Electromyography Signals Research Articles

A membership-function-based broad learning system for human-robot interaction force estimation under drawing task.

Estimating interaction force is of great significance in the field of human-robot interaction (HRI) thanks to its guarantee of interaction safety. To this end, this paper proposes a novel estimation method by leveraging broad learning system (BLS) and human surface electromyography (sEMG) signals. Since the previous sEMG may also contain valuable information of human muscle force, it would cause the estimation to be incomplete and abate the estimation accuracy in the case of neglecting the previous sEMG. To remedy this thorn, a new linear membership function is first developed to calculate contributions of sEMG at different sampling times in the proposed method. Subsequently, the contribution values calculated by the membership function are integrated with features of sEMG to be considered as the input layer of BLS. For extensive studies, five different features extracted from sEMG signals and their combination are explored to estimate the interaction force by the proposed method. Lastly, the performance of the proposed method is compared with those of three well-known methods through experimental test regarding the drawing task. The experimental results confirm that combining the time domain (TD) with frequency domain (FD) features of sEMG can enhance the estimation quality. Moreover, the proposed method outperforms its contenders with respect to estimation accuracy.

The effect of individual stress on the signature verification system using muscle synergy

Biometric authentication systems, in terms of using the biometric characteristic, and because these indicators are resistant to the passage of time, and environmental, and physical changes of people, in most different situations from the environment or changes in emotional factors of person, perform identity verification with optimal accuracy. In the signature verification systems, people may experience stress caused by environmental or internal factors when registering a signature, this stress can affect the performance of the signature verification system in terms of accuracy and stability. We try to study the performance of a signature verification system based on a biometric characteristic (muscle synergy patterns) for people who are stressed while signing.For this purpose, electromyography (EMG) signals were recorded from hand and arm muscles of people while signing. Then, using Non-Negative Matrix Factorization (NMF) method to extracted muscle synergies from EMG signals after pre-processing. The extracted synergy patterns are classified into genuine and forgery classes by Support Vector Machine (SVM) classifier. Furthermore, the confirmation of the authentication of stressed people was studied using this method. Finally, the results obtained were compared to the results obtained from the signature verification system for unstressed people and using K-means classifier method.

MCR-ALS-based muscle synergy extraction method combined with LSTM neural network for motion intention detection.

The time-varying and individual variability of surface electromyographic signals (sEMG) can lead to poorer motor intention detection results from different subjects and longer temporal intervals between training and testing datasets. The consistency of using muscle synergy between the same tasks may be beneficial to improve the detection accuracy over long time ranges. However, the conventional muscle synergy extraction methods, such as non-negative matrix factorization (NMF) and principal component analysis (PCA) have some limitations in the field of motor intention detection, especially in the continuous estimation of upper limb joint angles. In this study, we proposed a reliable multivariate curve-resolved-alternating least squares (MCR-ALS) muscle synergy extraction method combined with long-short term memory neural network (LSTM) to estimate continuous elbow joint motion by using the sEMG datasets from different subjects and different days. The pre-processed sEMG signals were then decomposed into muscle synergies by MCR-ALS, NMF and PCA methods, and the decomposed muscle activation matrices were used as sEMG features. The sEMG features and elbow joint angular signals were input to LSTM to establish a neural network model. Finally, the established neural network models were tested by using sEMG dataset from different subjects and different days, and the detection accuracy was measured by correlation coefficient. The detection accuracy of elbow joint angle was more than 85% by using the proposed method. This result was significantly higher than the detection accuracies obtained by using NMF and PCA methods. The results showed that the proposed method can improve the accuracy of motor intention detection results from different subjects and different acquisition timepoints. This study successfully improves the robustness of sEMG signals in neural network applications using an innovative muscle synergy extraction method. It contributes to the application of human physiological signals in human-machine interaction.

A Multiscale Feature Extraction Network Based on Channel-Spatial Attention for Electromyographic Signal Classification

The applications of myoelectrical interfaces are majorly limited by the efficacy of decoding motion intent in electromyographic (EMG) signal. Currently, EMG classification methods often rely substantially on hand-crafted features, or ignore key channel and inter-feature information for classification tasks. To address these issues, a multi-scale feature extraction network (MSFEnet) based on channel-spatial attention is proposed to decode EMG signal for the task of gesture recognition classification. Specifically, we fuse the spatio-temporal characteristics of EMG signal with different scales. Then, we construct the feature channel attention module and the feature spatial attention module to capture more key channels features, and more key spatial features. To evaluate the efficacy of proposed method, extensive experiments are conducted on two public datasets: Ninapro DB2 and CapgMyo DB-a. An average accuracy of 86.21%, 90.77%, 92.53% and 98.85% has been achieved in Exercise B, C, D of Ninapro DB2 and CapgMyo DB-a, respectively. The experimental results demonstrate that MSFEnet is more capable of extracting temporal and spatial fused features. It performs well in generalization and has higher classification accuracy compared with the state-of-the-art methods.

