Electromyography Signals Research Articles

Recent Advances of Stretchable Nanomaterial-Based Hydrogels for Wearable Sensors and Electrophysiological Signals Monitoring.

Electrophysiological monitoring is a commonly used medical procedure designed to capture the electrical signals generated by the body and promptly identify any abnormal health conditions. Wearable sensors are of great significance in signal acquisition for electrophysiological monitoring. Traditional electrophysiological monitoring devices are often bulky and have many complex accessories and thus, are only suitable for limited application scenarios. Hydrogels optimized based on nanomaterials are lightweight with excellent stretchable and electrical properties, solving the problem of high-quality signal acquisition for wearable sensors. Therefore, the development of hydrogels based on nanomaterials brings tremendous potential for wearable physiological signal monitoring sensors. This review first introduces the latest advancement of hydrogels made from different nanomaterials, such as nanocarbon materials, nanometal materials, and two-dimensional transition metal compounds, in physiological signal monitoring sensors. Second, the versatile properties of these stretchable composite hydrogel sensors are reviewed. Then, their applications in various electrophysiological signal monitoring, such as electrocardiogram monitoring, electromyographic signal analysis, and electroencephalogram monitoring, are discussed. Finally, the current application status and future development prospects of nanomaterial-optimized hydrogels in wearable physiological signal monitoring sensors are summarized. We hope this review will inspire future development of wearable electrophysiological signal monitoring sensors using nanomaterial-based hydrogels.

An Advanced Technique for the Detection of Pathological Gaits from Electromyography Signals: A Comprehensive Approach

An Advanced Technique for the Detection of Pathological Gaits from Electromyography Signals: A Comprehensive Approach

Effects of ischemic pre-conditioning on electrically stimulated contractions.

Ischemic pre-conditioning (IPC) offers protection against future ischemic events and may improve sports performance due to several mechanisms at local and systemic levels. This study investigates the local effects on muscle contractility in electrically induced muscle contractions, thus effectively excluding any uncontrolled change in the motor drive. Twenty-one subjects were divided into two groups: 12 subjects in the IPC group (3 × 5/5min right arm ischemia/reperfusion; cuff pressure 250mmHg) and 9 subjects in the SHAM group (same treatment at 20mmHg). The adductor pollicis was contracted by supramaximal stimulation of the ulnar nerve with single pulses, trains of stimuli (5, 8, 10 and 12Hz, 1-s duration) and bursts (4 pulses, 25Hz), all separated by 5-s intervals. The stimulation sequence was delivered before and 15 and 30min after IPC/SHAM treatment. The isometric contraction force, the superficial electromyographic signal, and tissue oxygenation were continuously monitored. A significant force decrease in time was observed at 8, 10 (p < 0.01) and 12Hz (p < 0.05) along with a decrease in half-relaxation time in single twitches and bursts (p = 0.01), regardless of treatment. This general time-related weakening was more marked in IPC than SHAM at 5-Hz stimulation. No effects were observed on the magnitude of the superficial electromyographic signal. Data indicate that IPC does not increase muscle force during electrically stimulated contractions, supporting the idea that IPC's ergogenic effects are not due to increased muscle contractility.

Head–neck cooling effects on central and peripheral fatigue, motor accuracy, and blood markers of stress in men with multiple sclerosis and healthy men: A randomized crossover study

BackgroundThe present study aimed to investigate whether head and neck cooling (at 18 °C next to the skin) and fatiguing submaximal exercise at a thermoneutral ambient temperature can induce peripheral and central responses in healthy men and those with multiple sclerosis (MS). MethodsA local head–neck cooling (at 18 °C next to the skin) intervention in men with a relapsing-remitting form of MS (n = 18; age 30.9 ± 8.1 years) and healthy men (n = 22; age 26.7 ± 5.9 years) was assessed. Men in both groups performed 100 intermittent isometric knee extensions with 5 s contractions and 20 s of rest. The primary variables were measured before exercise, after 50 and 100 repetitions, and 1 h after recovery. The central activation ratio, maximal voluntary contraction, electrically induced force, electromyography, contractile properties, blood markers, muscle temperature, and perception of effort were measured. ResultsCompared with noncooled conditions, head and neck cooling increased the central capacity to activate exercising muscles but resulted in greater exercise-induced peripheral fatigue in men with MS (p < 0.05). Local cooling did not affect motor accuracy or the amplitude of electromyography signals; however, these factors were related to the intensity of the motor task (p > 0.05). The changes in central and peripheral fatigability induced by local cooling during submaximal exercise were more pronounced in men with MS than in healthy men (p < 0.05). ConclusionHead and neck cooling enhances central activation of muscles during exercise, leading to improved exercise performance compared with noncooled conditions in men with MS.

