Transferable non-invasive modal fusion-transformer (NIMFT) for end-to-end hand gesture recognition

Objective.Recent studies have shown that integrating inertial measurement unit (IMU) signals with surface electromyographic (sEMG) can greatly improve hand gesture recognition (HGR) performance in applications such as prosthetic control and rehabilitation training. However, current deep learning models for multimodal HGR encounter difficulties in invasive modal fusion, complex feature extraction from heterogeneous signals, and limited inter-subject model generalization. To address these challenges, this study aims to develop an end-to-end and inter-subject transferable model that utilizes non-invasively fused sEMG and acceleration (ACC) data.Approach.The proposed non-invasive modal fusion-transformer (NIMFT) model utilizes 1D-convolutional neural networks-based patch embedding for local information extraction and employs a multi-head cross-attention (MCA) mechanism to non-invasively integrate sEMG and ACC signals, stabilizing the variability induced by sEMG. The proposed architecture undergoes detailed ablation studies after hyperparameter tuning. Transfer learning is employed by fine-tuning a pre-trained model on new subject and a comparative analysis is performed between the fine-tuning and subject-specific model. Additionally, the performance of NIMFT is compared to state-of-the-art fusion models.Main results.The NIMFT model achieved recognition accuracies of 93.91%, 91.02%, and 95.56% on the three action sets in the Ninapro DB2 dataset. The proposed embedding method and MCA outperformed the traditional invasive modal fusion transformer by 2.01% (embedding) and 1.23% (fusion), respectively. In comparison to subject-specific models, the fine-tuning model exhibited the highest average accuracy improvement of 2.26%, achieving a final accuracy of 96.13%. Moreover, the NIMFT model demonstrated superiority in terms of accuracy, recall, precision, and F1-score compared to the latest modal fusion models with similar model scale.Significance.The NIMFT is a novel end-to-end HGR model, utilizes a non-invasive MCA mechanism to integrate long-range intermodal information effectively. Compared to recent modal fusion models, it demonstrates superior performance in inter-subject experiments and offers higher training efficiency and accuracy levels through transfer learning than subject-specific approaches.

Evaluation of Hand Action Classification Performance Using Machine Learning Based on Signals from Two sEMG Electrodes

Classification-based myoelectric control has attracted significant interest in recent years, leading to prosthetic hands with advanced functionality, such as multi-grip hands. Thus far, high classification accuracies have been achieved by increasing the number of surface electromyography (sEMG) electrodes or adding other sensing mechanisms. While many prescribed myoelectric hands still adopt two-electrode sEMG systems, detailed studies on signal processing and classification performance are still lacking. In this study, nine able-bodied participants were recruited to perform six typical hand actions, from which sEMG signals from two electrodes were acquired using a Delsys Trigno Research+ acquisition system. Signal processing and machine learning algorithms, specifically, linear discriminant analysis (LDA), k-nearest neighbors (KNN), and support vector machines (SVM), were used to study classification accuracies. Overall classification accuracy of 93 ± 2%, action-specific accuracy of 97 ± 2%, and F1-score of 87 ± 7% were achieved, which are comparable with those reported from multi-electrode systems. The highest accuracies were achieved using SVM algorithm compared to LDA and KNN algorithms. A logarithmic relationship between classification accuracy and number of features was revealed, which plateaued at five features. These comprehensive findings may potentially contribute to signal processing and machine learning strategies for commonly prescribed myoelectric hand systems with two sEMG electrodes to further improve functionality.

Towards standardisation of surface electromyography measurements in the horse: Bipolar electrode location

The use of surface electromyography in the field of animal locomotion has increased considerably over the past decade. However, no consensus exists on the methodology for data collection in horses. This study aimed to start the development of recommendations for bipolar electrode locations to collect surface electromyographic data from horses during dynamic tasks. Data were collected from 21 superficial muscles of three horses during trot on a treadmill using linear electrode arrays. The data were assessed both quantitatively (signal-to-noise ratio (SNR) and coefficient of variation (CoV)) and qualitatively (presence of crosstalk and activation patterns) to compare and select electrode locations for each muscle. For most muscles and horses, the highest SNR values were detected near or cranial/proximal to the central region of the muscle. Concerning the CoV, there were larger differences between muscles and horses than within muscles. Qualitatively, crosstalk was suspected to be present in the signals of twelve muscles but not in all locations in the arrays. With this study, a first attempt is made to develop recommendations for bipolar electrode locations for muscle activity measurements during dynamic contractions in horses. The results may help to improve the reliability and reproducibility of study results in equine biomechanics.

A rotary transformer cross-subject model for continuous estimation of finger joints kinematics and a transfer learning approach for new subjects

Introduction

Surface Electromyographic (sEMG) signals are widely utilized for estimating finger kinematics continuously in human-machine interfaces (HMI), and deep learning approaches are crucial in constructing the models. At present, most models are extracted on specific subjects and do not have cross-subject generalizability. Considering the erratic nature of sEMG signals, a model trained on a specific subject cannot be directly applied to other subjects. Therefore, in this study, we proposed a cross-subject model based on the Rotary Transformer (RoFormer) to extract features of multiple subjects for continuous estimation kinematics and extend it to new subjects by adversarial transfer learning (ATL) approach.

Methods

We utilized the new subject's training data and an ATL approach to calibrate the cross-subject model. To improve the performance of the classic transformer network, we compare the impact of different position embeddings on model performance, including learnable absolute position embedding, Sinusoidal absolute position embedding, and Rotary Position Embedding (RoPE), and eventually selected RoPE. We conducted experiments on 10 randomly selected subjects from the NinaproDB2 dataset, using Pearson correlation coefficient (CC), normalized root mean square error (NRMSE), and coefficient of determination (R2) as performance metrics.

Results

The proposed model was compared with four other models including LSTM, TCN, Transformer, and CNN-Attention. The results demonstrated that both in cross-subject and subject-specific cases the performance of RoFormer was significantly better than the other four models. Additionally, the ATL approach improves the generalization performance of the cross-subject model better than the fine-tuning (FT) transfer learning approach.

Discussion

The findings indicate that the proposed RoFormer-based method with an ATL approach has the potential for practical applications in robot hand control and other HMI settings. The model's superior performance suggests its suitability for continuous estimation of finger kinematics across different subjects, addressing the limitations of subject-specific models.

The Lower Limb Muscle Co-Activation Map during Human Locomotion: From Slow Walking to Running

The central nervous system (CNS) controls movements and regulates joint stiffness with muscle co-activation, but until now, few studies have examined muscle pairs during running. This study aims to investigate differences in lower limb muscle coactivation during gait at different speeds, from walking to running. Nineteen healthy runners walked and ran at speeds ranging from 0.8 km/h to 9.3 km/h. Twelve lower limb muscles' co-activation was calculated using the time-varying multi-muscle co-activation function (TMCf) with global, flexor-extension, and rostro-caudal approaches. Spatiotemporal and kinematic parameters were also measured. We found that TMCf, spatiotemporal, and kinematic parameters were significantly affected by gait speed for all approaches. Significant differences were observed in the main parameters of each co-activation approach and in the spatiotemporal and kinematic parameters at the transition between walking and running. In particular, significant differences were observed in the global co-activation (CIglob, main effect F(1,17) = 641.04, p < 0.001; at the transition p < 0.001), the stride length (main effect F(1,17) = 253.03, p < 0.001; at the transition p < 0.001), the stride frequency (main effect F(1,17) = 714.22, p < 0.001; at the transition p < 0.001) and the Center of Mass displacement in the vertical (CoMy, main effect F(1,17) = 426.2, p < 0.001; at the transition p < 0.001) and medial-lateral (CoMz, main effect F(1,17) = 120.29 p < 0.001; at the transition p < 0.001) directions. Regarding the correlation analysis, the CoMy was positively correlated with a higher CIglob (r = 0.88, p < 0.001) and negatively correlated with Full Width at Half Maximum (FWHMglob, r = -0.83, p < 0.001), whereas the CoMz was positively correlated with the global Center of Activity (CoAglob, r = 0.97, p < 0.001). Positive and negative strong correlations were found between global co-activation parameters and center of mass displacements, as well as some spatiotemporal parameters, regardless of gait speed. Our findings suggest that walking and running have different co-activation patterns and kinematic characteristics, with the whole-limb stiffness exerted more synchronously and stably during running. The co-activation indexes and kinematic parameters could be the result of global co-activation, which is a sensory-control integration process used by the CNS to deal with more demanding and potentially unstable tasks like running.

