EMG Signals Research Articles

Continuous reach-to-grasp motion recognition based on an extreme learning machine algorithm using sEMG signals.

Recognizing user intention in reach-to-grasp motions is a critical challenge in rehabilitation engineering. To address this, a Machine Learning (ML) algorithm based on the Extreme Learning Machine (ELM) was developed for identifying motor actions using surface Electromyography (sEMG) during continuous reach-to-grasp movements, involving multiple Degrees of Freedom(DoFs). This study explores feature extraction methods based on time domain and autoregressive models to evaluate ELM performance under different conditions. The experimental setup encompassed variations in neuron size, time windows, validation with each muscle, increase in the number of features, comparison with five conventional ML-based classifiers, inter-subjects variability, and temporal dynamic response. To evaluate the efficacy of the proposed ELM-based method, an openly available sEMG dataset containing data from 12 participants was used. Results highlight the method's performance, achieving Accuracy above 85%, F-score above 90%, Recall above 85%, Area Under the Curve of approximately 84% and compilation times (computational cost) of less than 1ms. These metrics significantly outperform standard methods (p < 0.05). Additionally, specific trends were found in increasing and decreasing performance in identifying specific tasks, as well as variations in the continuous transitions in the temporal dynamics response. Thus, the ELM-based method effectively identifies continuous reach-to-grasp motions through myoelectric data. These findings hold promise for practical applications. The method's success prompts future research into implementing it for more reliable and effective Human-Machine Interface (HMI) control. This can revolutionize real-time upper limb rehabilitation, enabling natural and complex Activities of Daily Living (ADLs) like object manipulation. The robust results encourages further research and innovative solutions to improve people's quality of life through more effective interventions.

Get ready! High urgency reduces beta band cortico-muscular coherence during motor preparation

Motor preparation is a dynamic process that is tuned to task demands such as urgency. This study examined the effect of urgency to move on cortico-muscular coherence (CMC) in the beta frequency band during motor preparation. Participants (n = 25) prepared for a rapid wrist flexion movement under two distinct scenarios: high (350 ms to prepare) and low (1400 ms to prepare) urgency. Before participants performed the ballistic actions, they were required to hold a light contraction of the flexor carpi radialis muscle for 3 s. During this holding time, we simultaneously obtained EEG and EMG signals to estimate their coherence —a measure of how much brain and muscle activity is synchronized at specific rhythms— over the last 1 s of the contraction interval.Contrary to our hypothesis, we found greater CMC in conditions of low urgency rather than high urgency. This finding suggests that participants prioritized attending to the visual stimuli, dividing their attention to capture the preparation go-signal, rather than preparing the motor system, leading to a reduction in CMC. This interpretation suggests a cognitive-motor trade-off, wherein attentional resources are allocated more to sensory processing that to motor preparedness in urgent situations.

Knee Angle Estimation from Surface EMG during Walking Using Attention-Based Deep Recurrent Neural Networks: Feasibility and Initial Demonstration in Cerebral Palsy.

Accurately estimating knee joint angle during walking from surface electromyography (sEMG) signals can enable more natural control of wearable robotics like exoskeletons. However, challenges exist due to variability across individuals and sessions. This study evaluates an attention-based deep recurrent neural network combining gated recurrent units (GRUs) and an attention mechanism (AM) for knee angle estimation. Three experiments were conducted. First, the GRU-AM model was tested on four healthy adolescents, demonstrating improved estimation compared to GRU alone. A sensitivity analysis revealed that the key contributing muscles were the knee flexor and extensors, highlighting the ability of the AM to focus on the most salient inputs. Second, transfer learning was shown by pretraining the model on an open source dataset before additional training and testing on the four adolescents. Third, the model was progressively adapted over three sessions for one child with cerebral palsy (CP). The GRU-AM model demonstrated robust knee angle estimation across participants with healthy participants (mean RMSE 7 degrees) and participants with CP (RMSE 37 degrees). Further, estimation accuracy improved by 14 degrees on average across successive sessions of walking in the child with CP. These results demonstrate the feasibility of using attention-based deep networks for joint angle estimation in adolescents and clinical populations and support their further development for deployment in wearable robotics.