P28: Analysis of Surface Electromyography (sEMG) Signals for Motion Signatures in Strength Training Exercises via Stretchable Wearable Electronic Sensors

Background: The characterization of commonly used strength training exercises has a range of implications for analysis of techniques displaying proper form and injury prevention in both sports and clinical rehabilitation settings. This study examines the ability of wearable sensors to effectively determine the degree of activation of different muscle groups using surface electromyography (sEMG) signals. The interpretation of these signals across muscle groups within an exercise allow for the characterization of their motion signatures. Wearable sensors with embedded electrodes (BioStamps RC, MC10 Inc.) were applied to two defined muscle groups for three exercises: a triceps push-up (PU), a biceps curl (BC) and an unweighted squat (US). Methods: Seven healthy volunteers performed three consecutive exercises in the following order; PU, BC, and US. Each exercise was performed for five repetitions with BioStamps applied to the distal and proximal ends of the subjects’ dominant side using adhesive bandages. For each of the defined exercises the investigator played a timed voice recording in which the subjects were instructed to perform the series of repetitions with consistent timing. Sensors automatically upload de-identified data to a tablet device during use. The following parameters are reported from the stamp: electromyographic data (of the muscle causing abduction and adduction) and acceleration (of the distal and proximal ends of the limb which is being abducted/adducted). The data was uploaded to Python and analyzed using a rolling average. P-values were then determined using a one-tailed t-test. Results: Each of the three strength exercises had two identifiable motion signatures, one from each muscle group, derived from the sEMG data which shows the peak muscle activation during the 5 repetitions of an exercise (Figure 1, E). Placement on the BioStamps on the TB and BB recorded activation in the PU and BC (Figure 1, A & B). There is a difference between the TB and BB activation in the PU (p=0.358) but no difference was found between their activation in the BC (p=0.06). This finding was limited by the small sample size (n=7), which would be improved in a future study. Placement of the BioStamps on the BF and RF was used in the unweighted squat (Figure 1, C & D). There is a difference in the RF and BF activation in the US (p=0.179). Discussion: By nature of the antagonistic motion of the triceps brachii (TB) and biceps brachii (BB) in a push-up, activation levels measured by sEMG recordings are expected to be similar. The TB acts as one of the primary movers, while the BB acts as an antagonist and stabilizes the movement to allow for a controlled push-up. Similarly, in a squat similar levels of activation were expected in the rectus femoris (RF) and the biceps femoris (BF) as the RF functions as a primary mover and the BF as a stabilizer. Activation of both the primary mover and stabilizing muscles is important for proper form and function.Figure 1. A & B. Placement of BioStamps on the triceps brachii and biceps brachii, muscles used in the biceps curl (p=0.06) and triceps push-up (p=0.358). C & D. Placement of BioStamps on the rectus femoris and the biceps femoris, muscles used in the unweighted squat (p=0.179). E. Unweighted squat sEMG graph showing muscle activation (mV) of rectus femoris over time (s).

Detailed Investigation of Knee Biomechanics during Posture Maintenance while Applying Different Static Loadings on the Spine

The aim of this paper was to investigate in detail the biomechanics of the knee during different static loadings on the spine using electromyographic (EMG) signals from six main surface muscles acting in the knee joint; three components of the ground reaction force measured by a force plate; knee flexion joint angle measured by a flexible goniometer; and the distances between the bones (femur and tibia) forming the knee joint measured by an echograph. The measurements were taken without weight (reference straight position) and with a weight of 2, 5, 10, 15, 17, and 20 kg placed in a rucksack on the spine. The results showed that the forces in the horizontal and sagittal planes were negligible, and the reaction in the frontal plane increased and was linearly dependent on the carrying weight. The distance between bones decreased linearly with increasing weight for all participants from 3.94% to 53.92% from the referent position. The knee angle varied and in many cases decreased with increasing weight. The calculated correlation coefficients between mean EMG signals and loading weight showed that the adjustment of different subjects’ musculature to increasing load is individual. In general, knee joint balance is a dynamic individual process.