Influencing factors of corticomuscular coherence in stroke patients

Stroke, also known as cerebrovascular accident, is an acute cerebrovascular disease with a high incidence, disability rate, and mortality. It can disrupt the interaction between the cerebral cortex and external muscles. Corticomuscular coherence (CMC) is a common and useful method for studying how the cerebral cortex controls muscle activity. CMC can expose functional connections between the cortex and muscle, reflecting the information flow in the motor system. Afferent feedback related to CMC can reveal these functional connections. This paper aims to investigate the factors influencing CMC in stroke patients and provide a comprehensive summary and analysis of the current research in this area. This paper begins by discussing the impact of stroke and the significance of CMC in stroke patients. It then proceeds to elaborate on the mechanism of CMC and its defining formula. Next, the impacts of various factors on CMC in stroke patients were discussed individually. Lastly, this paper addresses current challenges and future prospects for CMC.

Motion intention recognition of the affected hand based on the sEMG and improved DenseNet network

The key to sEMG (surface electromyography)-based control of robotic hands is the utilization of sEMG signals from the affected hand of amputees to infer their motion intentions. With the advancements in deep learning, researchers have successfully developed viable solutions for CNN (Convolutional Neural Network)-based gesture recognition. However, most studies have primarily concentrated on utilizing sEMG data from the hands of healthy subjects, often relying on high-dimensional feature vectors obtained from a substantial number of electrodes. This approach has yielded high-performing sEMG recognition systems but has failed to consider the considerable inconvenience that the abundance of electrodes poses to the daily lives and work of patients. In this paper, we focused on transradial amputees and used sEMG data from the Ninapro DB3 database as our dataset. Firstly, we introduce a STFT (Short-Time Fourier Transform)-based time-frequency feature fusion map for sEMG. This map includes both time-frequency features and the time-frequency localization of sEMG signals. Secondly, we propose an Improved DenseNet (Dense Convolutional Network) model for recognizing motion intentions in the affected hand of amputees based on their sEMG signals. Finally, addressing the issue of optimizing the number of electrodes carried by amputees, we introduce the PCMIRR (Pearson Correlation and Motion Intention Recognition Rate) algorithm. This algorithm optimizes the number of channels by considering the Pearson correlation between the sEMG channels of amputees and the recognition rate of motion intentions in the affected hand based on single-channel sEMG data. The experimental results reveal that the recognition accuracy, recall, and F1 score achieved by the Improved DenseNet model were 93.82%, 93.61%, and 93.65%, respectively. When the number of electrodes was optimized to 8, the recognition accuracy reached 94.50%. In summary, this paper ultimately attained precise recognition of motion intentions in amputees' affected hands while utilizing the minimum number of sEMG channels. This method offers a novel approach to sEMG-based control of bionic robotic hands.

Improving wheelchair user sitting posture to alleviate lumbar fatigue: a study utilizing sEMG and pressure sensors

Background

The wheelchair is a widely used rehabilitation device, which is indispensable for people with limited mobility. In the process of using a wheelchair, they often face the situation of sitting for a long time, which is easy to cause fatigue of the waist muscles of the user. Therefore, this paper hopes to provide more scientific guidance and suggestions for the daily use of wheelchairs by studying the relationship between the development of muscle fatigue and sitting posture.

Methods

First, we collected surface Electromyography (sEMG) of human vertical spine muscle and analyzed it in the frequency domain. The obtained Mean Power Frequency (MPF) was used as the dependent variable. Then, the pose information of the human body, including the percentage of pressure points, span, and center of mass as independent variables, was collected by the array of thin film pressure sensors, and analyzed by a multivariate nonlinear regression model.

Results

When the centroid row coordinate of the cushion pressure point is about 16(range, 7.7-16.9), the cushion pressure area percentage is about 80%(range, 70.8%-89.7%), and the cushion pressure span range is about 27(range, 25-31), the backrest pressure point centroid row coordinate is about 15(range, 9.1-18.2), the backrest pressure area percentage is about 35%(range, 11.8%-38.7%), and the backrest pressure span range is about 16(range, 9-22). At this time, the MPF value of the subjects decreased by a small percentage, and the fatigue development of the muscles was slower. In addition, the pressure area percentage at the seat cushion is a more sensitive independent variable, too large or too small pressure area percentage will easily cause lumbar muscle fatigue.

Conclusion

The results show that people should sit in the middle and back of the seat cushion when riding the wheelchair, so that the Angle of the hip joint can be in a natural state, and the thigh should fully contact the seat cushion to avoid the weight of the body concentrated on the buttocks; The back should be fully in contact with the back of the wheelchair to reduce the burden on the waist, and the spine posture can be adjusted appropriately according to personal habits, but it is necessary to avoid maintaining a chest sitting position for a long time, which will cause the lumbar spine to be in an unnatural physiological Angle and easily lead to fatigue of the waist muscles.

Acute Effects of Sprint Interval Training and Blood Flow Restriction on Neuromuscular and Muscle Function

BFR) applied during sprint interval training (SIT) on performance and neuromuscular function.

METHODS

Fifteen men completed a randomized bout of SIT with CBFR, IBFR, and without BFR (No-BFR), consisting of 2, 30-s maximal sprints on a cycle ergometer with a resistance of 7.5% of body mass. Concentric peak torque (CPT), maximal voluntary isometric contraction (MVIC) torque, and muscle thickness (MT) were measured before and after SIT, including surface electromyography (sEMG) recorded during the strength assessments. Peak and mean revolutions per minute (RPM) were measured during SIT and power output was examined relative to physical working capacity at the fatigue threshold (PWCFT).

RESULTS

CPT and MVIC torque decreased from pre-SIT (220.3±47.6 Nm and 355.1±72.5 Nm, respectively) to post-SIT (147.9±27.7 Nm and 252.2±45.5 Nm, respectively, all P<0.05), while MT increased (1.77±0.31 cm to 1.96±0.30 cm). sEMG mean power frequency decreased during CPT (-12.8±10.5%) and MVIC (-8.7±10.2%) muscle actions. %PWCFT was greater during No-BFR (414.2±121.9%) than CBFR (375.9±121.9%).

CONCLUSION

SIT with or without BFR induced comparable alterations in neuromuscular fatigue and sprint performance across all conditions, without affecting neuromuscular function.

sEMG-Based Inter-Session Hand Gesture Recognition via Domain Adaptation with Locality Preserving and Maximum Margin

Surface electromyography (sEMG)-based gesture recognition can achieve high intra-session performance. However, the inter-session performance of gesture recognition decreases sharply due to the shift in data distribution. Therefore, developing a robust model to minimize the data distribution difference is crucial to improving the user experience. In this work, based on the inter-session gesture recognition task, we propose a novel algorithm called locality preserving and maximum margin criterion (LPMM). The LPMM algorithm integrates three main modules, including domain alignment, pseudo-label selection, and iteration result selection. Domain alignment is designed to preserve the neighborhood structure of the feature and minimize the overlap of different classes. The pseudo-label selection and iteration result selection can avoid the decrease in accuracy caused by mislabeled samples. The proposed algorithm was evaluated on two of the most widely used EMG databases. It achieves a mean accuracy of 98.46% and 71.64%, respectively, which is superior to state-of-the-art domain adaptation methods.

The mechanisms underpinning the slow component of [Formula: see text] in humans

PURPOSE

When exercising above the lactic threshold (LT), the slow component of oxygen uptake ([Formula: see text]) appears, mainly ascribed to the progressive recruitment of Type II fibers. However, also the progressive decay of the economy of contraction may contribute to it. We investigated oxygen uptake ([Formula: see text]) during isometric contractions clamping torque (T) or muscular activation to quantify the contributions of the two mechanisms.

METHODS

We assessed for 7 min T of the leg extensors, net oxygen uptake ([Formula: see text]) and root mean square (RMS) from vastus lateralis (VL) in 11 volunteers (21 ± 2 yy; 1.73 ± 0.11 m; 67 ± 14 kg) during cyclic isometric contractions (contraction/relaxation 5 s/5 s): (i) at 65% of maximal voluntary contraction (MVC) (FB-Torque) and; (ii) keeping the level of RMS equal to that at 65% of MVC (FB-EMG).