An Embedded Electromyogram Signal Acquisition Device.

In this study, we design an embedded surface EMG acquisition device to conveniently collect human surface EMG signals, pursue more intelligent human-computer interactions in exoskeleton robots, and enable exoskeleton robots to synchronize with or even respond to user actions in advance. The device has the characteristics of low cost, miniaturization, and strong compatibility, and it can acquire eight-channel surface EMG signals in real time while retaining the possibility of expanding the channel. This paper introduces the design and function of the embedded EMG acquisition device in detail, which includes the use of wired transmission to adapt to complex electromagnetic environments, light signals to indicate signal strength, and an embedded processing chip to reduce signal noise and perform filtering. The test results show that the device can effectively collect the original EMG signal, which provides a scheme for improving the level of human-computer interactions and enhancing the robustness and intelligence of exoskeleton equipment. The development of this device provides a new possibility for the intellectualization of exoskeleton systems and reductions in their cost.

A High-Performance, Secure Custom Electronics Circuit for Biopotential Measurement and Processing

Purpose: In this paper, we propose a secure wearable and portable device aiming to (i) monitor physical activity in medical and clinical rehabilitation, (ii) evaluate the subject's movements in sports environments, and (iii) monitor wellness indicators. Materials and Methods: The innovative low-power custom circuit can acquire, pre-process, digitalize, and transmit EMG signals to a Raspberry PI4 device via a low-energy Bluetooth module. The Raspberry PI4 is a hub that sends data to a cloud-based system for remote monitoring and processing. The best cybersecurity practices have been implemented: firewall, anti-DDoS and SELinux. Results: We have assessed the system's vulnerability before and after the system's hardening. SELinux makes the system safer and prevents unauthorized access to patients' data health by tampering with the devices. Conclusion: Adopting IoT systems in telemedicine requires greater attention to cybersecurity. It is necessary to implement security mechanisms to guarantee the privacy of patient's health data.

Hand Gesture Recognition Based on High-Density Myoelectricity in Forearm Flexors in Humans.

Electromyography-based gesture recognition has become a challenging problem in the decoding of fine hand movements. Recent research has focused on improving the accuracy of gesture recognition by increasing the complexity of network models. However, training a complex model necessitates a significant amount of data, thereby escalating both user burden and computational costs. Moreover, owing to the considerable variability of surface electromyography (sEMG) signals across different users, conventional machine learning approaches reliant on a single feature fail to meet the demand for precise gesture recognition tailored to individual users. Therefore, to solve the problems of large computational cost and poor cross-user pattern recognition performance, we propose a feature selection method that combines mutual information, principal component analysis and the Pearson correlation coefficient (MPP). This method can filter out the optimal subset of features that match a specific user while combining with an SVM classifier to accurately and efficiently recognize the user's gesture movements. To validate the effectiveness of the above method, we designed an experiment including five gesture actions. The experimental results show that compared to the classification accuracy obtained using a single feature, we achieved an improvement of about 5% with the optimally selected feature as the input to any of the classifiers. This study provides an effective guarantee for user-specific fine hand movement decoding based on sEMG signals.

Unraveling cEMG-wet sEMG Correlation Dynamics: Investigating Influential Factors

The electromyography (EMG) signal provides insight into neuromuscular activity which is used in medical and technological fields. Traditional needle electrodes and surface electrodes have several drawbacks making them less suitable for portable and long-term use. In contrast, emerging capacitive electrodes offer promising features over the existing electrodes. Yet, the full potential of capacitive electrodes remains untapped due to the lack of comprehensive design optimization for consistently reliable signal quality. This study highlights the complex interplay of factors influencing correlation in capacitive EMG (cEMG) and wet surface EMG (wet sEMG) signals. The study emphasizes the importance of the surface area of capacitive electrodes, muscle force, preprocessing, and sampling frequency in understanding and improving the correlation between cEMG and wet sEMG signals, providing valuable insights for future research and applications in the field. The study reveals that the electrode area has no significant effect on the correlation. However, the correlation significantly depends on the muscle force. In addition, removing artifacts from the cEMG signal increases the correlation, especially for lower force where artifacts are significant. Again, oversampling the EMG signal above 800 Hz does not have any impact on increasing the correlation but the correlation decreases with higher inter-electrode distance (IED). In this research, the highest correlation of 82.89% (normalized-91.62%) between cEMG and sEMG has been achieved for high muscle force with a plate area of 4 cm2. Therefore, the capacitive electrode can be an alternative for EMG signal acquisition.