Distinct Neural Drives along the Semitendinosus Muscle.

Conflicting results have been reported on the functional role of the proximal and distal compartments of the semitendinosus (ST) muscle. This study compared the discharge characteristics of motor units (MUs) in the two compartments at three knee-joint angles (0°: long length, 45°: intermediate length, and 90°: short length). Twenty men (21.4 ± 2.3 years) performed steady isometric contractions with the knee flexors at four target forces: 10%, 20%, 40%, and 60% of maximum voluntary contraction (MVC). High-density electromyography (EMG) signals were recorded to examine the MU discharge characteristics in the two compartments. Measurements included recruitment threshold (RT), mean discharge rate (MDR), coefficient of variation for interspike interval (CoV for ISI), and the standard deviation of filtered cumulative spike train (SD of fCST). Additionally, the within- and between-compartment association of the neural drive was calculated. Analysis of variance indicated that maximal force, absolute EMG amplitude during the MVCs, and force steadiness (CoV for force) were greater at the longest muscle length than the other two lengths (P < 0.05). Linear mixed models showed that both RT and CoV for ISI were similar between compartments (P > 0.05) at each of the three knee-joint angles. However, MDR and the variability in neural drive were greater for the proximal than the distal compartment (P < 0.05). The between-compartment association in neural drive (fCST) was relatively low. There were distinct differences in motor unit discharge characteristics between the proximal and distal compartments of ST across its operating range of muscle lengths and each compartment received a relatively distinct neural drive. These findings emphasize the importance of recognizing differences in neural control of the ST compartments to guide related interventions and inform rehabilitation strategies.

EVALUATION OF NECK FATIGUE CAUSED BY WEARING HELMET IN MOTION: AN ELECTROMYOGRAPHY STUDY

The increased weight of multifunction and intelligent helmet systems can cause an exacerbation of the neck workload. Further, increased weight of the helmet can reduce the wearing comfort, and prolonged use may cause neck fatigue and even neck injury. This study evaluates the fatigue of neck muscles caused by wearing a helmet in motion using electromyography (EMG) measurement. Additionally, a comprehensive evaluation model for neck fatigue was established effectively. Twenty healthy subjects were selected to run for 10[Formula: see text]min continuously in each task by wearing two different helmets, respectively, during which the EMG signals of different neck muscles and subjective scores were recorded and analyzed. Two-way repeated measures analysis of variance (ANOVA) and Pearson correlation analysis were used to obtain indicators of neck fatigue, based on which the support vector machine (SVM) was used to construct a classification model of neck fatigue. By using integral EMG (IEMG) and root mean square (RMS) for assessing the neck injury in sternocleidomastoideus and trapezius muscles, it was observed that the mean power frequency (MPF) and median frequency (MF) in trapezius and splenius capitis could be used as effective evaluation indicators of neck fatigue. The EMG activity in trapezius was the highly sensitivity to fatigue when wearing helmets in motion. The classifier for distinguishing three different neck fatigue levels was 91.67% accurate. This study demonstrates the feasibility of an EMG-based method to evaluate the neck fatigue caused by wearing a helmet in motion, and also provides an evaluation method for the optimal design of helmets in the future.

Rectus femoris electromyography signal clustering: Data-driven management of crouch gait in patients with cerebral palsy.

