The effects of electrode size and orientation on the sensitivity of myoelectric pattern recognition systems to electrode shift

EMG features dataset for arm activity recognition

This study presents a dataset on hand gesture recognition using electromyography (EMG) signals. The data was collected from eight healthy subjects aged between 19 and 35 years, with each subject performing three distinct hand gestures (lifting, grabbing, and flexing). Surface EMG signals were recorded using the Delsys Trigno Wireless biofeedback system from four sensors placed on the dominant hand's Palm A, Palm B, Biceps, and Forearm. The signals were sampled at 2000 Hz and segmented into gesture trials for analysis. The raw EMG data were filtered and processed to extract seven time-domain features across each channel, resulting in 28 total features. These features were reduced using Principal Component Analysis (PCA) to six components, which accounted for 95 % of the variance. The dataset was then used to train and test machine learning models (Random Forest and Logistic Regression) for gesture classification. This dataset has potential reuse in developing gesture recognition algorithms, enhancing prosthetic control, or exploring human-computer interaction (HCI) applications.

Gesture Recognition Through Mechanomyogram Signals: An Adaptive Framework for Arm Posture Variability

In hand gesture recognition, classifying gestures across multiple arm postures is challenging due to the dynamic nature of muscle fibers and the need to capture muscle activity through electrical connections with the skin. This paper presents a gesture recognition architecture addressing the arm posture challenges using an unsupervised domain adaptation technique and a wearable mechanomyogram (MMG) device that does not require electrical contact with the skin. To deal with the transient characteristics of muscle activities caused by changing arm posture, Continuous Wavelet Transform (CWT) combined with Domain-Adversarial Convolutional Neural Networks (DACNN) were used to extract MMG features and classify hand gestures. DACNN was compared with supervised trained classifiers and shown to achieve consistent improvement in classification accuracies over multiple arm postures. With less than 5 minutes of setup time to record 20 examples per gesture in each arm posture, the developed method achieved an average prediction accuracy of $87.43 \%$ for classifying 5 hand gestures in the same arm posture and $64.29 \%$ across 10 different arm postures. When further expanding the MMG segmentation window from $200 \,\mathrm{ms}$ to $600 \,\mathrm{ms}$ to extract greater discriminatory information at the expense of longer response time, the intra-posture and inter-posture accuracies increased to $92.32 \%$ and $71.75 \%$. The findings demonstrate the capability of the proposed method to improve generalization throughout dynamic changes caused by arm postures during non-laboratory usages and the potential of MMG to be an alternative sensor with comparable performance to the widely used electromyogram (EMG) gesture recognition systems.

Human-in-the-Loop Myoelectric Pattern Recognition Control of an Arm-Support Robot to Improve Reaching in Stroke Survivors

The objective of this study was to assess the feasibility and efficacy of using real-time human-in-the-loop pattern recognition-based myoelectric control to control vertical support force or vertical position to improve reach in individuals with chronic stroke. This work attempts to move proven lab-based static arm support paradigms towards a controllable wearable device. A machine learning (linear discriminant analysis)-based myoelectric pattern recognition system based on movement intent as determined by real-time muscle activation was used to control incremental changes in either vertical position or vertical support force during a reach and retrieve task, with the goal of improving reaching function. Performance under real-time control of both options was compared to two unchanging static-support conditions (current gold standard) and a no-support condition. Both real-time control paradigms were successfully implemented and resulted in greater forward-reaching performance as demonstrated by increased elbow extension and horizontal shoulder adduction compared to no-support and was not different from the current gold standard static support paradigms. Muscle activation levels with real-time support were lower than the no-support condition and similar to those observed during the static support paradigms. Real-time detection of user intent was successful in controlling both vertical position and vertical support force and enabled greater reaching distance than without it demonstrating both its feasibility and efficacy albeit with some limitations.

Plug-and-play myoelectric control via a self-calibrating random forest common model

Objective. Electromyographic (EMG) signals show large variabilities over time due to factors such as electrode shifting, user behavior variations, etc substantially degrading the performance of myoelectric control models in long-term use. Previously one-time model calibration was usually required each time before usage. However, the EMG characteristics could change even within a short period of time. Our objective is to develop a self-calibrating model, with an automatic and unsupervised self-calibration mechanism.Approach. We developed a computationally efficient random forest (RF) common model, which can (1) be pre-trained and easily adapt to a new user via one-shot calibration, and (2) keep calibrating itself once in a while by boosting the RF with new decision trees trained on pseudo-labels of testing samples in a data buffer.Main results. Our model has been validated in both offline and real-time, both open and closed-loop, both intra-day and long-term (up to 5 weeks) experiments. We tested this approach with data from 66 non-disabled participants. We also explored the effects of bidirectional user-model co-adaption in closed-loop experiments. We found that the self-calibrating model could gradually improve its performance in long-term use. With visual feedback, users will also adapt to the dynamic model meanwhile learn to perform hand gestures with significantly lower EMG amplitudes (less muscle effort).Significance. Our RF-approach provides a new alternative built on simple decision tree for myoelectric control, which is explainable, computationally efficient, and requires minimal data for model calibration. Source codes are avaiable at:https://github.com/MoveR-Digital-Health-and-Care-Hub/self-calibrating-rf.

EMG Dataset for Gesture Recognition with Arm Translation

Myoelectric control has emerged as a promising approach for a wide range of applications, including controlling limb prosthetics, teleoperating robots and enabling immersive interactions in the Metaverse. However, the accuracy and robustness of myoelectric control systems are often affected by various factors, including muscle fatigue, perspiration, drifts in electrode positions and changes in arm position. The latter has received less attention despite its significant impact on signal quality and decoding accuracy. To address this gap, we present a novel dataset of surface electromyographic (EMG) signals captured from multiple arm positions. This dataset, comprising EMG and hand kinematics data from 8 participants performing 6 different hand gestures, provides a comprehensive resource for investigating position-invariant myoelectric control decoding algorithms. We envision this dataset to serve as a valuable resource for both training and benchmark arm position-invariant myoelectric control algorithms. Additionally, to expand the publicly available data capturing the variability of EMG signals across diverse arm positions, we propose a novel data acquisition protocol that can be utilized for future data collection.

Improving Electromyography Electrode Placement Accuracy in Transtibial Amputees: A Comparative Study of Ultrasound and Palpation Methods

In the past decade, significant focus has been on electromyography (EMG) control of prostheses in transtibial amputees (TTAs). Reliable signal acquisition requires accurate EMG electrode placement. Conventional electrode placement methods are challenging due to altered post-surgical anatomy. This study investigated the application of ultrasound imaging for placement of EMG electrodes in TTAs. Four residual limb muscles, Tibialis Anterior (TA), Peroneus Longus (PL), Gastrocnemius Medial (GM), and Gastrocnemius Lateral (GL), were examined in 9 unilateral TTAs. Ultrasound was used to identify each muscle belly's thickest part and fiber orientation. A Certified Prosthetist Orthotist (CPO) then performed palpation to identify muscle bellies, blinded to ultrasound findings. Distances between ultrasound- and palpation-identified spots were measured. EMG data were contrasted between methods in terms of root mean square (RMS) amplitude and signal-to-noise ratio (SNR). The results indicated that Ultrasound-guided placement produced slightly higher, though non-significant, signal amplitudes (p = 0.06) and significantly higher SNR (p = 0.04). Moreover, palpation misidentified muscles in four cases. In 72.2% of cases, the distance between ultrasound- and palpation-identified spots was more than 10 mm. The mean distance was the greatest for PL and GL. Relying on palpation to identify PL and TA in TTAs may provide irrelevant EMG due to erroneous placement. Using ultrasound imaging can avoid this and, in addition to accurate muscle identification, may improve signal amplitude and SNR. In conclusion, ultrasound imaging is a valuable tool for enhancing the accuracy of EMG electrode placement in TTAs, which may lead to better prosthetic control outcomes.

