such as fingerprint and facial recognition. Therefore, this study used unsupervised hierarchical clustering (HCA) to examine the internal and external covariate influence on spatial and temporal footstep features of twenty individuals.

BioPoint: Enhancing Human-Computer Interaction through Single-Site, Multi-Sensor Gesture Recognition.

Advancements in human-computer interaction (HCI) and machine learning are seen as key avenues to help individuals living with upper limb disabilities in accomplishing their activities of daily living. Multi-channel myoelectric systems are a promising approach for HCI due to their intuitive and accurate capture of user intent through muscle activity. However, such systems are still bulky compared to widely accepted smartwatches-like devices and as such pose a challenge for seamless integration into daily life.

StepGAN: Gait Feature Extraction Using Generative Adversarial Networks for Footstep Recognition.

Pressure recordings of footsteps during walking can offer a convenient biometric recognition method for applications in security, forensic analysis, and health monitoring. However, footsteps can exhibit high variability due to a complex interplay of internal and external factors, posing a challenge for recognition systems. To address this issue, this study employed generative adversarial networks with a second discriminator and triplet loss to extract features from high-resolution foot pressure images.

Visual Scene Understanding for Enhanced EMG Gesture Recognition.

This work presents a multimodal approach combining electromyography (EMG) and computer vision (CV) for robust real-time gesture recognition in a real-world setting. A context-aware framework is proposed for myoelectric prosthesis control, wherein EMG hand gesture recognition is augmented by the visual detection of objects of interest in a scene, effectively mitigating risks of false movements. By supporting EMG gesture predictions produced by a Siamese deep convolution neural network (SDCNN) with context derived from object detection using a tailored YOLO computer vision model, the system prevents false detection during gesture onset and during static gesture maintenance.

Screen Guided Training Does Not Capture Goal-Oriented Behaviours: Learning Myoelectric Control Mappings From Scratch Using Context Informed Incremental Learning.

Human-machine interfaces based on myoelectric signals typically use screen-guided training (SGT) for model calibration, but this approach fails to capture realistic user behaviors. This study evaluates a user-in-the-loop context-informed incremental learning (CIIL) framework, comparing SGT, SGT followed by CIIL adaptation (SGT-A), and a novel zero-shot adaptation (ZS-A) CIIL approach that begins adapting with no prior training. Sixteen participants completed a Fitts' Law targeting task using these control schemes, with performance measured via online throughput and offline classification accuracy.

Advancing Myoelectric Prostheses: Efficacy of Gold-Plated 3D-Printed Thermoplastic Dry Electrodes.

In the evolving landscape of assistive technologies, significant advancements are being made in the functionality of intelligent myoelectric prostheses, positioning them as a legitimate option for amputees and persons with congenital limb differences. Concurrently, 3D printing is transitioning from its traditional role as a prototyping tool to a viable, cost-effective method for manufacturing. Against this backdrop, it becomes feasible to assess the capabilities of 3D printing in fabricating intricate components, such as electrodes, which are critical for the effective operation of these prostheses.

EMG-based wake gestures eliminate false activations during out-of-set activities of daily living: an online myoelectric control study.

While myoelectric control has been commercialized in prosthetics for decades, its adoption for more general human-machine interaction has been slow. Although high accuracies can be achieved across many gestures, current control approaches are prone to false activations in real-world conditions. This is because the same electromyogram (EMG) signals generated during the elicitation of gestures are also naturally activated when performing activities of daily living (ADLs), such as when driving to work or while typing on a keyboard.

Self-supervised learning via VICReg enables training of EMG pattern recognition using continuous data with unclear labels.

In this study, we investigate the application of self-supervised learning via pre-trained Long Short-Term Memory (LSTM) networks for training surface electromyography pattern recognition models (sEMG-PR) using dynamic data with transitions. While labeling such data poses challenges due to the absence of ground-truth labels during transitions between classes, self-supervised pre-training offers a way to circumvent this issue. We compare the performance of LSTMs trained with either fully-supervised or self-supervised loss to a conventional non-temporal model (LDA) on two data types: segmented ramp data (lacking transition information) and continuous dynamic data inclusive of class transitions.

Enhancing neuroprosthesis calibration: the advantage of integrating prior training over exclusive use of new data.