A Surface Electromyography (sEMG) System Applied for Grip Force Monitoring.

Muscles play an indispensable role in human life. Surface electromyography (sEMG), as a non-invasive method, is crucial for monitoring muscle status. It is characterized by its real-time, portable nature and is extensively utilized in sports and rehabilitation sciences. This study proposed a wireless acquisition system based on multi-channel sEMG for objective monitoring of grip force. The system consists of an sEMG acquisition module containing four-channel discrete terminals and a host computer receiver module, using Bluetooth wireless transmission. The system is portable, wearable, low-cost, and easy to operate. Leveraging the system, an experiment for grip force prediction was designed, employing the bald eagle search (BES) algorithm to enhance the Random Forest (RF) algorithm. This approach established a grip force prediction model based on dual-channel sEMG signals. As tested, the performance of acquisition terminal proceeded as follows: the gain was up to 1125 times, and the common mode rejection ratio (CMRR) remained high in the sEMG signal band range (96.94 dB (100 Hz), 84.12 dB (500 Hz)), while the performance of the grip force prediction algorithm had an R2 of 0.9215, an MAE of 1.0637, and an MSE of 1.7479. The proposed system demonstrates excellent performance in real-time signal acquisition and grip force prediction, proving to be an effective muscle status monitoring tool for rehabilitation, training, disease condition surveillance and scientific fitness applications.

Dual Stream Long Short-Term Memory Feature Fusion Classifier for Surface Electromyography Gesture Recognition.

Gesture recognition using electromyography (EMG) signals has prevailed recently in the field of human-computer interactions for controlling intelligent prosthetics. Currently, machine learning and deep learning are the two most commonly employed methods for classifying hand gestures. Despite traditional machine learning methods already achieving impressive performance, it is still a huge amount of work to carry out feature extraction manually. The existing deep learning methods utilize complex neural network architectures to achieve higher accuracy, which will suffer from overfitting, insufficient adaptability, and low recognition accuracy. To improve the existing phenomenon, a novel lightweight model named dual stream LSTM feature fusion classifier is proposed based on the concatenation of five time-domain features of EMG signals and raw data, which are both processed with one-dimensional convolutional neural networks and LSTM layers to carry out the classification. The proposed method can effectively capture global features of EMG signals using a simple architecture, which means less computational cost. An experiment is conducted on a public DB1 dataset with 52 gestures, and each of the 27 subjects repeats every gesture 10 times. The accuracy rate achieved by the model is 89.66%, which is comparable to that achieved by more complex deep learning neural networks, and the inference time for each gesture is 87.6 ms, which can also be implied in a real-time control system. The proposed model is validated using a subject-wise experiment on 10 out of the 40 subjects in the DB2 dataset, achieving a mean accuracy of 91.74%. This is illustrated by its ability to fuse time-domain features and raw data to extract more effective information from the sEMG signal and select an appropriate, efficient, lightweight network to enhance the recognition results.

Effective features extraction and selection for hand gesture recognition using sEMG signal

Effective features extraction and selection for hand gesture recognition using sEMG signal

Topology of surface electromyogram signals: hand gesture decoding on Riemannian manifolds