Mitigating the Concurrent Interference of Electrode Shift and Loosening in Myoelectric Pattern Recognition Using Siamese Autoencoder Network

The objective of this work is to develop a novel myoelectric pattern recognition (MPR) method to mitigate the concurrent interference of electrode shift and loosening, thereby improving the practicality of MPR-based gestural interfaces towards intelligent control. A Siamese auto-encoder network (SAEN) was established to learn robust feature representations against random occurrences of both electrode shift and loosening. The SAEN model was trained with a variety of shifted-view and masked-view feature maps, which were simulated through feature transformation operated on the original feature maps. Specifically, three mean square error (MSE) losses were devised to warrant the trained model's capability in adaptive recovery of any given interfered data. The SAEN was deployed as an independent feature extractor followed by a common support vector machine acting as the classifier. To evaluate the effectiveness of the proposed method, an eight-channel armband was adopted to collect surface electromyography (EMG) signals from nine subjects performing six gestures. Under the condition of concurrent interference, the proposed method achieved the highest classification accuracy in both offline and online testing compared to five common methods, with statistical significance (p <0.05). The proposed method was demonstrated to be effective in mitigating the electrode shift and loosening interferences. Our work offers a valuable solution for enhancing the robustness of myoelectric control systems.

Unravelling Influence Factors in Pattern Recognition Myoelectric Control Systems: The Impact of Limb Positions and Electrode Shifts

Pattern recognition (PR)-based myoelectric control systems can naturally provide multifunctional and intuitive control of upper limb prostheses and restore lost limb function, but understanding their robustness remains an open scientific question. This study investigates how limb positions and electrode shifts-two factors that have been suggested to cause classification deterioration-affect classifiers' performance by quantifying changes in the class distribution using each factor as a class and computing the repeatability and modified separability indices. Ten intact-limb participants took part in the study. Linear discriminant analysis (LDA) was used as the classifier. The results confirmed previous studies that limb positions and electrode shifts deteriorate classification performance (14-21% decrease) with no difference between factors (p > 0.05). When considering limb positions and electrode shifts as classes, we could classify them with an accuracy of 96.13 ± 1.44% and 65.40 ± 8.23% for single and all motions, respectively. Testing on five amputees corroborated the above findings. We have demonstrated that each factor introduces changes in the feature space that are statistically new class instances. Thus, the feature space contains two statistically classifiable clusters when the same motion is collected in two different limb positions or electrode shifts. Our results are a step forward in understanding PR schemes' challenges for myoelectric control of prostheses and further validation needs be conducted on more amputee-related datasets.

Enhancing the Myoelectric Pattern Recognition Robustness to Electrode Shift by an Autoencoder-Based Feature Calibrator

Electrode shift is considered a pivotal and unavoidable factor affecting the robustness of myoelectric pattern recognition (MPR). Nevertheless, most existing solutions face challenges in simultaneously ensuring plug-and-play compatibility and achieving high classification accuracy. To address this challenge, this study presents a novel method for adaptively calibrating testing data samples using an autoencoder-based feature calibrator. A feature transformation approach, encompassing interpolation, translation, and down-sampling operations, is executed on the original feature map to generate the simulated feature map representing the shifted view. Subsequently, the flattened shifted view features serve as input for the autoencoder network, facilitating the model to learn a more resilient feature representation based on the reconstruction error between the output and the original features. The trained autoencoder is deployed as an independent feature calibrator in the training and testing process of the classifier. The performance of the proposed method was evaluated with data recorded by wearing an 8-channel armband on the forearm of five subjects performing six gestures. The proposed method achieved a high classification accuracy of 87.20±3.53% under the electrode shift condition, outperforming three commonly used comparison methods with statistical significance (p < 0.05). This study provides a practical solution for mitigating electrode shift interference without requiring any additional calibration data, which contributes to enhancing the robustness of MPR systems.

SonoMyoNet: A Convolutional Neural Network for Predicting Isometric Force from Highly Sparse Ultrasound Images

Ultrasound imaging or sonomyography has been found to be a robust modality for measuring muscle activity due to its ability to image deep-seated muscles directly while providing superior spatiotemporal specificity compared to surface electromyography-based techniques. Quantifying the morphological changes during muscle activity involves computationally expensive approaches for tracking muscle anatomical structures or extracting features from brightness-mode (B-mode) images and amplitude-mode (A-mode) signals. This paper uses an offline regression convolutional neural network (CNN) called SonoMyoNet to estimate continuous isometric force from sparse ultrasound scanlines. SonoMyoNet learns features from a few equispaced scanlines selected from B-mode images and utilizes the learned features to estimate continuous isometric force accurately. The performance of SonoMyoNet was evaluated by varying the number of scanlines to simulate the placement of multiple single-element ultrasound transducers in a wearable system. Results showed that SonoMyoNet could accurately predict isometric force with just four scanlines and is immune to speckle noise and shifts in the scanline location. Thus, the proposed network reduces the computational load involved in feature tracking algorithms and estimates muscle force from the global features of sparse ultrasound images.

Prediction of Dexterous Finger Forces With Forearm Rotation Using Motoneuron Discharges

Motor unit (MU) discharge information obtained via electromyogram (EMG) decomposition can be used to decode dexterous multi-finger movement intention for neural-machine interfaces (NMI). However, the variation of the motor unit action potential (MUAP) shape resulted from forearm rotation leads to the decreased performance of EMG decomposition, especially under the real-time condition and then the degradation of motion decoding accuracy. The object of this study was to develop a method to realize the accurate extraction of MU discharge information across forearm pronated/supinated positions in the real-time condition for dexterous multi-finger force prediction. The FastICA-based EMG decomposition technique was used and the proposed method obtained multiple separation vectors for each MU at different forearm positions in the initialization phase. Under the real-time condition, the MU discharge information was extracted adaptively using the separation vector extracted at the nearest forearm position. As comparison, the previous method that utilized a single constant separation vector to extract MU discharges across forearm positions and the conventional method that utilized the EMG amplitude information were also performed. The results showed that the proposed method obtained a significantly better performance compared with the other two methods, manifested in a larger coefficient of determination ( [Formula: see text] and a smaller root mean squared error (RMSE) between the predicted and recorded force. Our results demonstrated the feasibility and the effectiveness of the proposed method to extract MU discharge information during forearm rotation for dexterous force prediction under the real-time conditions. Further development of the proposed method could potentially promote the application of the EMG decomposition technique for continuous dexterous motion decoding in a realistic NMI application scenario.

Design, Fabrication and Evaluation of a Stretchable High-Density Electromyography Array

The adoption of high-density electrode systems for human-machine interfaces in real-life applications has been impeded by practical and technical challenges, including noise interference, motion artefacts and the lack of compact electrode interfaces. To overcome some of these challenges, we introduce a wearable and stretchable electromyography (EMG) array, and present its design, fabrication methodology, characterisation, and comprehensive evaluation. Our proposed solution comprises dry-electrodes on flexible printed circuit board (PCB) substrates, eliminating the need for time-consuming skin preparation. The proposed fabrication method allows the manufacturing of stretchable sleeves, with consistent and standardised coverage across subjects. We thoroughly tested our developed prototype, evaluating its potential for application in both research and real-world environments. The results of our study showed that the developed stretchable array matches or outperforms traditional EMG grids and holds promise in furthering the real-world translation of high-density EMG for human-machine interfaces.

First-in-human demonstration of floating EMG sensors and stimulators wirelessly powered and operated by volume conduction

BACKGROUND

Recently we reported the design and evaluation of floating semi-implantable devices that receive power from and bidirectionally communicate with an external system using coupling by volume conduction. The approach, of which the semi-implantable devices are proof-of-concept prototypes, may overcome some limitations presented by existing neuroprostheses, especially those related to implant size and deployment, as the implants avoid bulky components and can be developed as threadlike devices. Here, it is reported the first-in-human acute demonstration of these devices for electromyography (EMG) sensing and electrical stimulation.