Multi-Attention Feature Fusion Network for Accurate Estimation of Finger Kinematics From Surface Electromyographic Signals

Simultaneous and proportional control (SPC) based on surface electromyographic (sEMG) signals has led to a broad range of applications. However, due to the limitation in the generalization and stability of current machine learning algorithms, these methods can only estimate less than 15 simultaneuous and proportional (SP) categories of finger movement. In this article, a novel deep learning algorithm, named multiattention feature fusion network (MAFN), is proposed to estimate comprehensive finger movement (up to 28 categories SP movements) from sEMG signals. MAFN is based on the multihead attention mechanism, which adaptively extracts essential features for analyzing the joint angles from the extracted sEMG features. Furthermore, a real-time exponential smoothing algorithm is designed for further improvement of the prediction stability. MAFN was evaluated on 28 finger movements of 38 subjects in the Ninapro_db2 dataset, and benchmarked with the state-of-the-art methods, such as temporal convolutional network (TCN) and long short term memory network (LSTM). The results demonstrated that the average Pearson correlation coefficient, root mean squared error of MAFN (0.84 ± 0.03,0.09 ± 0.01) were significantly higher than those of TCN (0.52 ± 0.06, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> < 0.001;0.16 ± 0.02, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> < 0.001) and LSTM (0.62 ± 0.06, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> < 0.001;0.13 ± 0.01, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">p</i> < 0.001). These improvements led to more stable and accurate movement predictions. Additionally, the time delay and power consumption of MAFN when applied to sEMG signals on a portable device are only 83.4 ms and 3 W, which implies prospective commercial applications.

A low-cost robotic hand prosthesis with apparent haptic sense controlled by electroencephalographic signals

One of the biggest problems faced by amputees is obtaining a suitable low-cost prosthesis. To address this problem, the design and implementation of a transradial prosthesis controlled by electroencephalographic (EEG) signals was carried out. This prosthesis is an alternative to prostheses using electromyographic (EMG) signals, which are very complex and exhausting for the patient to execute.We collected EEG signal data using the Emotiv Insight Headset, which were then processed to control the movement of the prosthesis, known as the Zero Arm. Additionally, we incorporated Machine Learning algorithms to classify different types of objects and shapes. The prosthesis also features a haptic feedback system, which simulates the function of mechanoreceptors in the skin, providing the user with a sense of touch when using the prosthesis.Our research has yielded a viable and cost-effective prosthetic limb. We utilized 3D printing and easily obtainable servomotors and controllers, making the prosthesis affordable and accessible.Performance tests of the Zero Arm prosthesis have yielded promising results. The prosthesis demonstrated an average success rate of 86.67% across various tasks, indicating its reliability and effectiveness. Additionally, the prosthesis has an average recognition rate of 70% for different types of objects, a noteworthy accomplishment.

Redefining the decisional components of motor responses: Evidence from lexical and object decision tasks.

Models of decision making focusing on two-alternative choices have classically described motor-response execution as a nondecisional stage that serially follows the termination of decision processes. Recent evidence, however, points toward a more continuous transition between decision and motor processes. We investigated this transition in two lexical decisions and one object decision task. By recording the electromyographic (EMG) signal associated with the muscle responsible for the manual responses (i.e., button press), we partitioned single-trial reaction times into premotor (the time elapsing from stimulus onset until the onset of the EMG burst) and motor times (the time elapsing from the onset of the EMG burst and the button press), with the latter measuring response execution. Responses were slower for pseudowords and pseudo-objects compared to words and real objects. Importantly, these effects were reliable even at the level of motor time measures. Differently, despite the reliable effect at the level of reaction times and premotor times, there was no difference in motor times between high- and low-frequency words. Although these results, in line with recent evidence, challenge a purely noncognitive characterization of motor-response execution, they further suggest that motor times may selectively capture specific decisional components, which we identify with late-occurring verification and/or control mechanisms. (PsycInfo Database Record (c) 2023 APA, all rights reserved).