RESULTS

[Formula: see text] after the third minute in FB-Torque increased with time ([Formula: see text] = 94 × t + 564; R2 = 0.99; P = 0.001), but not during FB-EMG. [Formula: see text]/T increased only during FB-Torque ([Formula: see text]/T = 1.10 × t + 0.57; R2 = 0.99; P = 0.001). RMS was larger in FB-Torque than in FB-EMG and significantly increased in the first three minutes of exercise to stabilize till the end of the trial, indicating that the pool of recruited MUs remained constant despite [Formula: see text].

CONCLUSION

The analysis of the RMS, [Formula: see text] and T during FB-Torque suggests that the intrinsic mechanism attributable to the decay of contraction efficiency was responsible for an increase of [Formula: see text] equal to 18% of the total [Formula: see text].

Effects of isometric training and R.I.C.E. treatment on the arm muscle performance of swimmers with elbow pain

The effects of IT and R.I.C.E. treatment on arm muscle performance in overhead athletes with elbow pain (EP) have been partially validated. However, there is a lack of research evidence regarding the efficacy of these two methods on arm muscle performance among swimmers with EP. The aim of this study was to investigate the trends and differences in the effects of IT and R.I.C.E. treatment on arm muscle performance among swimmers with EP. The main outcomes were the time effects and group effects of interventions on muscle voluntary contraction (MVC). Sixty elite freestyle swimmers from Tianjin, China, voluntarily participated in the study and completed a 10-week intervention program. Swimmers with EP in the IT group showed a positive trend in MVC, with an approximately 2% increase, whereas the MVC of subjects in the R.I.C.E. treatment group and control group decreased by approximately 4% and 5%, respectively. In comparison, the effects of the IT intervention on the MVC of the triceps and brachioradialis muscles in swimmers with EP were significant (p = 0.042 < 0.05, p = 0.027 < 0.05). The mean MVC value of the IT group (0.60) was greater than that of the other two groups (0.51, 0.50). IT has a beneficial impact on the MVC performance of the triceps and brachioradialis muscles in swimmers with EP. It is recommended that professionals consider incorporating IT into regular training routines to mitigate the risk of EP issues. Future research should examine the effectiveness of both interventions on hand-grip strength and completion time in 50-m freestyle swim drills in order for swimmers with EP to return to this sport.

Teleoperation of an Anthropomorphic Robot Hand with a Metamorphic Palm and Tunable-Stiffness Soft Fingers

Teleoperation in soft robotics can endow soft robots with the ability to perform complex tasks through human-robot interaction. In this study, we propose a teleoperated anthropomorphic soft robot hand with variable degrees of freedom (DOFs) and a metamorphic palm. The soft robot hand consists of four pneumatic-actuated fingers, which can be heated to tune stiffness. A metamorphic mechanism was actuated to morph the hand palm by servo motors. The human fingers' DOF, gesture, and muscle stiffness were collected and mapped to the soft robotic hand through the sensory feedback from surface electromyography devices on the jib. The results show that the proposed soft robot hand can generate a variety of anthropomorphic configurations and can be remotely controlled to perform complex tasks such as primitively operating the cell phone and placing the building blocks. We also show that the soft hand can grasp a target through the slit by varying the DOFs and stiffness in a trail.

Use of Surface Electromyography to Evaluate Effects of Therapeutic Methods on Masticatory Muscle Activity in Patients with Temporomandibular Disorders: A Narrative Review

The presented narrative review aims to present the impact of therapeutic methods on the masticatory muscle activity measured using surface electromyography (sEMG) in patients with temporomandibular disorders (TMDs). Original interventional studies with baseline data for diagnosed TMD groups with full-text articles in English published in scientific journals in the last ten years were included in the evaluation process. The following narrative review considered only clinical, controlled, and randomized studies. Articles that included the following parameters were qualified for this review: adult participants, diagnosis of temporomandibular disorder, the presence of a musculoskeletal dysfunction, no other severe comorbidities, use of therapeutic interventions, and sEMG measurement before and after the intervention. Ten papers were accepted and analyzed for the final evaluation in the presented review. Several studies using surface electromyographic examination prove the effectiveness of various therapies to normalize the bioelectrical activity of the masticatory muscles, either reduction during rest or increase during a functional task in patients diagnosed with temporomandibular disorders. This narrative review shows the influence of manual and physical treatments on electromyographic masticatory muscle activity, including soft tissue mobilization, transcutaneous electrical nerve stimulation, low-level laser therapy, and moist heat therapy. Changes in masticatory muscle activity coincided with changes in TMD-associated pain and range of mandibular mobility.

Metrology in sEMG and movement analysis: the need for training new figures in clinical rehabilitation

A new educational curriculum for the next generation of physical and occupational therapists is urgent in order to manage the recent fast advances in sensors, measurement technologies and related instrumentation. This is required by the growing role of STEM in rehabilitation, kinesiology, and sport sciences. Surface EMG technology is used in this work as a representative example of similar problems present in movement analysis, exoskeletons, and many other fields. A review of the most relevant articles and international projects in the field of interfacing physical therapy with measurement technology for quantitative assessment of outcome is presented. It is concluded that a new generation of educators is needed as well as a Ph.D. and/or a clinical doctorate degree in physical therapy, still lacking in many countries. It is urgent to consider knowledge translation since it will take many years before any recommended change in teaching will be accepted and show some effect. A call for a "white paper" on rehabilitation metrology is highly auspicable.

Ensemble Learning Method for the Continuous Decoding of Hand Joint Angles

Human-machine interface technology is fundamentally constrained by the dexterity of motion decoding. Simultaneous and proportional control can greatly improve the flexibility and dexterity of smart prostheses. In this research, a new model using ensemble learning to solve the angle decoding problem is proposed. Ultimately, seven models for angle decoding from surface electromyography (sEMG) signals are designed. The kinematics of five angles of the metacarpophalangeal (MCP) joints are estimated using the sEMG recorded during functional tasks. The estimation performance was evaluated through the Pearson correlation coefficient (CC). In this research, the comprehensive model, which combines CatBoost and LightGBM, is the best model for this task, whose average CC value and RMSE are 0.897 and 7.09. The mean of the CC and the mean of the RMSE for all the test scenarios of the subjects' dataset outperform the results of the Gaussian process model, with significant differences. Moreover, the research proposed a whole pipeline that uses ensemble learning to build a high-performance angle decoding system for the hand motion recognition task. Researchers or engineers in this field can quickly find the most suitable ensemble learning model for angle decoding through this process, with fewer parameters and fewer training data requirements than traditional deep learning models. In conclusion, the proposed ensemble learning approach has the potential for simultaneous and proportional control (SPC) of future hand prostheses.

Correlation of 3D Morphometric Changes, Kinematics, and Muscle Activity During Smile

OBJECTIVE

Knowing the morphological, kinematic, and electrophysiological parameters of the smile in healthy individuals may contribute to evaluating, planning, and monitoring the smile reanimation. This study aimed to determine the correlation between 3D morphometric changes, movement kinematics, and muscle activity in the facial soft tissue of healthy individuals.

METHOD

In this cohort study, 20 volunteers were selected from healthy individuals with no facial disorders. During smiling, three-dimensional face scanning, facial motion capture, and surface electromyography (sEMG) were performed. The average displacement, velocity, and acceleration during facial movements were measured. The mean change in 3D surface morphometry and activation of the zygomaticus major were determined.

RESULTS

The volunteers, comprising 10 males and 10 females, had a mean age of 24 ± 10 years; for female, mean age was 23 ± 5 years and for men 26 ± 13 years. Significant correlations were found between kinematic and morphometric data (r = 0.51, p < 0.001), sEMG and morphometric (r = 0.50, p < 0.001) data, and sEMG and kinematic data (r = 0.49, p < 0.002). The maximum acceleration occurred during approximately 65% of the muscle activation time and 64% of the peak muscle activation value. Additionally, the maximum velocity was reached at around 73% of the muscle activation time and 67% of the peak muscle activation value. Furthermore, the maximum displacement values were observed at approximately 88% of the muscle activation time and 76% of the peak muscle activation value.

CONCLUSION

The findings may provide insights into the smile's functional parameters, contribute to understanding facial muscle-related disorders, and aid in improving the diagnosis and treatment of the smile.

LEVEL OF EVIDENCE

N/A Laryngoscope, 2024.