METHODS

A proof-of-concept device, consisting of implantable thin-film electrodes and a nonimplantable miniature electronic circuit connected to them, was deployed in the upper or lower limb of six healthy participants. Two external electrodes were strapped around the limb and were connected to the external system which delivered high frequency current bursts. Within these bursts, 13 commands were modulated to communicate with the implant.

RESULTS

Four devices were deployed in the biceps brachii and the gastrocnemius medialis muscles, and the external system was able to power and communicate with them. Limitations regarding insertion and communication speed are reported. Sensing and stimulation parameters were configured from the external system. In one participant, electrical stimulation and EMG acquisition assays were performed, demonstrating the feasibility of the approach to power and communicate with the floating device.

CONCLUSIONS

This is the first-in-human demonstration of EMG sensors and electrical stimulators powered and operated by volume conduction. These proof-of-concept devices can be miniaturized using current microelectronic technologies, enabling fully implantable networked neuroprosthetics.

Adaptive neuro-fuzzy inference system model driven by the non-negative matrix factorization-extracted muscle synergy patterns to estimate lower limb joint movements

BACKGROUND AND OBJECTIVE

For patients with movement disorders, the main clinical focus is on exercise rehabilitation to help recover lost motor function, which is achieved by relevant assisted equipment. The basis for seamless control of the assisted equipment is to achieve accurate inference of the user's movement intentions in the human-machine interface. This study proposed a novel movement intention detection technology for estimating lower limb joint continuous kinematic variables following muscle synergy patterns, to develop applications for more efficient assisted rehabilitation training.

METHODS

This study recruited 16 healthy males and 16 male patients with symptomatic patellar tendinopathy (VISA-P: 59.1 ± 8.7). The surface electromyography of 12 muscles and lower limb joint kinematic and kinetic data from healthy subjects and patients during step-off landings from 30 cm-high stair steps were collected. We subsequently solved the preprocessed data based on the established recursive model of second-order differential equation to obtain the muscle activation matrix, and then imported it into the non-negative matrix factorization model to obtain the muscle synergy matrix. Finally, the lower limb neuromuscular synergy pattern was then imported into the developed adaptive neuro-fuzzy inference system non-linear regression model to estimate the human movement intention during this movement pattern.

RESULTS

Six muscle synergies were determined to construct the muscle synergy pattern driven ANFIS model. Three fuzzy rules were determined in most estimation cases. Combining the results of the four error indicators across the estimated variables indicates that the current model has excellent estimated performance in estimating lower limb joint movement. The estimation errors between the healthy (Angle: R2=0.98±0.03; Torque: R2=0.96±0.04) and patient (Angle: R2=0.98±0.02; Torque: R2=0.96±0.03) groups are consistent.

CONCLUSION

The proposed model of this study can accurately and reliably estimate lower limb joint movements, and the effectiveness will also be radiated to the patient group. This revealed that our models also have certain advantages in the recognition of motor intentions in patients with relevant movement disorders. Future work from this study can be focused on sports rehabilitation in the clinical field by achieving more flexible and precise movement control of the lower limb assisted equipment to help the rehabilitation of patients.

Feasibility of force myography for the direct control of an assistive robotic hand orthosis in non-impaired individuals

BACKGROUND

Assistive robotic hand orthoses can support people with sensorimotor hand impairment in many activities of daily living and therefore help to regain independence. However, in order for the users to fully benefit from the functionalities of such devices, a safe and reliable way to detect their movement intention for device control is crucial. Gesture recognition based on force myography measuring volumetric changes in the muscles during contraction has been previously shown to be a viable and easy to implement strategy to control hand prostheses. Whether this approach could be efficiently applied to intuitively control an assistive robotic hand orthosis remains to be investigated.

METHODS

In this work, we assessed the feasibility of using force myography measured from the forearm to control a robotic hand orthosis worn on the hand ipsilateral to the measurement site. In ten neurologically-intact participants wearing a robotic hand orthosis, we collected data for four gestures trained in nine arm configurations, i.e., seven static positions and two dynamic movements, corresponding to typical activities of daily living conditions. In an offline analysis, we determined classification accuracies for two binary classifiers (one for opening and one for closing) and further assessed the impact of individual training arm configurations on the overall performance.

RESULTS

We achieved an overall classification accuracy of 92.9% (averaged over two binary classifiers, individual accuracies 95.5% and 90.3%, respectively) but found a large variation in performance between participants, ranging from 75.4 up to 100%. Averaged inference times per sample were measured below 0.15 ms. Further, we found that the number of training arm configurations could be reduced from nine to six without notably decreasing classification performance.

CONCLUSION

The results of this work support the general feasibility of using force myography as an intuitive intention detection strategy for a robotic hand orthosis. Further, the findings also generated valuable insights into challenges and potential ways to overcome them in view of applying such technologies for assisting people with sensorimotor hand impairment during activities of daily living.

High-Fidelity sEMG Signals Recorded by an on-Skin Electrode Based on AgNWs for Hand Gesture Classification Using Machine Learning

The human forearm is one of the most densely distributed parts of the human body, with the most irregular spatial distribution of muscles. A number of specific forearm muscles control hand motions. Acquiring high-fidelity sEMG signals from human forearm muscles is vital for human-machine interface (HMI) applications based on gesture recognition. Currently, the most commonly used commercial electrodes for detecting sEMG or other electrophysiological signals have a rigid nature without stretchability and cannot maintain conformal contact with the human skin during deformation, and the adhesive hydrogel used in them to reduce skin-electrode impedance may shrink and cause skin inflammation after long-term use. Therefore, developing elastic electrodes with stretchability and biocompatibility for sEMG signal recording is essential for developing HMI. Here, we fabricated a nanocomposite hybrid on-skin electrode by infiltrating silver nanowires (AgNWs), a one-dimensional (1D) nano metal material with conductivity, into polydimethylsiloxane (PDMS), a silicone elastomer with a similar Young's modulus to that of the human skin. The AgNW on-skin electrode has a thickness of 300 μm and low sheet resistance of 0.481 ± 0.014 Ω/sq and can withstand the mechanical strain of up to 54% and maintain a sheet resistance lower than 1 Ω/sq after 1000 dynamic strain cycles. The AgNW on-skin electrode can record high signal-to-noise ratio (SNR) sEMG signals from forearm muscles and can reflect various force levels of muscles by sEMG signals. Besides, four typical hand gestures were recognized by the multichannel AgNW on-skin electrodes with a recognition accuracy of 92.3% using machine learning method. The AgNW on-skin electrode proposed in this study has great potential and promise in various HMI applications that employ sEMG signals as control signals.

Normalization of the electromyography amplitude during a multiple-set resistance training protocol: Reliability and differences between approaches

The first aim was to investigate the impact of different electromyography (EMG) parameters as a reference to normalize the EMG amplitude of the superficial quadriceps femoris muscles across different sets of a knee extension exercise. The second aim is to examine the reliability between days of the EMG parameters used as a reference. Eleven young males attended the laboratory on 4 different days and performed one repetition maximum test, maximumvoluntary isometric contractions, and a resistance training protocol until failure. Surface EMG was placed over the rectus femoris, vastus lateralis, and vastus medialis muscles. Seven EMG parameters were calculated from the tasks and used to normalize EMG amplitude measured during the resistance training protocol. A repeated-measures two-way ANOVA was used (normalized EMG amplitude × set) to compare normalized EMG across sets, while an intraclass correlation coefficient, coefficient of variation, and Bland-Altman plots were used to calculate the intra-day reliability of the EMG parameters. The present investigation showed that normalized EMG amplitude of the superficial muscles of the quadriceps measured during a knee extension exercise is influenced by the EMG parameter and depends on the muscle. While rectus femoris and vastus lateralis normalized EMG amplitude presented one parameter among seven showing similar value to the other parameters, VM showed two. Lastly, all EMG parameters for all muscles presented an overall excellent reliability and agreement between days.