Objective. Decoding gestures from the upper limb using noninvasive surface electromyogram (sEMG) signals is of keen interest for the rehabilitation of amputees, artificial supernumerary limb augmentation, gestural control of computers, and virtual/augmented realities. We show that sEMG signals recorded across an array of sensor electrodes in multiple spatial locations around the forearm evince a rich geometric pattern of global motor unit (MU) activity that can be leveraged to distinguish different hand gestures. Approach. We demonstrate a simple technique to analyze spatial patterns of muscle MU activity within a temporal window and show that distinct gestures can be classified in both supervised and unsupervised manners. Specifically, we construct symmetric positive definite covariance matrices to represent the spatial distribution of MU activity in a time window of interest, calculated as pairwise covariance of electrical signals measured across different electrodes. Main results. This allows us to understand and manipulate multivariate sEMG timeseries on a more natural subspace—the Riemannian manifold. Furthermore, it directly addresses signal variability across individuals and sessions, which remains a major challenge in the field. sEMG signals measured at a single electrode lack contextual information such as how various anatomical and physiological factors influence the signals and how their combined effect alters the evident interaction among neighboring muscles. Significance. As we show here, analyzing spatial patterns using covariance matrices on Riemannian manifolds allows us to robustly model complex interactions across spatially distributed MUs and provides a flexible and transparent framework to quantify differences in sEMG signals across individuals. The proposed method is novel in the study of sEMG signals and its performance exceeds the current benchmarks while being computationally efficient.

HAND GRASPS RECOGNITION USING SINGLE-CHANNEL TRANSIENT-STATE SURFACE ELECTROMYOGRAPHY

The need to perform large hand-grasping strategies in daily life has promoted the development of robotic hands and prosthetic hands that mimic natural ones. This work presents a system for the detection of 10 basic hand grasps in healthy subjects based on single-channel transient-state Surface Electromyography (sEMG) signals. The studied grasps are large diameter, ring, knife index finger, writing tripod, power sphere, precision sphere, prismatic pinch, lateral, extension type, and parallel extension grasp. Signals were collected from 10 healthy volunteers using three sEMG electrodes connected to an Electromyography (EMG) shield using MATLAB as data acquisition software. The signals were classified using three different classifiers, i.e. [Formula: see text]-Nearest Neighbors ([Formula: see text]-NN), Diagonal Linear Discriminant Analysis (dl-DA), and Random Forest (RF). The used features were mean absolute value, integrated absolute value, variance, root mean square value, waveform length, Willison amplitude, slope sign change, zero crossing, autoregressive coefficients, and mean frequency. The results show that good classification accuracy is achieved when classifying a reduced number of grasps using a single-channel transient-state sEMG. The average accuracy for the different classifiers varied from 41.5% to 53.3% when classifying 10 grasps and from 78.4% to 91.9% when classifying five grasps using two features as a trainer. It is found that transient-state sEMG signals are efficient in the detection of different hand grasps, reducing the time to generate control signals and the number of channels.

An Approach for Evaluation and Recognition of Facial Emotions Using EMG Signal

Background: Facial electromyography (fEMG) records muscular activities from the facial muscles, which provides details regarding facial muscle stimulation patterns in experimentation. Objectives: The Principal Component Analysis (PCA) is mostly implemented, whereas the actual or unprocessed initial fEMG data are rendered into low-spatial units with minimizing the level of data repetition. Methods: Facial EMG signal was acquired by using the instrument BIOPAC MP150. Four electrodes were fixed on the face of each participant for capturing the four different emotions like happiness, anger, sad and fear. Two electrodes were placed on arm for grounding purposes. Results: The aim of this research paper is to propagate the functioning of PCA in synchrony with the subjective fEMG analysis and to give a thorough apprehension of the advanced PCA in the areas of machine learning. It describes its arithmetical characteristics, while PCA is estimated by implying the covariance matrix. Datasets which are larger in size are progressively universal and their interpretation often becomes complex or tough. So, it is necessary to minimize the number of variables and elucidate linear compositions of the data to explicate it on a huge number of variables with a relevant approach. Therefore, Principal Component Analysis (PCA) is applied because it is an unsupervised training method that utilizes advanced statistical concept to minimize the dimensionality of huge datasets. Conclusion: This work is furthermore inclined toward the analysis of fEMG signals acquired for four different facial expressions using Analysis of Variance (ANOVA) to provide clarity on the variation of features.