Self-healing electrical bioadhesive interface for electrophysiology recording

Electrical bioadhesive interfaces (EBIs) are standing out in various applications, including medical diagnostics, prosthetic devices, rehabilitation, and human-machine interactions. Nonetheless, crafting a reliable and advanced EBI with comprehensive properties spanning electrochemical, electrical, mechanical, and self-healing capabilities remains a formidable challenge. Herein, we develop a self-healing EBI by thoughtfully integrating conducting polymer nanofibers and a typical bioadhesive within a robust hydrogel matrix. The accomplished EBI demonstrates extraordinary adhesion (lap shear strength of 197 kPa), exceptional electrical conductivity (2.18 S m-1), and outstanding self-healing performance. Taking advantage of these attributes, we integrated the EBI into flexible skin electrodes for surface electromyography (sEMG) signal recording from forearm muscles. The engineered skin electrodes exhibit robust adhesion to the skin even when sweating, rapid self-healing from damage, and seamless real-time signal recording with a higher signal-to-noise ratio (39 dB). Our EBI, along with its skin electrodes, offers a promising platform for tissue-device integration, health monitoring, and an array of bioelectronic applications.

Experimental Study of Fully Passive, Fully Active, and Active-Passive Upper-Limb Exoskeleton Efficiency: An Assessment of Lifting Tasks

Recently, robotic exoskeletons are gaining attention for assisting industrial workers. The exoskeleton power source ranges from fully passive (FP) to fully active (FA), or a mixture of both. The objective of this experimental study was to assess the efficiency of a new active-passive (AP) shoulder exoskeleton using statistical analyses of 11 quantitative measures from surface electromyography (sEMG) and kinematic data and a user survey for weight lifting tasks. Two groups of females and males lifted heavy kettlebells, while a shoulder exoskeleton helped them in modes of fully passive (FP), fully active (FA), and active-passive (AP). The AP exoskeleton outperformed the FP and FA exoskeletons because the participants could hold the weighted object for nearly twice as long before fatigue occurred. Future developments should concentrate on developing sex-specific controllers as well as on better-fitting wearable devices for women.

Biomechanical analysis of lower limbs during stand-to-sit tasks in patients with early-stage knee osteoarthritis

Background: Knee osteoarthritis (KOA) is a common degenerative disease among the older people that severely affects their daily life. Previous studies have confirmed that movement biomechanics are altered in patients with KOA during task performance. However, changes that occur in lower limb joints and muscles in the three planes during stand-to-sit (STS) tasks in patients with early-stage KOA are unclear. Method: Of the 36 participants recruited in this study, 24 (8 males and 16 females) and 12 (4 males and 8 females) were added to the KOA and control groups, respectively. The Nexus Vicon motion capture system along with Delsys wireless surface electromyography devices and plantar pressure measurement mat was used to record test data. A Visual 3D software was used to process the data and calculate the biomechanical and electromyographic parameters during STS tasks. Results: There was no significant difference in task duration between the two groups. Patients with KOA could perform a greater range of pelvic motion and smaller range of hip and knee joint motion with a lower maximum hip joint angular acceleration in the sagittal plane and greater knee and ankle joint motion in the coronal plane. There was no significant difference in the motion range in the horizontal plane. During the STS task, patients in the KOA group had a lower vertical ground reaction force (GRF) amplitude on the injured side but a higher integrated GRF on both sides than those in the control group. Moreover, patients with KOA demonstrated higher PERM and PABM of the lower limb joints and smaller knee PADM and ankle PEM. Additionally, maximum activation levels of GMed muscle, affected-side gluteus medius (GM), ST, rectus femoris (RF), and tibialis anterior (TA) muscles were lower in patients with KOA than in controls. Conversely, the activation level of biceps femoris (BF) was higher. Furthermore, the integral EMG values of GMed, GM, ST, VL, RF, vastus medialis VM, and TA muscles on the affected side were lower, except for the BF muscle, in patients with KOA. Conclusion: Compared with the participants in the control group, patients with early-stage KOA exhibited consistent changes in sEMG parameters and biomechanical alterations in the sagittal plane, as observed in previous studies. However, differences in parameters were observed in the coronal and transverse planes of these patients. The noninvasive analysis of the 3D parameters of the involved motion patterns may lead to the early detection of KOA.

A Real-Time Control Method for Upper Limb Exoskeleton Based on Active Torque Prediction Model

Exoskeleton rehabilitation robots have been widely used in the rehabilitation treatment of stroke patients. Clinical studies confirmed that rehabilitation training with active movement intentions could improve the effectiveness of rehabilitation treatment significantly. This research proposes a real-time control method for an upper limb exoskeleton based on the active torque prediction model. To fulfill the goal of individualized and precise rehabilitation, this method has an adjustable parameter assist ratio that can change the strength of the assist torque under the same conditions. In this study, upper limb muscles' EMG signals and elbow angle were chosen as the sources of control signals. The active torque prediction model was then trained using a BP neural network after appropriately extracting features. The model exhibited good accuracy on PC and embedded systems, according to the experimental results. In the embedded system, the RMSE of this model was 0.1956 N·m and 94.98%. In addition, the proposed real-time control system also had an extremely low delay of only 40 ms, which would significantly increase the adaptability of human-computer interactions.

Clinician perspectives on the development of a web portal for remote monitoring of mHealth facilitated dysphagia home exercise: A qualitative study

PURPOSE

Mobile health (mHealth) technologies for dysphagia management may allow patients to complete rehabilitation exercises from home and their clinicians to remotely monitor them. However, clinicians are rarely formally consulted in the early stages of ideation. This study aimed to determine necessary elements to be included in a clinician web portal that would allow for remote monitoring of patients completing dysphagia exercises using mHealth equipped with surface electromyography (sEMG).

METHOD

Ten dysphagia clinicians were consulted individually using convergent interviewing. Interviews were transcribed and analysed using thematic analysis to identify themes and sub-themes.

RESULT

Themes identified included: perceived benefits of an mHealth system; clinical uptake of an mHealth system; clinical targets desired; preferred communication method; notification style and frequency; and user interface considerations. There was no consensus regarding clinical targets to display, notification frequency, method of clinician-patient communication, or layout for the user interface. Agreement existed on the importance of the simplicity and customisability for the clinician web portal user interface.

CONCLUSION

Lack of consensus on specific elements to be included in a clinician web portal could reflect low clinical exposure to sEMG. This study provides an example of formal end user feedback in the ideation phase of design.

The assistance of BAZAR robot promotes improved upper limb motor coordination in workers performing an actual use-case manual material handling

This study aims at evaluating upper limb muscle coordination and activation in workers performing an actual use-case manual material handling (MMH). The study relies on the comparison of the workers' muscular activity while they perform the task, with and without the help of a dual-arm cobot (BAZAR). Eleven participants performed the task and the flexors and extensors muscles of the shoulder, elbow, wrist, and trunk joints were recorded using bipolar electromyography. The results showed that, when the particular MMH was carried out with BAZAR, both upper limb and trunk muscular co-activation and activation were decreased. Therefore, technologies that enable human-robot collaboration (HRC), which share a workspace with employees, relieve employees of external loads and enhance the effectiveness and calibre of task completion. Additionally, these technologies improve the worker's coordination, lessen the physical effort required to interact with the robot, and have a favourable impact on his or her physiological motor strategy. Practitioner summary: Upper limb and trunk muscle co-activation and activation is reduced when a specific manual material handling was performed with a cobot than without it. By improving coordination, reducing physical effort, and changing motor strategy, cobots could be proposed as an ergonomic intervention to lower workers' biomechanical risk in industry.

A comparative study to evaluate abdominal wall dynamics in patients with incisional hernia compared to healthy controls

BACKGROUND

Incisional hernia is a common complication following abdominal surgery. It causes change in function of core abdominal muscles leading to change in abdominal wall dynamics. This study aims to objectively measure and compare preoperative abdominal wall dynamics with surface electromyography (sEMG) in incisional hernia patients with healthy individuals.

MATERIALS AND METHODS

In this prospective comparative study, two groups of participants as cases and controls were evaluated for their abdominal wall dynamics by using sEMG. Both cases and controls were evenly matched in terms of age and gender. Statistical analysis was done with STATA 14.1 and p value of < 0.05 was considered significant.

RESULTS

Demographic profile was comparable between the two groups. Mean BMI of cases was higher than controls. The most common index procedure was lower segment cesarean section. The strength and power of all three abdominal wall muscles (rectus abdominis, external oblique, internal oblique) were significantly diminished among cases compared to controls.