Customizable, reconfigurable, and anatomically coordinated large-area, high-density electromyography from drawn-on-skin electrode arrays

Accurate anatomical matching for patient-specific electromyographic (EMG) mapping is crucial yet technically challenging in various medical disciplines. The fixed electrode construction of multielectrode arrays (MEAs) makes it nearly impossible to match an individual's unique muscle anatomy. This mismatch between the MEAs and target muscles leads to missing relevant muscle activity, highly redundant data, complicated electrode placement optimization, and inaccuracies in classification algorithms. Here, we present customizable and reconfigurable drawn-on-skin (DoS) MEAs as the first demonstration of high-density EMG mapping from in situ-fabricated electrodes with tunable configurations adapted to subject-specific muscle anatomy. The DoS MEAs show uniform electrical properties and can map EMG activity with high fidelity under skin deformation-induced motion, which stems from the unique and robust skin-electrode interface. They can be used to localize innervation zones (IZs), detect motor unit propagation, and capture EMG signals with consistent quality during large muscle movements. Reconfiguring the electrode arrangement of DoS MEAs to match and extend the coverage of the forearm flexors enables localization of the muscle activity and prevents missed information such as IZs. In addition, DoS MEAs customized to the specific anatomy of subjects produce highly informative data, leading to accurate finger gesture detection and prosthetic control compared with conventional technology.

Ascertaining the optimal myoelectric signal recording duration for pattern recognition based prostheses control

Introduction

Electromyogram-based pattern recognition (EMG-PR) has been widely considered an essentially intuitive control method for multifunctional upper limb prostheses. A crucial aspect of the scheme is the EMG signal recording duration (SRD) from which requisite motor tasks are characterized per time, impacting the system's overall performance. For instance, lengthy SRD inevitably introduces fatigue (that alters the muscle contraction patterns of specific limb motions) and may incur high computational costs in building the motion intent decoder, resulting in inadequate prosthetic control and controller delay in practical usage. Conversely, relatively shorter SRD may lead to reduced data collection durations that, among other advantages, allow for more convenient prosthesis recalibration protocols. Therefore, determining the optimal SRD required to characterize limb motion intents adequately that will aid intuitive PR-based control remains an open research question.

Method

This study systematically investigated the impact and generalizability of varying lengths of myoelectric SRD on the characterization of multiple classes of finger gestures. The investigation involved characterizing fifteen classes of finger gestures performed by eight normally limb subjects using various groups of EMG SRD including 1, 5, 10, 15, and 20 s. Two different training strategies including Between SRD and Within-SRD were implemented across three popular machine learning classifiers and three time-domain features to investigate the impact of SRD on EMG-PR motion intent decoder.

Result

The between-SRD strategy results which is a reflection of the practical scenario showed that an SRD greater than 5 s but less than or equal to 10 s (>5 and < = 10 s) would be required to achieve decent average finger gesture decoding accuracy for all feature-classifier combinations. Notably, lengthier SRD would incur more acquisition and implementation time and vice-versa. In inclusion, the study's findings provide insight and guidance into selecting appropriate SRD that would aid inadequate characterization of multiple classes of limb motion tasks in PR-based control schemes for multifunctional prostheses.

Muscle Engagement Monitoring Using Self-Adhesive Elastic Nanocomposite Fabrics

Insight into, and measurements of, muscle contraction during movement may help improve the assessment of muscle function, quantification of athletic performance, and understanding of muscle behavior, prior to and during rehabilitation following neuromusculoskeletal injury. A self-adhesive, elastic fabric, nanocomposite, skin-strain sensor was developed and validated for human movement monitoring. We hypothesized that skin-strain measurements from these wearables would reveal different degrees of muscle engagement during functional movements. To test this hypothesis, the strain sensing properties of the elastic fabric sensors, especially their linearity, stability, repeatability, and sensitivity, were first verified using load frame tests. Human subject tests conducted in parallel with optical motion capture confirmed that they can reliably measure tensile and compressive skin-strains across the calf and tibialis anterior. Then, a pilot study was conducted to assess the correlation of skin-strain measurements with surface electromyography (sEMG) signals. Subjects did biceps curls with different weights, and the responses of the elastic fabric sensors worn over the biceps brachii and flexor carpi radialis (i.e., forearm) were well-correlated with sEMG muscle engagement measures. These nanocomposite fabric sensors were validated for monitoring muscle engagement during functional activities and did not suffer from the motion artifacts typically observed when using sEMGs in free-living community settings.

Noncontact Electromagnetic Wireless Recognition for Prosthesis Based on Intelligent Metasurface

With the development of artificial intelligence and Internet of Things, hand gesture recognition techniques have attracted great attention owing to their excellent applications in developing human-machine interaction (HMI). Here, the authors propose a non-contact hand gesture recognition method based on intelligent metasurface. Owing to the advantage of dynamically controlling the electromagnetic (EM) focusing in the wavefront engineering, a transmissive programmable metasurface is presented to illuminate the forearm with more focusing spots and obtain comprehensive echo data, which can be processed under the machine learning technology to reach the non-contact gesture recognition with high accuracy. Compared with the traditional passive antennas, unique variations of echo coefficients resulted from near fields perturbed by finger and wrist agonist muscles can be aquired through the programmable metasurface by switching the positions of EM focusing. The authors realize the gesture recognition using support vector machine algorithm based on five individual focusing spots data and all-five-spot data. The influences of the focusing spots on the gesture recognition are analyzed through linear discriminant analysis algorithm and Fisher score. Experimental verifications prove that the proposed metasurface-based non-contact wireless design can realize the classification of hand gesture recognition with higher accuracy than traditional passive antennas, and give an HMI solution.

Finger Force Estimation using Motor Unit Discharges Across Forearm Postures

BACKGROUND

Myoelectric-based decoding has gained popularity in upper-limb neural-machine interfaces. Motor unit (MU) firings decomposed from surface electromyographic (EMG) signals can represent motor intent, but EMG properties at different arm configurations can change due to electrode shift and differing neuromuscular states. This study investigated whether isometric fingertip force estimation using MU firings is robust to forearm rotations from a neutral to either a fully pronated or supinated posture.

METHODS

We extracted MU information from high-density EMG of the extensor digitorum communis in two ways: (1) Decomposed EMG in all three postures (MU-AllPost); and (2) Decomposed EMG in neutral posture (MU-Neu), and extracted MUs (separation matrix) were applied to other postures. Populational MU firing frequency estimated forces scaled to subjects' maximum voluntary contraction (MVC) using a regression analysis. The results were compared with the conventional EMG-amplitude method.

RESULTS

We found largely similar root-mean-square errors (RMSE) for the two MU-methods, indicating that MU decomposition was robust to postural differences. MU-methods demonstrated lower RMSE in the ring (EMG = 6.23, MU-AllPost = 5.72, MU-Neu = 5.64 %MVC) and pinky (EMG = 6.12, MU-AllPost = 4.95, MU-Neu = 5.36 %MVC) fingers, with mixed results in the middle finger (EMG = 5.47, MU-AllPost = 5.52, MU-Neu = 6.19% MVC).

CONCLUSION

Our results suggest that MU firings can be extracted reliably with little influence from forearm posture, highlighting its potential as an alternative decoding scheme for robust and continuous control of assistive devices.

Co-adaptive control of bionic limbs via unsupervised adaptation of muscle synergies

OBJECTIVE

In this work, we present a myoelectric interface that extracts natural motor synergies from multi-muscle signals and adapts in real-time with new user inputs. With this unsupervised adaptive myocontrol (UAM) system, optimal synergies for control are continuously co-adapted with changes in user motor control, or as a function of perturbed conditions via online non-negative matrix factorization guided by physiologically informed sparseness constraints in lieu of explicit data labelling.