Multimodal Fusion Convolutional Neural Network Based on sEMG and Accelerometer Signals for Intersubject Upper Limb Movement Classification

The variation in the distributions of recorded data between individuals leads to low classification accuracy. To address this issue, we introduce a multimodal fusion convolutional neural network (MFCNN). This network extracts common information from surface electromyography (sEMG) and accelerometer signals of different subjects using a two-stream CNN. To enhance the classification accuracy of a particular subject, a fine-tuning approach was implemented. The performance of the proposed method was assessed in four different scenarios, which include inter-subject classification, inter-subject classification when training data from multiple subjects, fine-tuned inter-subject classification, and fine-tuned inter-subject classification when training data from multiple subjects. The results demonstrate that in the inter-subject scenario, when multiple subjects are available for training, the MFCNN achieves higher classification accuracy (p < 0.05) than other neural networks and support vector machines (SVMs) that use sEMG signals (NN and SVM), accelerometer signals (accNN and accSVM), sEMG and accelerometer signals (MFNN and MFSVM) as inputs, as well as a CNN that uses sEMG signals as input after fine-tuning. Furthermore, compared with an MFCNN model trained with data from a single subject and an accCNN model trained with data from a single subject or multiple subjects, an MFCNN trained with multiple subjects demonstrated better performance on new subjects after fine-tuning (p < 0.05). This method can learn common features among different subjects and improve the performance of classification among subjects. Our proposed method demonstrates the innovation of using a multimodal fusion approach and two-stream CNN to improve inter-subject classification accuracy in upper limb movements.

Evaluation of a Fused Sonomyography and Electromyography-Based Control on a Cable-Driven Ankle Exoskeleton

This article presents an assist-as-needed (AAN) control framework for exoskeleton assistance based on human volitional effort prediction via a Hill-type neuromuscular model. A sequential processing algorithm-based multirate observer is applied to continuously estimate muscle activation levels by fusing surface electromyography (sEMG) and ultrasound (US) echogenicity signals from the ankle muscles. An adaptive impedance controller manipulates the exoskeleton's impedance for a more natural behavior by following a desired intrinsic impedance model. Two neural networks provide robustness to uncertainties in the overall ankle joint-exoskeleton model and the prediction error in the volitional ankle joint torque. A rigorous Lyapunov-based stability analysis proves that the AAN control framework achieves uniformly ultimately bounded tracking for the overall system. Experimental studies on five participants with no neurological disabilities walking on a treadmill validate the effectiveness of the designed ankle exoskeleton and the proposed AAN approach. Results illustrate that the AAN control approach with fused sEMG and US echogenicity signals maintained a higher human volitional effort prediction accuracy, less ankle joint trajectory tracking error, and less robotic assistance torque than the AAN approach with the sEMG-based volitional effort prediction alone. The findings support our hypotheses that the proposed controller increases human motion intent prediction accuracy, improves the exoskeleton's control performance, and boosts voluntary participation from human subjects. The new framework potentially paves a foundation for using multimodal biological signals to control rehabilitative or assistive robots.

A signal EMerGes from the noise

In this issue of Cell Reports Methods, Osanai etal. report an innovative approach to extract an electromyography (EMG) signal from multi-channel local field potential (LFP) recordings using independent component analysis (ICA). This ICA-based approach offers precise and stable long-term behavioral assessment, eliminating the need for direct muscular recordings.

Robot teaching system based on hand-robot contact state detection and motion intention recognition

This paper presents a robot teaching system based on hand-robot contact state detection and human motion intent recognition. The system can detect the contact state of the hand-robot joint and extracts motion intention information from the human surface electromyography (sEMG) signals to control the robot's motion. First, a hand-robot contact state detection method is proposed based on the fusion of the virtual robot environment with the physical environment. With the use of a target detection algorithm, the position of the human hand in the color image of the physical environment can be identified and its pixel coordinates can be calculated. Meanwhile, the synthetic images of the virtual robot environment are combined with those of the physical robot scene to determine whether the human hand is in contact with the robot. Besides, a human motion intention recognition model based on deep learning is designed to recognize human motion intention with the input of sEMG signals. Moreover, a robot motion mode selection module is built to control the robot for single-axis motion, linear motion, or repositioning motion by combining the hand-robot contact state and human motion intention. The experimental results indicate that the proposed system can perform online robot teaching for the three motion modes.