CONCLUSIONS

Abdominal wall dynamics can be objectively and correctly interpreted from sEMG of abdominal wall core muscles in patients with incisional hernia. This study shows that there is a decrease in abdominal wall strength and power in patients suffering from incisional hernia in comparison with healthy controls.

Effect of physiotherapeutic procedures on the bioelectric activity of the masseter muscle and the range of motion of the temporomandibular joints in the female population with chronic pain: a randomized controlled trial

INTRODUCTION

Physical therapy (PT) methods applied in dentistry are increasingly discussed nowadays. Taking into account a rapidly growing number of temporomandibular disorders (TMDs) and orofacial pain patients, it is reasonable to determine which of the available physiotherapeutic (PT) methods are more effective than others, especially in terms of their possible analgesic and myorelaxant effects.

OBJECTIVE

To assess manual and physical factors influencing pain reduction or elimination and increased muscle tension in patients with TMD; yet the influence of the applied forms of PT on the range of motion (ROM) of temporomandibular joints (TMJ).

MATERIAL AND METHODS

A randomized, parallel-group, RCT, single-blind, equi-randomized (1:1) study was conducted in DC/TMD Group Ib patients (20-45 years of age). An experimental group (G1, n = 104) and a control group without TMD (G2, n = 104) were created according to CONSORT guidelines. Diagnostic measurements were performed in both groups (mass sEMG, temporomandibular joint range of motion-ROM, pain intensity - NRS). Group G1 was randomly divided (envelope method) into 4 therapeutic groups, in which therapy was carried out for 10 days: magnetostimulation (MS), magnetoledotherapy (MLE), magnetolaserotherapy (MLA), manual therapy (MT). Each time after the therapy, ROM and NRS measurements were performed, and after the 5th and 10th day sEMG.

RESULTS

Statistically significant differences were found in the sEMG values of the masseter muscles, TMJ ROM and the pain intensity in G1 and G2 (p < 0.00). The largest decrease in sEMG (% MVC) of the masseter muscle occurred in the subgroup in which the manual therapy (MT) procedures were applied, p < 0.000. There was no clinically significant difference in and between other subgroups. There was a distinct mandible ROM increase noted in the MT group, with minimal changes in the MLA and MLE groups and no changes in the MS group. There was a clear increase in the lateral mobility of both right and left TMJ in the MT group. There were no differences in the course of the study in the MS group, and slight increases in the MLA and MLE groups. In the case of pain measurements, the greatest decrease in pain intensity was observed in the MT subgroup.

CONCLUSIONS

According to our results manual therapy is an effective form of treatment in patients with pain, increased masticatory muscle tension and limitation in mandible ROM. Dental physiotherapy should become an integral part of multimodal TMD patients' treatment.

Synthesis of sEMG Signals for Hand Gestures Using a 1DDCGAN

The emergence of modern prosthetics controlled by bio-signals has been facilitated by AI and microchip technology innovations. AI algorithms are trained using sEMG produced by muscles during contractions. The data acquisition procedure may result in discomfort and fatigue, particularly for amputees. Furthermore, prosthetic companies restrict sEMG signal exchange, limiting data-driven research and reproducibility. GANs present a viable solution to the aforementioned concerns. GANs can generate high-quality sEMG, which can be utilised for data augmentation, decrease the training time required by prosthetic users, enhance classification accuracy and ensure research reproducibility. This research proposes the utilisation of a one-dimensional deep convolutional GAN (1DDCGAN) to generate the sEMG of hand gestures. This approach involves the incorporation of dynamic time wrapping, fast Fourier transform and wavelets as discriminator inputs. Two datasets were utilised to validate the methodology, where five windows and increments were utilised to extract features to evaluate the synthesised sEMG quality. In addition to the traditional classification and augmentation metrics, two novel metrics-the Mantel test and the classifier two-sample test-were used for evaluation. The 1DDCGAN preserved the inter-feature correlations and generated high-quality signals, which resembled the original data. Additionally, the classification accuracy improved by an average of 1.21-5%.

Adaptations in equine axial movement and muscle activity occur during induced fore- and hindlimb lameness: A kinematic and electromyographic evaluation during in-hand trot

BACKGROUND

The inter-relationship between equine thoracolumbar motion and muscle activation during normal locomotion and lameness is poorly understood.

OBJECTIVE

To compare thoracolumbar and pelvic kinematics and longissimus dorsi (longissimus) activity of trotting horses between baseline and induced forelimb (iFL) and hindlimb (iHL) lameness.

STUDY DESIGN

Controlled experimental cross-over study.

METHODS

Three-dimensional kinematic data from the thoracolumbar vertebrae and pelvis, and bilateral surface electromyography (sEMG) data from longissimus at T14 and L1, were collected synchronously from clinically nonlame horses (n = 8) trotting overground during a baseline evaluation, and during iFL and iHL conditions (2-3/5 AAEP), induced on separate days using a lameness model (modified horseshoe). Motion asymmetry parameters, maximal thoracolumbar flexion/extension and lateral bending angles, and pelvis range of motion (ROM) were calculated from kinematic data. Normalised average rectified value (ARV) and muscle activation onset, offset and activity duration were calculated from sEMG signals. Mixed model analysis and statistical parametric mapping compared discrete and continuous variables between conditions (α = 0.05).

RESULTS

Asymmetry parameters reflected the degree of iFL and iHL. Maximal thoracolumbar flexion and pelvis pitch ROM increased significantly following iFL and iHL. During iHL, peak lateral bending increased towards the nonlame side (NLS) and decreased towards the lame side (LS). Longissimus ARV significantly increased bilaterally at T14 and L1 for iHL, but only at LS L1 for iFL. Longissimus activation was significantly delayed on the NLS and precipitated on the LS during iHL, but these clear phasic shifts were not observed in iFL.

MAIN LIMITATIONS

Findings should be confirmed in clinical cases.

CONCLUSIONS

Distinctive, significant adaptations in thoracolumbar and pelvic motion and underlying longissimus activity occur during iFL and iHL and are detectable using combined motion capture and sEMG. For iFL, these adaptations occur primarily in a cranio-caudal direction, whereas for iHL, lateral bending and axial rotation are also involved.

Design and Analysis of an Upper Limb Rehabilitation Robot Based on Multimodal Control

To address the rehabilitation needs of upper limb hemiplegic patients in various stages of recovery, streamline the workload of rehabilitation professionals, and provide data visualization, our research team designed a six-degree-of-freedom upper limb exoskeleton rehabilitation robot inspired by the human upper limb's structure. We also developed an eight-channel synchronized signal acquisition system for capturing surface electromyography (sEMG) signals and elbow joint angle data. Utilizing Solidworks, we modeled the robot with a focus on modularity, and conducted structural and kinematic analyses. To predict the elbow joint angles, we employed a back propagation neural network (BPNN). We introduced three training modes: a PID control, bilateral control, and active control, each tailored to different phases of the rehabilitation process. Our experimental results demonstrated a strong linear regression relationship between the predicted reference values and the actual elbow joint angles, with an R-squared value of 94.41% and an average error of four degrees. Furthermore, these results validated the increased stability of our model and addressed issues related to the size and single-mode limitations of upper limb rehabilitation robots. This work lays the theoretical foundation for future model enhancements and further research in the field of rehabilitation.

Sign Language Recognition Using the Electromyographic Signal: A Systematic Literature Review

The analysis and recognition of sign languages are currently active fields of research focused on sign recognition. Various approaches differ in terms of analysis methods and the devices used for sign acquisition. Traditional methods rely on video analysis or spatial positioning data calculated using motion capture tools. In contrast to these conventional recognition and classification approaches, electromyogram (EMG) signals, which measure muscle electrical activity, offer potential technology for detecting gestures. These EMG-based approaches have recently gained attention due to their advantages. This prompted us to conduct a comprehensive study on the methods, approaches, and projects utilizing EMG sensors for sign language handshape recognition. In this paper, we provided an overview of the sign language recognition field through a literature review, with the objective of offering an in-depth review of the most significant techniques. These techniques were categorized in this article based on their respective methodologies. The survey discussed the progress and challenges in sign language recognition systems based on surface electromyography (sEMG) signals. These systems have shown promise but face issues like sEMG data variability and sensor placement. Multiple sensors enhance reliability and accuracy. Machine learning, including deep learning, is used to address these challenges. Common classifiers in sEMG-based sign language recognition include SVM, ANN, CNN, KNN, HMM, and LSTM. While SVM and ANN are widely used, random forest and KNN have shown better performance in some cases. A multilayer perceptron neural network achieved perfect accuracy in one study. CNN, often paired with LSTM, ranks as the third most popular classifier and can achieve exceptional accuracy, reaching up to 99.6% when utilizing both EMG and IMU data. LSTM is highly regarded for handling sequential dependencies in EMG signals, making it a critical component of sign language recognition systems. In summary, the survey highlights the prevalence of SVM and ANN classifiers but also suggests the effectiveness of alternative classifiers like random forests and KNNs. LSTM emerges as the most suitable algorithm for capturing sequential dependencies and improving gesture recognition in EMG-based sign language recognition systems.