METHODS

UAM was tested in a set of virtual target reaching tasks completed by able-bodied and amputee subjects. Tests were conducted under normative and electrode perturbed conditions to gauge control robustness with comparisons to non-adaptive and supervised adaptive myocontrol schemes. Furthermore, UAM was used to interface an amputee with a multi-functional powered hand prosthesis during standardized Clothespin Relocation Tests, also conducted in normative and perturbed conditions.

RESULTS

In virtual tests, UAM effectively mitigated performance degradation caused by electrode displacement, affording greater resilience over an existing supervised adaptive system for amputee subjects. Induced electrode shifts also had negligible effect on the real world control performance of UAM with consistent completion times (23.91±1.33 s) achieved across Clothespin Relocation Tests in the normative and electrode perturbed conditions.

CONCLUSION

UAM affords comparable robustness improvements to existing supervised adaptive myocontrol interfaces whilst providing additional practical advantages for clinical deployment.

SIGNIFICANCE

The proposed system uniquely incorporates neuromuscular control principles with unsupervised online learning methods and presents a working example of a freely co-adaptive bionic interface.

A Mass-Producible Washable Smart Garment with Embedded Textile EMG Electrodes for Control of Myoelectric Prostheses: A Pilot Study

Electromyography (EMG) is the resulting electrical signal from muscle activity, commonly used as a proxy for users' intent in voluntary control of prosthetic devices. EMG signals are recorded with gold standard Ag/AgCl gel electrodes, though there are limitations in continuous use applications, with potential skin irritations and discomfort. Alternative dry solid metallic electrodes also face long-term usability and comfort challenges due to their inflexible and non-breathable structures. This is critical when the anatomy of the targeted body region is variable (e.g., residual limbs of individuals with amputation), and conformal contact is essential. In this study, textile electrodes were developed, and their performance in recording EMG signals was compared to gel electrodes. Additionally, to assess the reusability and robustness of the textile electrodes, the effect of 30 consumer washes was investigated. Comparisons were made between the signal-to-noise ratio (SNR), with no statistically significant difference, and with the power spectral density (PSD), showing a high correlation. Subsequently, a fully textile sleeve was fabricated covering the forearm, with 14 textile electrodes. For three individuals, an artificial neural network model was trained, capturing the EMG of 7 distinct finger movements. The personalized models were then used to successfully control a myoelectric prosthetic hand.

Reliability Analysis For Finger Movement Recognition With Raw Electromyographic Signal by Evidential Convolutional Networks

Hand gesture recognition with surface electromyography (sEMG) is indispensable for Muscle-Gesture-Computer Interface. The usual focus of it is upon performance evaluation involving the accuracy and robustness of hand gesture recognition. However, addressing the reliability of such classifiers has been absent, to our best knowledge. This may be due to the lack of consensus on the definition of model reliability in this field. An uncertainty-aware model has the potential to self-evaluate the quality of its inference, thereby making it more reliable. Moreover, uncertainty-based rejection has been shown to improve the performance of sEMG-based hand gesture recognition. Therefore, we first define model reliability here as the quality of its uncertainty estimation and propose an offline framework to quantify it. To promote reliability analysis, we propose a novel end-to-end uncertainty-aware finger movement classifier, i.e., evidential convolutional neural network (ECNN), and illustrate the advantages of its multidimensional uncertainties such as vacuity and dissonance. Extensive comparisons of accuracy and reliability are conducted on NinaPro Database 5, exercise A, across CNN and three variants of ECNN based on different training strategies. The results of classifying 12 finger movements over 10 subjects show that the best mean accuracy achieved by ECNN is 76.34%, which is slightly higher than the state-of-the-art performance. Furthermore, ECNN variants are more reliable than CNN in general, where the highest improvement of reliability of 19.33% is observed. This work demonstrates the potential of ECNN and recommends using the proposed reliability analysis as a supplementary measure for studying sEMG-based hand gesture recognition.

Muscle-Specific High-Density Electromyography Arrays for Hand Gesture Classification

OBJECTIVE

Dexterous hand motion is critical for object manipulation. Electrophysiological studies of the hand are key to understanding its underlying mechanisms. High-density electromyography (HD-EMG) provides spatio-temporal information about the underlying electrical activity of muscles, which can be used in neurophysiological research, rehabilitation and control applications. However, existing EMG electrodes platforms are not muscle-specific, which makes the assessment of intrinsic hand muscles difficult.

METHODS

Muscle-specific flexible HD-EMG electrode arrays were developed to capture intrinsic hand muscle myoelectric activity during manipulation tasks. The arrays consist of 60 individual electrodes targeting 10 intrinsic hand muscles. Myoelectric activity was displayed as spatio-temporal amplitude maps to visualize muscle activation. Time-domain and temporal-spatial HD-EMG features were extracted to train cubic support vector machine machine-learning classifiers to classify the intended user motion.

RESULTS

Experimental data was collected from 5 subjects performing a range of 10 common hand motions. Spatio-temporal EMG maps showed distinct activation areas correlated to the muscles recruited during each movement. The thenar muscle fiber conduction velocity (CV) was estimated to be at 4.70.3 m/s for all subjects. Hand motions were successfully classified and average accuracy for all subjects was directly related to spatial resolution based on the number of channels used as inputs; ranging from 744% when using only 5 channels and up to 922% when using 41 channels. Temporal-spatial features were shown to provide increased motion-specific accuracy when similar muscles were recruited for different gestures.

CONCLUSIONS

Muscle-specific electrodes were capable of accurately recording HD-EMG signals from intrinsic hand muscles and accurately predicting motion.

SIGNIFICANCE

The muscle-specific electrode arrays could improve electrophysiological research studies using EMG decomposition techniques to assess motor unit activity and in applications involving the analysis of dexterous hand motions.

Questioning Domain Adaptation in Myoelectric Hand Prostheses Control: An Inter- and Intra-Subject Study

One major challenge limiting the use of dexterous robotic hand prostheses controlled via electromyography and pattern recognition relates to the important efforts required to train complex models from scratch. To overcome this problem, several studies in recent years proposed to use transfer learning, combining pre-trained models (obtained from prior subjects) with training sessions performed on a specific user. Although a few promising results were reported in the past, it was recently shown that the use of conventional transfer learning algorithms does not increase performance if proper hyperparameter optimization is performed on the standard approach that does not exploit transfer learning. The objective of this paper is to introduce novel analyses on this topic by using a random forest classifier without hyperparameter optimization and to extend them with experiments performed on data recorded from the same patient, but in different data acquisition sessions. Two domain adaptation techniques were tested on the random forest classifier, allowing us to conduct experiments on healthy subjects and amputees. Differently from several previous papers, our results show that there are no appreciable improvements in terms of accuracy, regardless of the transfer learning techniques tested. The lack of adaptive learning is also demonstrated for the first time in an intra-subject experimental setting when using as a source ten data acquisitions recorded from the same subject but on five different days.

Computational design and optimization of electro-physiological sensors

Electro-physiological sensing devices are becoming increasingly common in diverse applications. However, designing such sensors in compact form factors and for high-quality signal acquisition is a challenging task even for experts, is typically done using heuristics, and requires extensive training. Our work proposes a computational approach for designing multi-modal electro-physiological sensors. By employing an optimization-based approach alongside an integrated predictive model for multiple modalities, compact sensors can be created which offer an optimal trade-off between high signal quality and small device size. The task is assisted by a graphical tool that allows to easily specify design preferences and to visually analyze the generated designs in real-time, enabling designer-in-the-loop optimization. Experimental results show high quantitative agreement between the prediction of the optimizer and experimentally collected physiological data. They demonstrate that generated designs can achieve an optimal balance between the size of the sensor and its signal acquisition capability, outperforming expert generated solutions.