Multimodal biofeedback for Parkinson’s disease motor and nonmotor symptoms

Parkinson’s disease (PD) is a neurodegenerative disorder characterized by motor retardation, myotonia, quiescent tremor, and postural gait abnormality, as well as nonmotor symptoms such as anxiety and depression. Biofeedback improves motor and nonmotor functions of patients by regulating abnormal electroencephalogram (EEG), electrocardiogram (ECG), photoplethysmography (PPG), electromyography (EMG), respiration (RSP), or other physiological signals. Given that multimodal signals are closely related to PD states, the clinical effect of multimodal biofeedback on patients with PD is worth exploring. Twenty-one patients with PD in Beijing Rehabilitation Hospital were enrolled and divided into three groups: multimodal (EEG, ECG, PPG, and RSP feedback signal), EEG (EEG feedback signal), and sham (random feedback signal), and they received biofeedback training five times in two weeks. The combined clinical scale and multimodal signal analysis results revealed that the EEG group significantly improved motor symptoms and increased Berg balance scale scores by regulating β band activity; the multimodal group significantly improved nonmotor symptoms and reduced Hamilton rating scale for depression scores by improving θ band activity. Our preliminary results revealed that multimodal biofeedback can improve the clinical symptoms of PD, but the regulation effect on motor symptoms is weaker than that of EEG biofeedback.

Lower Limb Exoskeleton for Rehabilitation with Flexible Joints and Movement Routines Commanded by Electromyography and Baropodometry Sensors.

This paper presents the development of an instrumented exoskeleton with baropodometry, electromyography, and torque sensors. The six degrees of freedom (Dof) exoskeleton has a human intention detection system based on a classifier of electromyographic signals coming from four sensors placed in the muscles of the lower extremity together with baropodometric signals from four resistive load sensors placed at the front and rear parts of both feet. In addition, the exoskeleton is instrumented with four flexible actuators coupled with torque sensors. The main objective of the paper was the development of a lower limb therapy exoskeleton, articulated at hip and knees to allow the performance of three types of motion depending on the detected user's intention: sitting to standing, standing to sitting, and standing to walking. In addition, the paper presents the development of a dynamical model and the implementation of a feedback control in the exoskeleton.

Adjustments in the motor unit discharge behavior following neuromuscular electrical stimulation compared to voluntary contractions.

Introduction: The application of neuromuscular electrical stimulation superimposed on voluntary muscle contractions (NMES+) has demonstrated a considerable potential to enhance or restore muscle function in both healthy and individuals with neurological or orthopedic disorders. Improvements in muscle strength and power have been commonly associated with specific neural adaptations. In this study, we investigated changes in the discharge characteristics of the tibialis anterior motor units, following three acute exercises consisting of NMES+, passive NMES and voluntary isometric contractions alone. Methods: Seventeen young participants participated in the study. High-density surface electromyography was used to record myoelectric activity in the tibialis anterior muscle during trapezoidal force trajectories involving isometric contractions of ankle dorsi flexors with target forces set at 35, 50% and 70% of maximal voluntary isometric contraction (MVIC). From decomposition of the electromyographic signal, motor unit discharge rate, recruitment and derecruitment thresholds were extracted and the input-output gain of the motoneuron pool was estimated. Results: Global discharge rate increased following the isometric condition compared to baseline at 35% MVIC while it increased after all experimental conditions at 50% MVIC target force. Interestingly, at 70% MVIC target force, only NMES + led to greater discharge rate compared to baseline. Recruitment threshold decreased after the isometric condition, although only at 50% MVIC. Input-output gain of the motoneurons of the tibialis anterior muscle was unaltered after the experimental conditions. Discussion: These results indicated that acute exercise involving NMES + induces an increase in motor unit discharge rate, particularly when higher forces are required. This reflects an enhanced neural drive to the muscle and might be strongly related to the distinctive motor fiber recruitment characterizing NMES+.

Evaluation of surface electromyography of selected neck muscles during the whiplash mechanism in aware and unaware conditions due to safe punching in kickboxing