Vibration comfort assessment of tractor drivers based on sEMG and vibration signals

In order to comprehensively evaluate the driver's vibration comfort under different vibration conditions, eighteen subjects were required to drive a tractor at different speeds on field and asphalt roads respectively in the real vehicle experiment. The sEMG signals and vibration acceleration signals of the subjects were recorded. And the time-frequency domain analysis of sEMG signals and acceleration signals were used to determine the relationship among the characteristic indexes, tractor speed and road surfaces. The relevance analysis showed that there was a significant correlation between the integral electromyography (iEMG) and median frequency (MF) of the middle scalene muscle, erector spinae muscle and gastrocnemius muscle, the RMS of weighted acceleration (aw) of the neck, waist and legs, and the subjective comfort feelings. It was proven that the tractor speed had a significant impact on human body vibration based on the ANOVA result (p < 0.05). With the increase of running speed, the time domain indexes of sEMG signals including iEMG, RMS and the vibration acceleration signals of the testing body parts increased significantly, while the amplitudes of frequency domain indexes decreased. Therefore, a quantitative regression evaluation model for the comfort of the neck, waist and legs integrating the sEMG and vibration signals was established, and its relative errors were 5.05, 4.38 and 6.12% respectively. This proposed assessment model can combine characteristics of the partial and overall vibration response of human body effectively, predict the tractor driver's vibration comfort accurately, provide a theoretical basis for the evaluation of tractor cab vibration comfort.

Dynamic CT scanning of the knee: Combining weight bearing with real-time motion acquisition

BACKGROUND

Imaging the lower limb during weight-bearing conditions is essential to acquire advanced functional joint information. The horizontal bed position of CT systems however hinders this process. The purpose of this study was to validate and test a device to simulate realistic knee weight-bearing motion in a horizontal position during dynamic CT acquisition and process the acquired images.

METHODS

"Orthostatic squats" was compared to "Horizontal squats" on a device with loads between 35% and 55% of the body weight (%BW) in 20 healthy volunteers. Intraclass Correlation Coefficient (ICC), and standard error of measurement (SEM), were computed as measures of the reliability of curve kinematic and surface EMG (sEMG) data. Afterwards, the device was tested during dynamic CT acquisitions on three healthy volunteers and three patients with patellofemoral pain syndrome. The respective images were processed to extract Tibial-Tuberosity Trochlear-Groove distance, Bisect Offset and Lateral Patellar Tilt metrics.

RESULTS

For sEMG, the highest average ICCs (SEM) of 0.80 (6.9), was found for the load corresponding to 42%BW. Kinematic analysis showed ICCs were the highest for loads of 42%BW during the eccentric phase (0.79-0.87) and from maximum flexion back to 20° (0.76). The device proved to be safe and reliable during the acquisition of dynamic CT images and the three metrics were computed, showing preliminary differences between healthy and pathological participants.

CONCLUSIONS

This device could simulate orthostatic squats in a horizontal position with good reliability. It also successfully provided dynamic CT scan images and kinematic parameters of healthy and pathological knees during weight-bearing movement.

Surface electromyographic frequency characteristics of the quadriceps differ between continuous high- and low-torque isometric knee extension to momentary failure

Surface EMG (sEMG) has been used to compare loading conditions during exercise. Studies often explore mean/median frequencies. This potentially misses more nuanced electrophysiological differences between exercise tasks. Therefore, wavelet-based analysis was used to evaluate electrophysiological characteristics in the sEMG signal of the quadriceps under both higher- and lower-torque (70 % and 30 % of MVC, respectively) isometric knee extension performed to momentary failure. Ten recreationally active adult males with previous resistance training experience were recruited. Using a within-session, repeated-measures, randomised crossover design, participants performed isometric knee extension whilst sEMG was collected from the vastus medialis (VM), rectus femoris (RF) and vastus lateralis (VL). Mean signal frequency showed similar characteristics in each condition at momentary failure. However, individual wavelets revealed different frequency component changes between the conditions. All frequency components increased during the low-torque condition. But low-frequency components increased, and high-frequency components decreased, in intensity throughout the high-torque condition. This resulted in convergence of the low-torque and high-torque trial wavelet characteristics towards the end of the low-torque trial. Our results demonstrate a convergence of myoelectric signal properties between low- and high-torque efforts with fatigue via divergent signal adaptations. Further work should disentangle factors influencing frequency characteristics during exercise tasks.

Movement recognition via channel-activation-wise sEMG attention

CONTEXT

Surface electromyography (sEMG) signals contain rich information recorded from muscle movements and therefore reflect the user's intention. sEMG has seen dominant applications in rehabilitation, clinical diagnosis as well as human engineering, etc. However, current feature extraction methods for sEMG signals have been seriously limited by their stochasticity, transiency, and non-stationarity.

OBJECTIVE

Our objective is to combat the difficulties induced by the aforementioned downsides of sEMG and thereby extract representative features for various downstream movement recognition.

METHOD

We propose a novel 3-axis view of sEMG features composed of temporal, spatial, and channel-wise summary. We leverage the state-of-the-art architecture Transformer to enforce efficient parallel search and to get rid of limitations imposed by previous work in gesture classification. The transformer model is designed on top of an attention-based module, which allows for the extraction of global contextual relevance among channels and the use of this relevance for sEMG recognition.

RESULTS

We compared the proposed method against existing methods on two Ninapro datasets consisting of data from both healthy people and amputees. Experimental results show the proposed method attains the state-of-the-art (SOTA) accuracy on both datasets. We further show that the proposed method enjoys strong generalization ability: a new SOTA is achieved by pretraining the model on a different dataset followed by fine-tuning it on the target dataset.

A Global and Local Feature fused CNN architecture for the sEMG-based hand gesture recognition

Deep learning methods have been widely used for the classification of hand gestures using sEMG signals. Existing deep learning architectures only captures local spatial information and has limitations in extracting global temporal dependency to enhance the model's performance. In this paper, we propose a Global and Local Feature fused CNN (GLF-CNN) model that extracts features both globally and locally from sEMG signals to enhance the performance of hand gestures classification. The model contains two independent branches extracting local and global features each and fuses them to learn more diversified features and effectively improve the stability of gesture recognition. Besides, it also exhibits lower computational cost compared to the present approaches. We conduct experiments on five benchmark databases, including the NinaPro DB4, NinaPro DB5, BioPatRec DB1-DB3, and the Mendeley Data. The proposed model achieved the highest average accuracy of 88.34% on these databases, with a 9.96% average accuracy improvement and a 50% reduction in variance compared to the models with the same number of parameters. Moreover, the classification accuracies for the BioPatRec DB1, BioPatRec DB3 and Mendeley Data are 91.4%, 91.0% and 88.6% respectively, corresponding to an improvement of 13.2%, 41.5% and 12.2% over the respective state-of-the-art models. The experimental results demonstrate that the proposed model effectively enhances robustness, with improved gesture recognition performance and generalization ability. It contributes a new way for prosthetic control and human-machine interaction.

Evaluation of the efficacy of manual soft tissue therapy and therapeutic exercises in patients with pain and limited mobility TMJ: a randomized control trial (RCT)

The limited number of randomized controlled trials (RCTs) comparing the efficacy of soft tissue manual therapy and self-therapy interventions prompted the authors to focus on the analgesic and myorelaxant use of massage, post-isometric muscle relaxation (PIR) and therapeutic exercise in TMD patients.

OBJECTIVES

To evaluate the effectiveness of soft tissue therapy and therapeutic exercises in female patients with pain, increased masseter muscle tension and limited mandibular mobility.