Though skin-conformable electro-physiological sensors are attractive for epidermal electronics, their optimal design remains a challenge. Here, the authors report a computational design approach for realizing multi-modal electro-physiological sensors that optimizes electrode layout design.

Flexible Dry Electrodes for EMG Acquisition within Lower Extremity Prosthetic Sockets

Acquisition of surface electromyography (sEMG) from a person with an amputated lower extremity (LE) during prosthesis-assisted walking remains a significant challenge due to the dynamic nature of the gait cycle. Current solutions to sEMG-based neural control of active LE prostheses involve a combination of customized electrodes, prosthetic sockets, and liners. These technologies are generally: (i) incompatible with a subject's existing prosthetic socket and liners; (ii) uncomfortable to use; and (iii) expensive. This paper presents a flexible dry electrode design for sEMG acquisition within LE prosthetic sockets which seeks to address these issues. Design criteria and corresponding design decisions are explained and a proposed flexible electrode prototype is presented. Performances of the proposed electrode and commercial Ag/AgCl electrodes are compared in seated subjects without amputations. Quantitative analyses suggest comparable signal qualities for the proposed novel electrode and commercial electrodes. The proposed electrode is demonstrated in a subject with a unilateral transtibial amputation wearing her own liner, socket, and the portable sEMG processing platform in a preliminary standing and level ground walking study. Qualitative analyses suggest the feasibility of real-time sEMG data collection from load-bearing, ambulatory subjects.

Acquisition of Surface EMG Using Flexible and Low-Profile Electrodes for Lower Extremity Neuroprosthetic Control

For persons with lower extremity (LE) amputation, acquisition of surface electromyography (sEMG) from within the prosthetic socket remains a significant challenge due to the dynamic loads experienced during the gait cycle. However, these signals are critical for both understanding the clinical effects of LE amputation and determining the desired control trajectories of active LE prostheses. Current solutions for collecting within-socket sEMG are generally (i) incompatible with a subject's prescribed prosthetic socket and liners, (ii) uncomfortable, and (iii) expensive. This study presents an alternative within-socket sEMG acquisition paradigm using a novel flexible and low-profile electrode. First, the practical performance of this Sub-Liner Interface for Prosthetics (SLIP) electrode is compared to that of commercial Ag/AgCl electrodes within a cohort of subjects without amputation. Then, the corresponding SLIP electrode sEMG acquisition paradigm is implemented in a single subject with unilateral transtibial amputation performing unconstrained movements and walking on level ground. Finally, a quantitative questionnaire characterizes subjective comfort for SLIP electrode and commercial Ag/AgCl electrode instrumentation setups. Quantitative analyses suggest comparable signal qualities between SLIP and Ag/AgCl electrodes while qualitative analyses suggest the feasibility of using the SLIP electrode for real-time sEMG data collection from load-bearing, ambulatory subjects with LE amputation.

The Need to Work Arm in Arm: Calling for Collaboration in Delivering Neuroprosthetic Limb Replacements

Over the last few decades there has been a push to enhance the use of advanced prosthetics within the fields of biomedical engineering, neuroscience, and surgery. Through the development of peripheral neural interfaces and invasive electrodes, an individual's own nervous system can be used to control a prosthesis. With novel improvements in neural recording and signal decoding, this intimate communication has paved the way for bidirectional and intuitive control of prostheses. While various collaborations between engineers and surgeons have led to considerable success with motor control and pain management, it has been significantly more challenging to restore sensation. Many of the existing peripheral neural interfaces have demonstrated success in one of these modalities; however, none are currently able to fully restore limb function. Though this is in part due to the complexity of the human somatosensory system and stability of bioelectronics, the fragmentary and as-yet uncoordinated nature of the neuroprosthetic industry further complicates this advancement. In this review, we provide a comprehensive overview of the current field of neuroprosthetics and explore potential strategies to address its unique challenges. These include exploration of electrodes, surgical techniques, control methods, and prosthetic technology. Additionally, we propose a new approach to optimizing prosthetic limb function and facilitating clinical application by capitalizing on available resources. It is incumbent upon academia and industry to encourage collaboration and utilization of different peripheral neural interfaces in combination with each other to create versatile limbs that not only improve function but quality of life. Despite the rapidly evolving technology, if the field continues to work in divided "silos," we will delay achieving the critical, valuable outcome: creating a prosthetic limb that is right for the patient and positively affects their life.

Intramuscular EMG-Driven Musculoskeletal Modelling: Towards Implanted Muscle Interfacing in Spinal Cord Injury Patients

OBJECTIVE

Surface EMG-driven modelling has been proposed as a means to control assistive devices by estimating joint torques. Implanted EMG sensors have several advantages over wearable sensors but provide a more localized information on muscle activity, which may impact torque estimates. Here, we tested and compared the use of surface and intramuscular EMG measurements for the estimation of required assistive joint torques using EMG driven modelling.

METHODS

Four healthy subjects and three incomplete spinal cord injury (SCI) patients performed walking trials at varying speeds. Motion capture marker trajectories, surface and intramuscular EMG, and ground reaction forces were measured concurrently. Subject-specific musculoskeletal models were developed for all subjects, and inverse dynamics analysis was performed for all individual trials. EMG-driven modelling based joint torque estimates were obtained from surface and intramuscular EMG.

RESULTS

The correlation between the experimental and predicted joint torques was similar when using intramuscular or surface EMG as input to the EMG-driven modelling estimator in both healthy individuals and patients.

CONCLUSION

We have provided the first comparison of non-invasive and implanted EMG sensors as input signals for torque estimates in healthy individuals and SCI patients.

SIGNIFICANCE

Implanted EMG sensors have the potential to be used as a reliable input for assistive exoskeleton joint torque actuation.

Force-Invariant Improved Feature Extraction Method for Upper-Limb Prostheses of Transradial Amputees

A force-invariant feature extraction method derives identical information for all force levels. However, the physiology of muscles makes it hard to extract this unique information. In this context, we propose an improved force-invariant feature extraction method based on nonlinear transformation of the power spectral moments, changes in amplitude, and the signal amplitude along with spatial correlation coefficients between channels. Nonlinear transformation balances the forces and increases the margin among the gestures. Additionally, the correlation coefficient between channels evaluates the amount of spatial correlation; however, it does not evaluate the strength of the electromyogram signal. To evaluate the robustness of the proposed method, we use the electromyogram dataset containing nine transradial amputees. In this study, the performance is evaluated using three classifiers with six existing feature extraction methods. The proposed feature extraction method yields a higher pattern recognition performance, and significant improvements in accuracy, sensitivity, specificity, precision, and F1 score are found. In addition, the proposed method requires comparatively less computational time and memory, which makes it more robust than other well-known feature extraction methods.

Gesture Recognition Using Surface Electromyography and Deep Learning for Prostheses Hand: State-of-the-Art, Challenges, and Future

Amputation of the upper limb brings heavy burden to amputees, reduces their quality of life, and limits their performance in activities of daily life. The realization of natural control for prosthetic hands is crucial to improving the quality of life of amputees. Surface electromyography (sEMG) signal is one of the most widely used biological signals for the prediction of upper limb motor intention, which is an essential element of the control systems of prosthetic hands. The conversion of sEMG signals into effective control signals often requires a lot of computational power and complex process. Existing commercial prosthetic hands can only provide natural control for very few active degrees of freedom. Deep learning (DL) has performed surprisingly well in the development of intelligent systems in recent years. The significant improvement of hardware equipment and the continuous emergence of large data sets of sEMG have also boosted the DL research in sEMG signal processing. DL can effectively improve the accuracy of sEMG pattern recognition and reduce the influence of interference factors. This paper analyzes the applicability and efficiency of DL in sEMG-based gesture recognition and reviews the key techniques of DL-based sEMG pattern recognition for the prosthetic hand, including signal acquisition, signal preprocessing, feature extraction, classification of patterns, post-processing, and performance evaluation. Finally, the current challenges and future prospects in clinical application of these techniques are outlined and discussed.