Neuroprostheses typically operate under supervised learning, in which a machine-learning algorithm is trained to correlate neural or myoelectric activity with an individual's motor intent. Due to the stochastic nature of neuromyoelectric signals, algorithm performance decays over time. This decay is accelerated when attempting to regress proportional control of multiple joints in parallel, compared with the more typical classification-based pattern recognition control.

Big data in myoelectric control: large multi-user models enable robust zero-shot EMG-based discrete gesture recognition.

Myoelectric control, the use of electromyogram (EMG) signals generated during muscle contractions to control a system or device, is a promising input, enabling always-available control for emerging ubiquitous computing applications. However, its widespread use has historically been limited by the need for user-specific machine learning models because of behavioural and physiological differences between users. Leveraging the publicly available 612-user EMG-EPN612 dataset, this work dispels this notion, showing that true zero-shot cross-user myoelectric control is achievable without user-specific training.

Comparing online wrist and forearm EMG-based control using a rhythm game-inspired evaluation environment.

The use of electromyogram (EMG) signals recorded from the wrist is emerging as a desirable input modality for human-machine interaction (HMI). Although forearm-based EMG has been used for decades in prosthetics, there has been comparatively little prior work evaluating the performance of wrist-based control, especially in online, user-in-the-loop studies. Furthermore, despite different motivating use cases for wrist-based control, research has mostly adopted legacy prosthesis control evaluation frameworks.

Understanding the influence of confounding factors in myoelectric control for discrete gesture recognition.

Discrete myoelectric control-based gesture recognition has recently gained interest as a possible input modality for many emerging ubiquitous computing applications. Unlike the continuous control commonly employed in powered prostheses, discrete systems seek to recognize the dynamic sequences associated with gestures to generate event-based inputs. More akin to those used in general-purpose human-computer interaction, these could include, for example, a flick of the wrist to dismiss a phone call or a double tap of the index finger and thumb to silence an alarm.

Context-informed incremental learning improves both the performance and resilience of myoelectric control.

Despite its rich history of success in controlling powered prostheses and emerging commercial interests in ubiquitous computing, myoelectric control continues to suffer from a lack of robustness. In particular, EMG-based systems often degrade over prolonged use resulting in tedious recalibration sessions, user frustration, and device abandonment. Unsupervised adaptation is one proposed solution that updates a model's parameters over time based on its own predictions during real-time use to maintain robustness without requiring additional user input or dedicated recalibration.

Generalizing Upper Limb Force Modeling With Transfer Learning: A Multimodal Approach Using EMG and IMU for New Users and Conditions.

In the field of EMG-based force modeling, the ability to generalize models across individuals could play a significant role in its adoption across a range of applications, including assistive devices, robotic and rehabilitation devices. However, current studies have predominately focused on intra-subject modeling, largely neglecting the burden of end-user data acquisition. In this work, we propose the use of transfer learning (TL) to generalize force modeling to a new user by first establishing a baseline model trained using other users' data, and then adapting to the end-user using a small amount of new data (only 10% , 20% , and 40% of the new user data).

Feature Learning Networks for Floor Sensor-based Gait Recognition.

Deep learning (DL) has become a powerful tool in many image classification applications but often requires large training sets to achieve high accuracy. For applications where the available data are limited, this can become a severely limiting factor in model performance. To address this limitation, feature learning network approaches that integrate traditional feature extraction methods with DL frameworks have been proposed.

Decision-Change Informed Rejection Improves Robustness in Pattern Recognition-Based Myoelectric Control.

Post-processing techniques have been shown to improve the quality of the decision stream generated by classifiers used in pattern-recognition-based myoelectric control. However, these techniques have largely been tested individually and on well-behaved, stationary data, failing to fully evaluate their trade-offs between smoothing and latency during dynamic use. Correspondingly, in this work, we survey and compare 8 different post-processing and decision stream improvement schemes in the context of continuous and dynamic class transitions: majority vote, Bayesian fusion, onset locking, outlier detection, confidence-based rejection, confidence scaling, prior adjustment, and adaptive windowing.

Novel Wearable HD-EMG Sensor With Shift-Robust Gesture Recognition Using Deep Learning.

In this work, we present a hardware-software solution to improve the robustness of hand gesture recognition to confounding factors in myoelectric control. The solution includes a novel, full-circumference, flexible, 64-channel high-density electromyography (HD-EMG) sensor called EMaGer. The stretchable, wearable sensor adapts to different forearm sizes while maintaining uniform electrode density around the limb.