Potato peels-based electrodes for recording ECG and EMG signals

Reliable measurement and acquisition of physiological parameters is among critical tasks in human health monitoring. While the presence of personalized measurement of Electrocardiography (ECG) and Electromyography (EMG) devices enables more frequent data collection, and consequently better health monitoring, it also leads to higher consumption of electrodes. On the other hand, commonly used Ag/AgCl electrodes are not free of charge or biodegradable. Therefore, their extensive use leads to higher costs and higher waste production. In this paper, we present an approach for the development of ECG/EMG electrodes that are based on biodegradable materials (two potato types). We performed successful integration of potato peel-based electrodes with the commercial device as well as with our in-house developed portable system. Measurements on 8 healthy volunteers revealed very small differences when heart rate, inter-beat-interval or normal-to-normal intervals are extracted from the ECG signal with potato peel-based and commercial Ag/AgCl electrodes. Our study demonstrates the feasibility of utilizing biodegradable potato peel-based electrodes for ECG and EMG measurements, showcasing their comparable performance to traditional Ag/AgCl electrodes in capturing physiological parameters. We introduced biodegradable electrodes as a viable and eco-friendly alternative for accurate ECG and EMG measurements, addressing the issues of electrode waste and cost associated with conventional electrodes.

Highly stretchable six-leaf hand structure electrodes prepared by sacrificial layer method, resistant to sweat erosion, for EMG and ECG signal detection

Recently, wearable flexible electronic devices have become more widely used in detecting human physiological signals, so higher demands have been placed on flexible stretchable electrodes directly attached to the human body, which need to have better mechanical tensile properties, anti-fatigue properties, and chemical stability. In this paper, the four-segment hand structure is optimized to obtain the four-leaf hand structure, which reduces the maximum stress value when the electrode is stretched and decreases the probability of electrode fracture. Further, the structure of the electrode is optimized by changing the number of nodes, the six-leaf hand structure electrode is obtained. The six-leaf hand structure electrode has lower tensile stress and stability. The substrate-free six-leaf hand structure electrode prepared by the sacrificial layer method has a much higher stretchability than the electrode with a substrate layer due to the bonding of the substrate-free layer, and there is no significant change in the resistance value during the stretching process. The screen-printed waterproof-coated six-leaf hand structure electrode has good sweat resistance and can be used for ECG and EMG detection.

Artificial Neural Network Accuracy Optimization Using Transfer Function Methods on Various Human Gait Walking Environments

A bionic leg with ergonomic functionality can increase the user’s independence. However, an ergonomic bionic leg can be challenged to be developed. One of its challenges is related to functionality, where the bionic leg motor can be rugged to adapt to the user. One of the solutions for the bionic leg challenge is the application of a motor driver controlled by the user’s muscle signal. EMG signal can be utilized as the user’s signal source. The EMG signal is then fed back into the motor device. EMG signals obtained during a natural walking environment can result in smooth and natural movement. This study classifies EMG signals into 8 classes: a controlled walking environment (treadmill walking with various speeds) and a natural walking environment (ground walking, upstairs and downstairs walking). This research aims to optimize the ANN method using transfer function variations. The best method will be used to train EMG-driven motors for future studies related to bionic legs. The best ANN parameter in this research using Levenberg-Marquardt backpropagation as a training algorithm with transfer function pairing of the exponential function: Hyperbolic tangent sigmoid transfer function and SoftMax transfer function with 98.8% accuracy and 0.036 MSE value. The best method from the experiment and ANN classification can be used as a training method for a bionic leg in future research.

A geometric algebra-based approach for myoelectric pattern recognition control and faster prosthesis recalibration

ObjectiveAlthough many advancements have been made on myoelectric pattern-recognition, the control of poly-articulated upper-limb prostheses remains insufficiently robust. Electrode-shift, sweat or fatigue degrade the performance of classifiers over time, resulting in unfruitful device usage and frequent re-calibration. To tackle this issue, here we introduce two models − µP6 and µP8 − that combine Geometric Algebra with nearest-neighbor classification. We aim at reducing both the necessary training data and training time and, unlike most current state-of-the-art algorithms, we exploit an alternative geometric representation (and visualization) of the EMG signal as different polygons for different types of gestures, facilitating the explanation of the decision-making process to a layman. Moreover, we explore four abstention strategies to reduce the number of misclassifications. MethodsWe perform an offline analysis on two datasets, alongside two other standard models: nonlinear logistic regression (NLR) and linear discriminant analysis (LDA). ResultsEven with few training data, the proposed algorithms achieve high F1-scores (>0.95), significantly higher or non-significantly different from the values obtained with NLR and LDA, while maintaining relatively low abstentions rates and training times (<2 ms). ConclusionThe proposed algorithms allow to reduce the amount of training data and training times without compromising recognition rates. SignificanceThe proposed algorithms may contribute for a faster prosthesis re-calibration procedure while allowing to re-gain high recognition rates. Furthermore, the decision-making process is explainable and interpretable, potentially improving user trust and acceptance.