A Framework for Optimizing Co-adaptation in Body-Machine Interfaces

The operation of a human-machine interface is increasingly often referred to as a two-learners problem, where both the human and the interface independently adapt their behavior based on shared information to improve joint performance over a specific task. Drawing inspiration from the field of body-machine interfaces, we take a different perspective and propose a framework for studying co-adaptation in scenarios where the evolution of the interface is dependent on the users' behavior and that do not require task goals to be explicitly defined. Our mathematical description of co-adaptation is built upon the assumption that the interface and the user agents co-adapt toward maximizing the interaction efficiency rather than optimizing task performance. This work describes a mathematical framework for body-machine interfaces where a naïve user interacts with an adaptive interface. The interface, modeled as a linear map from a space with high dimension (the user input) to a lower dimensional feedback, acts as an adaptive “tool” whose goal is to minimize transmission loss following an unsupervised learning procedure and has no knowledge of the task being performed by the user. The user is modeled as a non-stationary multivariate Gaussian generative process that produces a sequence of actions that is either statistically independent or correlated. Dependent data is used to model the output of an action selection module concerned with achieving some unknown goal dictated by the task. The framework assumes that in parallel to this explicit objective, the user is implicitly learning a suitable but not necessarily optimal way to interact with the interface. Implicit learning is modeled as use-dependent learning modulated by a reward-based mechanism acting on the generative distribution. Through simulation, the work quantifies how the system evolves as a function of the learning time scales when a user learns to operate a static vs. an adaptive interface. We show that this novel framework can be directly exploited to readily simulate a variety of interaction scenarios, to facilitate the exploration of the parameters that lead to optimal learning dynamics of the joint system, and to provide an empirical proof for the superiority of human-machine co-adaptation over user adaptation.

Electrode Shifts Estimation and Adaptive Correction for Improving Robustness of sEMG-Based Recognition

In sEMG-based recognition systems, accuracy is severely worsened by disturbances, such as electrode shifts by doffing/donning. Traditional recognition models are fixed or static, with limited abilities to work in the presence of the disturbances. In this paper, a transfer learning method is proposed to reduce the impact of electrode shifts. In the proposed method, a novel activation angle is introduced to locate electrodes within a polar coordinate system. An adaptive transformation is utilized to correct electrode-shifted sEMG samples. The transformation is based on estimated shifts relative to the initial position. The experiments acquisition data from ten subjects consist of sEMG signals under eight gestures in seven or nine arbitrary positions, and recorded shifts from a 3D-printed annular ruler. In our extensive experiments, the errors between recorded shifts (as the reference) and estimated shifts is about -0.017±0.13 radians. Eight gestures recognition results have shown an average accuracy around 79.32%, which represents a significant improvement over the 35.72% ( ) average accuracy of results obtained using nonadaptive models, and 60.99% ( ) results of the other method iGLCM (an improved gray-level co-occurrence matrix). More importantly, by only using one-label samples, the proposed method updates the pre-trained model in an initial position. As a result, the pre-trained model can be adaptively corrected to recognize eight-label gestures in arbitrarily rotary positions. It is proven a highly efficient way to relieve subjects' re-training burden of sEMG-based rehabilitation systems.

Adaptive Electrode Calibration Method Based on Muscle Core Activation Regions and Its Application in Myoelectric Pattern Recognition

To reduce the bad effect of electrode shifts on myoelectric pattern recognition, this paper presents an adaptive electrode calibration method based on core activation regions of muscles. In the proposed method, the high-density surface electromyography (HD-sEMG) matrix collected during hand gesture execution is decomposed into source signal matrix and mixed coefficient matrix by fast independent component analysis algorithm firstly. The mixed coefficient vector whose source signal has the largest two-norm energy is selected as the major pattern, and core activation region of muscles is extracted by traversing the major pattern periodically using a sliding window. The electrode calibration is realized by aligning the core activation regions in unsupervised way. Gestural HD-sEMG data collection experiments with known and unknown electrode shifts are carried out on 9 gestures and 11 participants. A CNN+LSTM-based network is constructed and two network training strategies are adopted for the recognition task. The experimental results demonstrate the effectiveness of the proposed method in mitigating the bad effect of electrode shifts on gesture recognition accuracy and the potentials in reducing user training burden of myoelectric control systems. With the proposed electrode calibration method, the overall gesture recognition accuracies increase about (5.72~7.69)%. In specific, the average recognition accuracy increases (13.32~17.30)% when using only one batch of data in data diversity strategy, and increases (12.01~13.75)% when using only one repetition of each gesture in model update strategy. The proposed electrode calibration algorithm can be extended and applied to improve the robustness of myoelectric control system.

Learning regularized representations of categorically labelled surface EMG enables simultaneous and proportional myoelectric control

Background

Processing the surface electromyogram (sEMG) to decode movement intent is a promising approach for natural control of upper extremity prostheses. To this end, this paper introduces and evaluates a new framework which allows for simultaneous and proportional myoelectric control over multiple degrees of freedom (DoFs) in real-time. The framework uses multitask neural networks and domain-informed regularization in order to automatically find nonlinear mappings from the forearm sEMG envelope to multivariate and continuous encodings of concurrent hand- and wrist kinematics, despite only requiring categorical movement instruction stimuli signals for calibration.

Methods

Forearm sEMG with 8 channels was collected from healthy human subjects (N = 20) and used to calibrate two myoelectric control interfaces, each with two output DoFs. The interfaces were built from (I) the proposed framework, termed Myoelectric Representation Learning (MRL), and, to allow for comparisons, from (II) a standard pattern recognition framework based on Linear Discriminant Analysis (LDA). The online performances of both interfaces were assessed with a Fitts’s law type test generating 5 quantitative performance metrics. The temporal stabilities of the interfaces were evaluated by conducting identical tests without recalibration 7 days after the initial experiment session.

Results

Metric-wise two-way repeated measures ANOVA with factors method (MRL vs LDA) and session (day 1 vs day 7) revealed a significant (\documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$p<0.05$$\end{document}p<0.05) advantage for MRL over LDA in 5 out of 5 performance metrics, with metric-wise effect sizes (Cohen’s \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$d$$\end{document}d) separating MRL from LDA ranging from \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\left|d\right|=0.62$$\end{document}d=0.62 to \documentclass[12pt]{minimal} \usepackage{amsmath} \usepackage{wasysym} \usepackage{amsfonts} \usepackage{amssymb} \usepackage{amsbsy} \usepackage{mathrsfs} \usepackage{upgreek} \setlength{\oddsidemargin}{-69pt} \begin{document}$$\left|d\right|=1.13$$\end{document}d=1.13. No significant effect on any metric was detected for neither session nor interaction between method and session, indicating that none of the methods deteriorated significantly in control efficacy during one week of intermission.

Conclusions

The results suggest that MRL is able to successfully generate stable mappings from EMG to kinematics, thereby enabling myoelectric control with real-time performance superior to that of the current commercial standard for pattern recognition (as represented by LDA). It is thus postulated that the presented MRL approach can be of practical utility for muscle-computer interfaces.