MATERIAL AND METHODS

The study was conducted on a group of 82 women (G1) with the Ib disorder diagnosed in DC/TMD (Ib-myofascial pain with restricted mobility). The control group (G2) consisted of 104 women without diagnosed TMDs (normal reference values for TMJ ROM and masseter muscle sEMG bioelectric activity). Diagnostic procedures were performed in both groups (sEMG of the masseter muscles at baseline and during exercise, measurement of TMJ mobility, assessment of pain intensity-NRS scale). The G1 group was randomly divided into 3 therapeutic groups in which the therapy was carried out for 10 days: therapeutic exercises (TE), manual therapy - massage and therapeutic exercises (MTM_TE), manual therapy - PIR and therapeutic exercises (MTPIR_TE). Each time after therapy, the intensity of pain and TMJ mobility were assessed. Sealed, opaque envelopes were used for randomization. After 5 and 10 days of therapy, bilateral sEMG signals of the masseter muscles were acquired.

RESULTS

Massage, PIR and self-therapy led to a decrease in sEMG at rest as well as in exercise. After day 6 of therapy, the groups obtained a significant difference (p = 0.0001). Each of the proposed forms of therapy showed a minimal clinically significant difference (MID) in the sEMG parameter at the endpoint, with the most considerable difference in the MTM_TE group. The forms of MT used were effective in reducing the patients' pain intensity; however, a significant difference between therapies occurred after 4 treatments (p = 0.0001). Analyzing the MID between methods, it was observed that self-therapy had an analgesic effect only after 8 treatments, while PIR after 3 and massage after 1 treatment. After day 7, the mean pain score in the MTM_TE group was 0.889 and in the TMPIR_TE group was 3.44 on the NRS scale. In terms of MMO, a significant difference was obtained between monotherapy and each form of TM, i.e. massage (p = 0.0001) and PIR (p = 0.0001). Analyzing mandibular lateral movements, the authors got a significant difference in the proposed MT forms, of which massage treatments exceeded the effectiveness of PIR.

CONCLUSIONS

Soft tissue manual therapy and therapeutic exercise are simple and safe interventions that can potentially benefit patients with myogenic TMDs, with massage showing better analgesic effects than PIR.

Continuous online prediction of lower limb joints angles based on sEMG signals by deep learning approach

Continuous online prediction of human joints angles is a key point to improve the performance of man-machine cooperative control. In this study, a framework of online prediction method of joints angles by long short-term memory (LSTM) neural network only based on surface electromyography (sEMG) signals was proposed. The sEMG signals from eight muscles of five subjects' right leg and three joints angles and plantar pressure signals of subjects were collected simultaneously. Different inputs (only sEMG (unimodal), sEMG combined with plantar pressure (multimodal)) after online feature extraction and standardization were used for training the angle online prediction model by LSTM. The results indicate that there is no significant difference between the two kinds of inputs for LSTM model and the proposed method can make up for the shortage of using a single type of sensor. The range of mean values of root square mean error, mean absolute error and Pearson correlation coefficient of the three joints angles achieved by the proposed model only with the input of sEMG under four kinds of predicted time (50, 100, 150, and 200 ms) are [1.63°,3.20°],[1.27°, 2.36°] and [0.9747, 0.9935]. Three popular machine learning algorithms with different inputs were compared to the proposed model only based on sEMG. Experiment results demonstrate that the proposed method has the best prediction performance and there are highly significant differences between it and other methods. The difference of prediction results under different gait phases by the proposed method was also analyzed. The results indicate that the prediction effect of support phases is generally better than that of swing phases. Above experimental results show that the proposed method can realize accurate online joint angle prediction and has better performance to promote man-machine cooperation.

A Smartphone-Based sEMG Signal Analysis System for Human Action Recognition

In lower-limb rehabilitation, human action recognition (HAR) technology can be introduced to analyze the surface electromyography (sEMG) signal generated by movements, which can provide an objective and accurate evaluation of the patient's action. To balance the long cycle required for rehabilitation and the inconvenient factors brought by wearing sEMG devices, a portable sEMG signal acquisition device was developed that can be used under daily scenarios. Additionally, a mobile application was developed to meet the demand for real-time monitoring and analysis of sEMG signals. This application can monitor data in real time and has functions such as plotting, filtering, storage, and action capture and recognition. To build the dataset required for the recognition model, six lower-limb motions were developed for rehabilitation (kick, toe off, heel off, toe off and heel up, step back and kick, and full gait). The sEMG segment and action label were combined for training a convolutional neural network (CNN) to achieve high-precision recognition performance for human lower-limb actions (with a maximum accuracy of 97.96% and recognition accuracy for all actions reaching over 97%). The results show that the smartphone-based sEMG analysis system proposed in this paper can provide reliable information for the clinical evaluation of lower-limb rehabilitation.

Analysis of Ankle Muscle Dynamics during the STS Process Based on Wearable Sensors

Ankle joint moment is an important indicator for evaluating the stability of the human body during the sit-to-stand (STS) movement, so a method to analyze ankle joint moment is needed. In this study, a wearable sensor system that could derive surface-electromyography (sEMG) signals and kinematic signals on the lower limbs was developed for non-invasive estimation of ankle muscle dynamics during the STS movement. Based on the established ankle joint musculoskeletal information and sEMG signals, ankle joint moment during the STS movement was calculated. In addition, based on a four-segment STS dynamic model and kinematic signals, ankle joint moment during the STS movement was calculated using the inverse dynamics method. Ten healthy young people participated in the experiment, who wore a self-developed wearable sensor system and performed STS movements as an experimental task. The results showed that there was a high correlation (all R ≥ 0.88) between the results of the two methods for estimating ankle joint moment. The research in this paper can provide theoretical support for the development of an intelligent bionic joint actuator and clinical rehabilitation evaluation.

The Effect of Asymmetrical Occlusion on Surface Electromyographic Activity in Subjects with a Chewing Side Preference: A Preliminary Study

The relationship between asymmetrical occlusion and surface electromyographic activity (sEMG) in people with different chewing preferences is not clear. In this study, the 5 s sEMG changes in the masseter muscle (MM), sternocleidomastoid (SCM), lateral (LGA), and medial (MGA) gastrocnemius muscles were recorded in controls, and subjects with chewing side preference (CSP) during clench with bilateral (BCR), left (LCR), and right (RCR) posterior teeth placement of cotton rolls. The images of the middle 3 s were selected and expressed as the root mean square (unit: μV/s). The EMG waves of bilateral muscles were compared by computing the percentage overlapping coefficient (POC). Only the POCMM of the CSP showed gender differences at BCR and RCR. Between the control group and the CSP group, there were significant differences in the POCMM and the POCLGA at BCR. In addition, there was a significant difference in POCMM and POCSCM between the two populations in different occlusal positions. The change in the POCSCM correlated with the change in the POCMM (r = 0.415, p = 0.018). The experiment-induced asymmetrical occlusion showed that the altered symmetry of the MM correlated with the altered symmetry of the SCM. Long-term asymmetrical occlusion (i.e., CSP) not only affects MM but also has potential effects on other superficial muscles (e.g., LGA).

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.

Electromyographic and Kinematic Comparison of the Leading and Trailing Fore- and Hindlimbs of Horses during Canter

This study compared muscle activity and movement between the leading (Ld) and trailing (Tr) fore- (F) and hindlimbs (H) of horses cantering overground. Three-dimensional kinematic and surface electromyography (sEMG) data were collected from right triceps brachii, biceps femoris, middle gluteal, and splenius from 10 ridden horses during straight left- and right-lead canter. Statistical parametric mapping evaluated between-limb (LdF vs. TrF, LdH vs. TrH) differences in time- and amplitude-normalized sEMG and joint angle-time waveforms over the stride. Linear mixed models evaluated between-limb differences in discrete sEMG activation timings, average rectified values (ARV), and spatio-temporal kinematics. Significantly greater gluteal ARV and activity duration facilitated greater limb retraction, hip extension, and stifle flexion (p < 0.05) in the TrH during stance. Earlier splenius activation during the LdF movement cycle (p < 0.05), reflected bilateral activation during TrF/LdH diagonal stance, contributing to body pitching mechanisms in canter. Limb muscles were generally quiescent during swing, where significantly greater LdF/H protraction was observed through greater elbow and hip flexion (p < 0.05), respectively. Alterations in muscle activation facilitate different timing and movement cycles of the leading and trailing limbs, which justifies equal training on both canter leads to develop symmetry in muscular strength, enhance athletic performance, and mitigate overuse injury risks.

A low-cost and portable wrist exoskeleton using EEG-sEMG combined strategy for prolonged active rehabilitation

Introduction

Hemiparesis is a common consequence of stroke that severely impacts the life quality of the patients. Active training is a key factor in achieving optimal neural recovery, but current systems for wrist rehabilitation present challenges in terms of portability, cost, and the potential for muscle fatigue during prolonged use.