SEMG biceps and triceps effort signals classification using 1D-CNN convolution

In this paper, we present a system for acquiring and classifying surface physiological muscles signals (sEMG) for the biceps and triceps muscles during movement or work, as normal or aggressive effort in order to control and command the aid prostheses to intervene only during aggressive efforts. Thus, the main objective of our work is to developing and improving the performance of the hand prostheses for daily life tasks for elderly persons or for persons who have hand muscle failure. Our contribution consists of detecting and classifying physiological signals of biceps and triceps muscles hand as normal and aggressive efforts, for that we proposed a technique based on a 1D Convolutional Neural Network (CNN-1D) using the Wavelet Scattering Transform as the sEMG feature extraction technique. Our methodology is carried out in two steps: the first step is crucial to build a database for deep learning network for sEMG signals classification based on fifty-five volunteers spanning various ages and genders. The second step achieves the sEMG signals effort classification as normal or aggressive efforts based on the classification network produced based on sEMG signal sequences treated by the WST. The obtained results for the training and validation sets indicate perfect performance of the proposed technique, with an accuracy, precision, sensitivity, and specificity of 100% for the training process, and 99.3%, 98.6%, 100% and 98.7% for the accuracy, precision, sensibility and specificity respectively. It is important to note that while perfect metrics on the training and the test set might suggest excellent model learning.

Soft tissue material properties based on human abdominal in vivo macro-indenter measurements

Simulations of human-technology interaction in the context of product development require comprehensive knowledge of biomechanical in vivo behavior. To obtain this knowledge for the abdomen, we measured the continuous mechanical responses of the abdominal soft tissue of ten healthy participants in different lying positions anteriorly, laterally, and posteriorly under local compression depths of up to 30 mm. An experimental setup consisting of a mechatronic indenter with hemispherical tip and two time-of-flight (ToF) sensors for optical 3D displacement measurement of the surface was developed for this purpose. To account for the impact of muscle tone, experiments were conducted with both controlled activation and relaxation of the trunk muscles. Surface electromyography (sEMG) was used to monitor muscle activation levels. The obtained data sets comprise the continuous force-displacement data of six abdominal measurement regions, each synchronized with the local surface displacements resulting from the macro-indentation, and the bipolar sEMG signals at three key trunk muscles. We used inverse finite element analysis (FEA), to derive sets of nonlinear material parameters that numerically approximate the experimentally determined soft tissue behaviors. The physiological standard values obtained for all participants after data processing served as reference data. The mean stiffness of the abdomen was significantly different when the trunk muscles were activated or relaxed. No significant differences were found between the anterior-lateral measurement regions, with exception of those centered on the linea alba and centered on the muscle belly of the rectus abdominis below the intertubercular plane. The shapes and areas of deformation of the skin depended on the region and muscle activity. Using the hyperelastic Ogden model, we identified unique material parameter sets for all regions. Our findings confirmed that, in addition to the indenter force-displacement data, knowledge about tissue deformation is necessary to reliably determine unique material parameter sets using inverse FEA. The presented results can be used for finite element (FE) models of the abdomen, for example, in the context of orthopedic or biomedical product developments.

Instruction transmission of combat robotic arm based on neck muscles surface electromyography signals

This paper introduces a novel method for instructing wearable robotic arms based on neck movements to enhance user control. By capturing head movements representing four aiming directions and analysing surface electromyography (sEMG) signals from specific muscles, the study employs the random forest algorithm for movement recognition. Results show that utilising sEMG signals from six muscles improve classification accuracy, and applying the variational mode decomposition (VMD) algorithm enhances feature extraction. Notably, right-side muscles, particularly the sternocleidomastoid muscles, significantly impact movement classification. These findings provide theoretical support for better recognition of neck movements.