This study aimed to investigate how electromyography (EMG) cluster analysis of the rectus femoris (RF) could help to better interpret gait analysis in patients with cerebral palsy (CP). The retrospective gait data of CP patients were categorized into two groups: initial examination (E1, 881 patients) and subsequent examination (E2, 377 patients). Envelope-formatted EMG data of RF were collected. Using PCA and a combined PSO-K-means algorithm, main clusters were identified. Patients were further classified into crouch, jump, recurvatum, stiff and mild gait for detailed analysis. The clusters (labels) were characterized by a significant peak EMG activity during mid-swing (L1), prolonged EMG activity during stance (L2), and a peak EMG activity during loading response (L3). Notably, L2 contained 76% and 92% of all crouch patients at E1 and E2, respectively. Comparing patients with a crouch gait pattern in L2-E1 and L2-E2, two subgroups emerged: patients with persistent crouch (G1) and patients showing improvement at E2 (G2). The minimum activity of RF during 20-45% of the gait was significantly higher (p = 0.025) in G1 than in G2. A greater chance of improvement from crouch gait might be associated with lower RF activity during the stance phase. Using our findings, we could potentially establish an approach to improve clinical decision-making regarding treatment of patients with CP.

Decisional components of motor responses are not related to online response control: Evidence from lexical decision and speed-accuracy tradeoff manipulations.

Evidence suggests that decision processes can propagate to motor-response execution. However, the functional characterization of motor decisional components is not yet fully understood. By combining a classic lexical decision experiment with manipulations of speed-accuracy tradeoff (SAT), the present experiment assessed the hypothesis that decisional effects on chronometric measures of motor-response execution are related to online response control. The electromyographic (EMG) signal associated with manual button-press responses was used to dissociate the premotor component (from stimulus onset until the onset of the EMG activity) from the motor component (from EMG onset until the button-press), thus enabling the assessment of decision-related effects in terms of motor-response duration within single-trial reaction times. Other than replicating all the previously reported SAT effects, the experiment revealed hindered control processes when the instructions emphasized speed over accuracy, as indicated by measures of response control such as partial errors, fast errors, and correction likelihood. Nonetheless, the lexicality effect on motor responses, consisting of slower motor times for pseudowords compared to words, was impervious to any SAT modulation. The results suggest that SAT-induced variations in decision and response control policies may not be the prominent determinant of decision-related effects on motor times, highlighting the multiple "cognitive" components that affect peripheral response execution.

Wearable sensor technology and medical robotics for fatigue assessment using electromyography signal processing

Wearable sensor technology and medical robotics for fatigue assessment using electromyography signal processing

Anisotropic Hydrogel Microelectrodes for Intraspinal Neural Recordings in vivo.

Creating durable, motion-compliant neural interfaces is crucial for accessing dynamic tissues under in vivo conditions and linking neural activity with behaviors. Utilizing the self-alignment of nano-fillers in a polymeric matrix under repetitive tension, here, we introduce conductive carbon nanotubes with high aspect ratios into semi-crystalline polyvinyl alcohol hydrogels and create electrically anisotropic percolation pathways through cyclic stretching. The resulting anisotropic hydrogel fibers (diameter of 187 ± 13 μm) exhibit fatigue resistance (20,000 cycles at 20% strain) with a stretchability of 64.5 ± 7.9%, and low electrochemical impedance (900 ± 149 kΩ @ 1kHz). We observe the re-constructed nanofillers' axial alignment and a corresponding anisotropic impedance decrease along the direction of cyclic stretching. We fabricate fiber-shaped hydrogels into bioelectronic devices and implant them into wild-type and transgenic Thy1-ChR2-EYFP mice to record electromyographic signals from muscles in anesthetized and freely moving conditions. These hydrogel fibers effectively enable the simultaneous recording of electrical signals from ventral spinal cord neurons and the tibialis anterior muscles during optogenetic stimulation. Importantly, the devices maintain functionality with repeatable recording results over eight months after implantation, demonstrating their durability and potential for long-term monitoring in neurophysiological studies.

Performance Analysis of EMG Signal Classification Methods for Hand Gesture Recognition in Stroke Rehabilitation

This study evaluates the performance of different classification methods in classifying healthy individuals and stroke patients. The hand gesture variations of the subjects were also analyzed based on electromyography (EMG) signals. Several classification methods were tested in this analysis to find out which method had the most suitable performance. The results showed that Decision Tree and Naive Bayes classifiers achieved the highest performance in classifying EMG signals from healthy individuals and stroke patients, with both methods showing high accuracy, precision, recall, and F1 score. Specifically, Decision Tree excelled in overall accuracy and recall, while Naive Bayes showed superior precision. For hand gesture recognition, SVM, KNN, and Random Forest classifiers showed similarly high performance, achieving accuracy, precision, recall, and F1 score above 82%. Naive Bayes also performed well, especially in precision, while Decision Tree performed poorly compared to other methods. This insight can form the basis for the development of more effective and personalized rehabilitation systems for stroke patients, by utilizing reliable and accurate EMG signal classification

Enhanced Hand Gesture Recognition with Surface Electromyogram and Machine Learning.