Methods

To address these challenges, this paper proposes a low-cost, portable wrist rehabilitation system with a control strategy that combines surface electromyogram (sEMG) and electroencephalogram (EEG) signals to encourage patients to engage in consecutive, spontaneous rehabilitation sessions. In addition, a detection method for muscle fatigue based on the Boruta algorithm and a post-processing layer are proposed, allowing for the switch between sEMG and EEG modes when muscle fatigue occurs.

Results

This method significantly improves accuracy of fatigue detection from 4.90 to 10.49% for four distinct wrist motions, while the Boruta algorithm selects the most essential features and stabilizes the effects of post-processing. The paper also presents an alternative control mode that employs EEG signals to maintain active control, achieving an accuracy of approximately 80% in detecting motion intention.

Discussion

For the occurrence of muscle fatigue during long term rehabilitation training, the proposed system presents a promising approach to addressing the limitations of existing wrist rehabilitation systems.

An Evaluation Study of a New Designed Oscillating Hydraulic Trainer of Neck

In view of the importance of neck strength training and the lack of adequate training equipment, this study designed a new oscillating hydraulic trainer (OHT) of neck based on oscillating hydraulic damper. We used surface electromyography (sEMG) and subjective ratings to evaluate the neck OHT and compared the results with a simple hat trainer (HATT) and traditional weight trainer (TWT) to verify the feasibility and validity of the OHT. Under similar exercise conditions, 12 subjects performed a set of neck flexion and extension exercise with these 3 trainers. The sEMG signals of targeted muscles were collected in real time, and subjects were asked to complete subjective evaluations of product usability after exercise. The results showed that the root mean square (RMS%) of sEMG indicated that the OHT could provide two-way resistance and train the flexors and extensors simultaneously. The overall degree of muscle activation with OHT was higher than that with the other two trainers in one movement cycle. In terms of resistance characteristics exhibited by the sEMG waveform, duration (D) with OHT was significantly longer than HATT and TWT when exercising at a high speed, while Peak Timing (PT) was later. The ratings of product usability and performing usability of OHT were remarkably higher than that of HATT and TWT. Based on the above results, the OHT was proved to be more suitable for strength training, such as neck muscles, which were getting more attention gradually, but lacked mature and special training equipment.

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.

Evaluation of Novel Embroidered Textile-Electrodes Made from Hybrid Polyamide Conductive Threads for Surface EMG Sensing

Recently, there has been an increase in the number of reports on textile-based dry electrodes that can detect biopotentials without the need for electrolytic gels. However, these textile electrodes have a higher electrode skin interface impedance due to the improper contact between the skin and the electrode, diminishing the reliability and repeatability of the sensor. To facilitate improved skin-electrode contact, the effects of load and holding contact pressure were monitored for an embroidered textile electrode composed of multifilament hybrid thread for its application as a surface electromyography (sEMG) sensor. The effect of the textile's inter-electrode distance and double layering of embroidery that increases the density of the conductive threads were studied. Electrodes embroidered onto an elastic strap were wrapped around the forearm with a hook and loop fastener and tested for their performance. Time domain features such as the Root Mean Square (RMS), Average Rectified Value (ARV), and Signal to Noise Ratio (SNR) were quantitatively monitored in relation to the contact pressure and load. Experiments were performed in triplicates, and the sEMG signal characteristics were observed for various loads (0, 2, 4, and 6 kg) and holding contact pressures (5, 10, and 20 mmHg). sEMG signals recorded with textile electrodes were comparable in amplitude to those recorded using typical Ag/AgCl electrodes (28.45 dB recorded), while the signal-to-noise ratios were, 11.77, 19.60, 19.91, and 20.93 dB for the different loads, and 21.33, 23.34, and 17.45 dB for different holding pressures. The signal quality increased as the elastic strap was tightened further, but a pressure higher than 20 mmHg is not recommended because of the discomfort experienced by the subjects during data collection.

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.

Evaluation of Posturographic and Neuromuscular Parameters during Upright Stance and Hand Standing: A Pilot Study

Upright bipedal posture is the physiological human posture; however, it is not the only possible form of human standing; indeed, an inverted position, a handstand, is required during gymnastics or other sports. Thus, this study aimed to understand the differences between the two standing strategies from a postural and neuromuscular perspective. Thirteen gymnasts with at least three years of sports experience underwent a baropodometric assessment and a surface electromyography (sEMG) examination in a standard upright bipodalic stance and during a handstand. The sEMG examination was performed on the gastrocnemius during an upright stance and on the flexor carpi radialis during the handstand. Limb weight distribution presented differences between the two vertical stances (p < 0.01). During the handstand, the weight ratio was prevalently observed on the palm of the hand for both hands with a significant difference between the front and rear aspect of the hand compared to the standing tasks (p < 0.01). Normalized sEMG amplitude showed significant differences during bipedal standing and hand standing; however, over a 5 s period, the normalized median frequency (MDF) value was similar for the two tasks. Both standing tasks presented similar postural weight managing patterns when analysed on the frontal plane, but they were different on the sagittal plane. In addition, the neuromuscular patterns during a 5 s window differ in amplitude but not for the frequency domain.

Exploratory Study on Central Sensitization and Bioelectrical Activity of the Selected Masticatory Muscles in Subjects with Myopia

BACKGROUND

Myopia is one of the most common eye disorders involving abnormal focusing of light rays. The studies recognize the association between the stomatognathic and visual systems. This compound may have a neurological basis associated with disorders such as central sensitization. The main aim of this study was to evaluate the influence of central sensitization on the bioelectrical activity of selected muscles of the masticatory organ in subjects with myopia.

METHODS

Selected masticatory and cervical spine muscles were analyzed using an eight-channel BioEMG III electromyograph. Central sensitization was analyzed using the central sensitization inventory.

RESULTS

Statistical analysis revealed significantly higher scores on the central sensitization inventory in subjects with axial myopia compared to subjects without refractive error. Repeated positive correlations were observed in the sternocleidomastoid muscle activity and negative correlations in the digastric muscle activity during open and closed eyes in myopic subjects.

CONCLUSIONS

Subjects with myopia have an increased score in the central sensitization inventory. The increase in the central sensitization inventory score is connected with the changes within the electromyographic activity of the masticatory and neck muscles. The effect of central sensitization on masticatory muscle activity in myopic subjects requires further study.

Underwater Surface Electromyography for the Evaluation of Muscle Activity during Front Crawl Swimming: A Systematic Review

This systematic review is aimed to provide an up-to-date summary and review on the use of surface electromyography (sEMG) in evaluating front crawl (FC) swim performance. Several online databases were searched by different combinations of selected keywords, in total 1956 articles were retrieved, and each article was assessed by a 10-item quality checklist. 16 articles were eligible to be included in this study, and most of the articles were evaluating the muscle activity about the swimming phases and focused on assessing the upper limbs muscles, only few studies have assessed the performance in starts and turns phases. Insufficient information about these two phases despite the critical contribution on final swimming time. Also, with the contribution roles of legs and trunk muscles in swimming performance, more research should be conducted to explore the overall muscle activation pattern and their roles on swimming performance. Moreover, more detailed description in participants' characteristics and more investigations of bilateral muscle activity and the asymmetrical effects on relevant biomechanical performance are recommended. Lastly, with increasing attention about the effects of muscles co-activation on swimming performance, more in-depth investigations on this topic are also highly recommended, for evaluating its influence on swimmers.

A multidimensional sensory evaluation model to investigate the (dis)comfort of body parts in a supine sitting position during a lunch break

Employees who work long hours frequently complain of muscle fatigue caused by prolonged sitting. As a result, products that assist them when resting in a chair in a reclining position, in order to relieve fatigue and improve comfort are required. To ensure that the new product works as intended, a usability test based on prototyping must be developed. The research process was divided into three stages: firstly, the development of the perception assessment questionnaire; secondly, a validated factor analysis (CFA) was conducted on the perception assessment data of 26 subjects and the measurement model was fitted to verify the reliability and validity of the questionnaire; finally, the sEMG technique was used to verify the comfort level of 21 subjects. Based on usability experiments and an exploration of human factor relationships, this study develops a prototype testing model, which focuses on the comfort perception of body parts, as a means of promoting innovation in the design and manufacturing industry.