A novel energy-motion model for continuous sEMG decoding: from muscle energy to motor pattern

At present, sEMG-based gesture recognition requires vast amounts of training data; otherwise it is limited to a few gestures. Objective. This paper presents a novel dynamic energy model that decodes continuous hand actions by training small amounts of sEMG data. Approach. The activation of forearm muscles can set the corresponding fingers in motion or state with movement trends. The moving fingers store kinetic energy, and the fingers with movement trends store potential energy. The kinetic energy and potential energy in each finger are dynamically allocated due to the adaptive-coupling mechanism of five-fingers in actual motion. Meanwhile, the sum of the two energies remains constant at a certain muscle activation. We regarded hand movements with the same direction of acceleration for five-finger as the same in energy mode and divided hand movements into ten energy modes. Independent component analysis and machine learning methods were used to model associations between sEMG signals and energy modes and expressed gestures by energy form adaptively. This theory imitates the self-adapting mechanism in actual tasks. Thus, ten healthy subjects were recruited, and three experiments mimicking activities of daily living were designed to evaluate the interface: (1) the expression of untrained gestures, (2) the decoding of the amount of single-finger energy, and (3) real-time control. Main results. (1) Participants completed the untrained hand movements (100/100, p < 0.0001). (2) The interface performed better than chance in the experiment where participants pricked balloons with a needle tip (779/1000, p < 0.0001). (3) In the experiment where participants punched a hole in the plasticine on the balloon, the success rate was over 95% (97.67 ± 5.04%, p < 0.01). Significance. The model can achieve continuous hand actions with speed or force information by training small amounts of sEMG data, which reduces learning task complexity.

Improved High-Density Myoelectric Pattern Recognition Control Against Electrode Shift Using Data Augmentation and Dilated Convolutional Neural Network

OBJECTIVE

the objective of this work is to develop a robust method for myoelectric control towards alleviating the interference of electrode shift. M ethods: In the proposed method, a preprocessing approach was first performed to convert high-density surface electromyogram (HD-sEMG) signals into a series of images, and the electrode shift appeared as pixel shift in these images. Next, a data augmentation approach was applied to the training data from just one position (no shift), so as to simulate HD-sEMG images derived from fictitious shift positions. The dilated convolutional neural network (DCNN) was subsequently adopted for classification. Compared to common convolutional neural network, DCNN always contained a larger receptive field that was supposed to be adept at mining wider spatial contextual information in images. This property was further confirmed to facilitate the classification of myoelectric patterns using HD-sEMG. The performance of the proposed method was evaluated with HD-sEMG data recorded by a 10×10 electrode array placed over forearm extensors of ten subjects during their performance of six wrist and finger extension tasks.

RESULTS

Under a variety of actual electrode shift conditions, the proposed method achieved a mean classification accuracy of 95.34%, and it outperformed other common methods.

CONCLUSION

This work demonstrated feasibility and usability of combining data augmentation and DCNN in predicting myoelectric patterns in the context of electrode shifts.

SIGNIFICANCE

The proposed method is a practical solution for robust myoelectric control against electrode array shifts.

Position Identification for Robust Myoelectric Control Against Electrode Shift

The vulnerability to the electrode shift was one of the key barriers to the wide application of pattern recognition-based (PR-based) myoelectric control systems outside the controlled laboratory conditions. To overcome this challenge, a novel framework named position identification (PI) was proposed. In the PI framework, an anchor gesture performed by the user was first analyzed to identify the current electrode position from a pool of potential electrode shift positions. Next, the classifier calibrated by the data of the identified position would be selected for following myoelectric control tasks. The results of the amputee and able-bodied participants both demonstrated that the differential filter combined with majority voting improved the PI accuracy. With only one second contraction of the chosen anchor gesture (hand close), the subsequent PR-based myoelectric control performance was fully restored from eight different electrode shift scenarios, with 1 cm in either or both perpendicular and parallel directions. The classification accuracies with PI framework were not significant before and after the shift ( 0.001). The advantage of restoring performance fully in just one second made it a practical solution to improve the robustness of PR-based myoelectric control systems in a wide range of real-world applications.

Improve Inter-day Hand Gesture Recognition Via Convolutional Neural Network-based Feature Fusion

The learning of inter-day representation of electromyographic (EMG) signals across multiple days remains a challenging topic and not fully accommodated yet. This study aims to improve the inter-day hand motion classification accuracy via convolutional neural network (CNN)-based data feature fusion. An EMG database (ISRMyo-I) was recorded from six subjects on 10 days via a low density electrode setting. This study investigated CNNs’ capability of feature learning, and found that the output of the first fully connected layer (CNNFeats) was a decent supplement feature set to the most prevalent Hudgins’ time domain features in combination with fourth-order autoregressive coefficients (TDAR). Through adding the automatically learned CNNFeats to the handcrafted TDAR feature set, both linear discriminant analysis (LDA) and support vector machine (SVM) classifiers received [Formula: see text]3% accuracy improvement. Similarly, taking TDAR as additional input to the CNN improved the accuracy by [Formula: see text]1% in the comparison with the basic CNN. Our results also demonstrated that the CNN approach outperformed conventional approaches when multiple subjects’ data were available for training, while traditional approaches were more adept at presenting motion patterns for single subject. A preliminary conclusion is drawn that substantial “common knowledge/features” can be learned by CNNs from the raw EMG signals across multiple days and multiple subjects, and thus it is believed that a pre-trained CNN model would contribute to higher accuracy as well as the reduction of learning burden.

Arduino-Based Myoelectric Control: Towards Longitudinal Study of Prosthesis Use

Understanding how upper-limb prostheses are used in daily life helps to improve the design and robustness of prosthesis control algorithms and prosthetic components. However, only a very small fraction of published research includes prosthesis use in community settings. The cost, limited battery life, and poor generalisation may be the main reasons limiting the implementation of home-based applications. In this work, we introduce the design of a cost-effective Arduino-based myoelectric control system with wearable electromyogram (EMG) sensors. The design considerations focused on home studies, so the robustness, user-friendly control adjustments, and user supports were the main concerns. Three control algorithms, namely, direct control, abstract control, and linear discriminant analysis (LDA) classification, were implemented in the system. In this paper, we will share our design principles and report the robustness of the system in continuous operation in the laboratory. In addition, we will show a first real-time implementation of the abstract decoder for prosthesis control with an able-bodied participant.

Simultaneous control of multiple functions of bionic hand prostheses: Performance and robustness in end users

Myoelectric hand prostheses are usually controlled with two bipolar electrodes located on the flexor and extensor muscles of the residual limb. With clinically established techniques, only one function can be controlled at a time. This is cumbersome and limits the benefit of additional functions offered by modern prostheses. Extensive research has been conducted on more advanced control techniques, but the clinical impact has been limited, mainly due to the lack of reliability in real-world conditions. We implemented a regression-based control approach that allows for simultaneous and proportional control of two degrees of freedom and evaluated it on five prosthetic end users. In the evaluation of tasks mimicking daily life activities, we included factors that limit reliability, such as tests in different arm positions and on different days. The regression approach was robust over multiple days and only slightly affected by changing in the arm position. Additionally, the regression approach outperformed two clinical control approaches in most conditions.

Exploring the Relationship Between EMG Feature Space Characteristics and Control Performance in Machine Learning Myoelectric Control

In myoelectric machine learning (ML) based control, it has been demonstrated that control performance usually increases with training, but it remains largely unknown which underlying factors govern these improvements. It has been suggested that the increase in performance originates from changes in characteristics of the Electromyography (EMG) patterns, such as separability or repeatability. However, the relation between these EMG metrics and control performance has hardly been studied. We assessed the relation between three common EMG feature space metrics (separability, variability and repeatability) in 20 able bodied participants who learned ML myoelectric control in a virtual task over 15 training blocks on 5 days. We assessed the change in offline and real-time performance, as well as the change of each EMG metric over the training. Subsequently, we assessed the relation between individual EMG metrics and offline and real-time performance via correlation analysis. Last, we tried to predict real-time performance from all EMG metrics via L2-regularized linear regression. Results showed that real-time performance improved with training, but there was no change in offline performance or in any of the EMG metrics. Furthermore, we only found a very low correlation between separability and real-time performance and no correlation between any other EMG metric and real-time performance. Finally, real-time performance could not be successfully predicted from all EMG metrics employing L2-regularized linear regression. We concluded that the three EMG metrics and real-time performance appear to be unrelated.