This study delves into decoding hand gestures using surface electromyography (EMG) signals collected via a precision Myo-armband sensor, leveraging machine learning algorithms. The research entails rigorous data preprocessing to extract features and labels from raw EMG data. Following partitioning into training and testing sets, four traditional machine learning models are scrutinized for their efficacy in classifying finger movements across seven distinct gestures. The analysis includes meticulous parameter optimization and five-fold cross-validation to evaluate model performance. Among the models assessed, the Random Forest emerges as the top performer, consistently delivering superior precision, recall, and F1-score values across gesture classes, with ROC-AUC scores surpassing 99%. These findings underscore the Random Forest model as the optimal classifier for our EMG dataset, promising significant advancements in healthcare rehabilitation engineering and enhancing human-computer interaction technologies.

Immediate effect of local vibration on motor unit firing behavior and muscle strength in healthy young adult males.

The aim of this study was to examine the effect of vibration on motor unit (MU) firing behavior and physical performance of antagonist muscles in healthy young adult males. Fourteen males (age = 24.3 ± 3.6years) were included in this study. There were two conditions, one in which participants received 80Hz vibration in the distal tendon of the hamstring for 30s and the control condition (no vibration). High-density surface electromyography (HD-SEMG) signals and maximal voluntary contraction (MVC) of knee extensor muscles were evaluated before and after the respective conditions and recorded from the vastus lateralis muscle during submaximal ramp-up and sustained contractions at 30% MVC. Convolution blind source separation was used to decompose the HD-SEMG signals into individual MU firing behaviors. In total, 739 MUs were detected (control; 360 MUs and vibration; 379 MUs), and a total of 312 matched MUs were identified across both submaximal contraction conditions (control: 150 MUs; vibration: 162 MUs). Vibration significantly increased the discharge rate (p = 0.047) and decreased the recruitment threshold before and after intervention (p = 0.001) but not in the control condition. Furthermore, the recruitment threshold is a factor that influences discharge rate. Significant correlations were observed between the recruitment threshold and both the ∆ discharge rate and the ∆ recruitment threshold under the vibration condition (p < 0.001). Vibration increased in the discharge rate and decreased the recruitment threshold of the antagonist muscle. These findings suggested that vibration contributes to immediate changes in the neural control of antagonist muscles.

Enhancing lower limb and core muscle activation with blood flow restriction training: a randomized crossover study on high-intensity squat exercises.