BackgroundKickboxing is considered as a combat sport in progress, in which injuries are frequent and significant, and close injury monitoring is highly recommended. Sports injuries to the head and neck are estimated to cause 70% deaths and 20% permanent disabilities although they are much less common than those to the limbs. Whiplash mechanism involves the rapid extension (opening) and flexion (bending) of neck. The purpose of the current study was to investigate the electromyographic activity of selected muscles in the whiplash mechanism in aware and unaware conditions of the safe punching in kickboxing so that we can design special exercises.MethodIn the present study, 24 male kickboxing athletes aged 18–40 years were selected based on a purposive sampling method. The surface electromyography (EMG) signals of muscles were recorded with and without awareness of safe punching by using a nine-channel wireless EMG device. Additionally, a nine-channel 3D inertial measurement unit (IMU, wireless,) was utilized to determine the acceleration, kinematics, and angular velocity of the subjects’ head. The statistical dependent t-test was applied to compare the EMG activity of each muscle, as well as its participation ratio.ResultsThe results of statistical analysis represented a significant increase in the EMG activity of sternocleidomastoid (p = 0.001), upper trapezius (p = 0.001) and cervical erector spinae muscles (p = 0.001), as well as the neck extension and flexion angles between the athletes aware (open eyes) and unaware (closed eyes) of the safe punching.ConclusionIn this study, the EMG activity of the sternocleidomastoid, upper trapezius, and cervical erector spine muscles in the aware condition was significantly different from the activity under unaware condition. In fact, the intended muscles exhibited significantly different behaviors in preventing extension and flexion in the two conditions.

COMPLEXITY ANALYSIS OF SURFACE ELECTROMYOGRAPHY SIGNALS UNDER FATIGUE USING HJORTH PARAMETERS AND BUBBLE ENTROPY

This work aims to analyze the complexity of surface electromyography (sEMG) signals under muscle fatigue conditions using Hjorth parameters and bubble entropy (BE). Signals are recorded from the biceps brachii muscle of 25 healthy males during dynamic and isometric contraction exercises. These signals are filtered and segmented into 10 equal parts. The first and tenth segments are considered as nonfatigue and fatigue conditions, respectively. Activity, mobility, complexity, and BE features are extracted from both segments and classified using support vector machine (SVM), Naïve bayes (NB), k-nearest neighbor (kNN), and random forest (RF). The results indicate a reduction in signal complexity during fatigue. The parameter activity is found to increase under fatigue for both dynamic and isometric contractions with mean values of 0.35 and 0.22, respectively. It is observed that mobility, complexity, and BE are lowest during fatigue for both contractions. Maximum accuracy of 95.00% is achieved with the kNN and Hjorth parameters for dynamic signals. It is also found that the reduction of signal complexity during fatigue is more significant in dynamic contractions. This study confirms that the extracted features are suitable for analyzing the complex nature of sEMG signals. Hence, the proposed approach can be used for analyzing the complex characteristics of sEMG signals under various myoneural conditions.

A Wireless, High-Quality, Soft and Portable Wrist-Worn System for sEMG Signal Detection.

The study of wearable systems based on surface electromyography (sEMG) signals has attracted widespread attention and plays an important role in human-computer interaction, physiological state monitoring, and other fields. Traditional sEMG signal acquisition systems are primarily targeted at body parts that are not in line with daily wearing habits, such as the arms, legs, and face. In addition, some systems rely on wired connections, which impacts their flexibility and user-friendliness. This paper presents a novel wrist-worn system with four sEMG acquisition channels and a high common-mode rejection ratio (CMRR) greater than 120 dB. The circuit has an overall gain of 2492 V/V and a bandwidth of 15~500 Hz. It is fabricated using flexible circuit technologies and is encapsulated in a soft skin-friendly silicone gel. The system acquires sEMG signals at a sampling rate of over 2000 Hz with a 16-bit resolution and transmits data to a smart device via low-power Bluetooth. Muscle fatigue detection and four-class gesture recognition experiments (accuracy greater than 95%) were conducted to validate its practicality. The system has potential applications in natural and intuitive human-computer interaction and physiological state monitoring.

Forearm sEMG data from young healthy humans during the execution of hand movements

This work provides a complete dataset containing surface electromyography (sEMG) signals acquired from the forearm with a sampling frequency of 1000 Hz. The dataset is named WyoFlex sEMG Hand Gesture and recorded the data of 28 participants between 18 and 37 years old without neuromuscular diseases or cardiovascular problems. The test protocol consisted of sEMG signals acquisition corresponding to ten wrist and grasping movements (extension, flexion, ulnar deviation, radial deviation, hook grip, power grip, spherical grip, precision grip, lateral grip, and pinch grip), considering three repetitions for each gesture. Also, the dataset contains general information such as anthropometric measures of the upper limb, gender, age, laterally of the person, and physical condition. Likewise, the implemented acquisition system consists of a portable armband with four sEMG channels distributed equidistantly for each forearm. The database could be used for the recognition of hand gestures, evaluation of the evolution of patients in rehabilitation processes, control of upper limb orthoses or prostheses, and biomechanical analysis of the forearm.