The primary objective of this study was to assess the impact of high-intensity deep squat training integrated with various blood flow restriction (BFR) modalities on the activation of lower limb and core muscles. A randomized, self-controlled crossover experimental design was employed with 12 participants. The exercise protocol consisted of squat training at 75% of one-repetition maximum (1RM), performed in 3 sets of 8 repetitions with a 2-min inter-set rest period. This was conducted under four distinct BFR conditions: continuous low BFR (T1), intermittent medium BFR (T2), intermittent high BFR (T3), and a non-restricted control (C). Surface electromyography (EMG) was utilized to collect EMG signals from the target muscles during the BFR and squat training sessions. The root mean square (RMS) amplitude standard values were calculated for each squat set to quantify muscle activation levels, with these values expressed as a percentage of the maximum voluntary contraction (%MVC). Rating of Perceived Exertion was evaluated after each squat set, and leg circumference measurements were taken. 1) During the first two sets of deep squats, the %MVC of the vastus lateralis and vastus medialis in all compression groups was significantly higher than that in the control group (p < 0.05). Furthermore, in the first set, the %MVC of the vastus lateralis in Group T3 was significantly higher than in Group T2 (p < 0.05). In the third set, the %MVC of the vastus medialis in Groups T1 and T3 was significantly lower than in the first two sets (p < 0.05). 2) Group T1 showed an increased activation of the biceps femoris and semitendinosus muscles in the second and third sets, with %MVC values significantly greater than in the first set (p < 0.05). Group T2 only showed an increase in biceps femoris activation in the third set (p < 0.05). Group T3 significantly increased the activation of the biceps femoris and semitendinosus muscles only in the first set (p < 0.05). 3) No significant differences were observed in the changes of rectus abdominis %MVC among the groups (p > 0.05). In the first set, Group T3's erector spinae %MVC was significantly higher than the control group's; in the second set, it was significantly higher than both Group T2 and the control group's (p < 0.05). 4) After training, a significant increase in thigh circumference was observed in all groups compared to before training (p < 0.05). 5) For RPE values, Group T2's post-squat values were significantly higher than the control group's after all three sets (p < 0.05). Group T1's RPE values were also significantly higher than the control group's after the third set (p < 0.05). Groups T1, T2, and C all had significantly higher RPE values in the second and third sets compared to the first set (p < 0.05). All BFR modalities significantly enhanced the activation level of the anterior thigh muscles, with the continuous low BFR mode demonstrating a more stable effect. No significant differences were found in the activation level of the rectus abdominis among the groups. However, the intermittent high BFR mode was the most effective in increasing the activation level of the erector spinae muscles. While BFR did not further augment leg circumference changes, it did elevate subjective fatigue levels. The RPE was lowest during squatting under the intermittent high BFR condition.

Gaussianity Evaluation of HD-sEMG Signals with Aging and Sex During Low and Moderate Isometric Contractions of the Biceps Brachii

IntroductionAging is associated with muscle decline, which alters both functional and anatomical properties of the neuromuscular system. These modifications can be reflected in high-density surface electromyography (HD-sEMG) signals. This study examines how age and sex impact the shape of the amplitude Probability Density Function (PDF) of HD-sEMG signals. Materials and MethodsMonopolar HD-sEMG signals were collected from the Biceps Brachii in a cohort of 17 individuals: 10 women (mean age: 22.9 ± 3.6 years) and 7 men (mean age: 24.4 ± 2.5 years) in the younger group, and 10 women (mean age: 69.8 ± 4.8 years) and 7 men (mean age: 72.8 ± 2.7 years) in the elderly group. The recordings were conducted during an elbow flexion at both 20% and 40% maximum voluntary contraction. The signal amplitude was evaluated using root means square amplitude (RMSA) and the PDF shape of each HD-sEMG signal was assessed through skewness, excess Kurtosis, and robust functional statistics. These shape distance metrics evaluate the departure from Gaussianity related to muscle aging. a) We conducted a comparison study of the HD-sEMG PDF shapes between younger and elderly individuals. b) Evaluating differences between men and women. c) Considering monopolar and Laplacian electrode configurations that are sensitive to different muscle regions. ResultsA) The HD-sEMG PDFs of elderly subjects demonstrated a lower departure from Gaussianity than their younger counterparts. B) Women exhibited lower RMSA values than men, and, on average, a lower departure from Gaussianity whatever the age and contraction level C) Trends of departure from Gaussianity with contraction level, seems to be influenced by the electrode configuration. In fact, a decrease in Gaussianity departure is observed with monopolar recordings where an increase is observed with Laplacian one, clearly indicating different muscle region assessment. DiscussionThe findings highlight the influence of factors such aging, sex, contraction level and electrode montage on the shape of the HD-sEMG PDF, emphasizing the significance of using this descriptor for monitoring and better assessment of muscle aging.

Reciprocal Inhibition and Coactivation of Ankle Muscles in Low- and High-Velocity Forward and Backward Perturbations

Reciprocal inhibition and coactivation are strategies of the central nervous system used to perform various daily tasks. In automatic postural responses (APR), coactivation is widely investigated in the ankle joint muscles, however reciprocal inhibition, although clear in manipulative motor actions, has not been investigated in the context of APRs. The aim was to identify whether reciprocal inhibition can be observed as a strategy in the recruitment of gastrocnemius Medialis (GM), Soleus (So) and Tibialis Anterior (TA) muscles in low- and high-velocity forward and backward perturbations. We applied two balance perturbations with a low and a high velocity of displacement of the movable platform in forward and backward conditions and we evaluated the magnitude and latency time of TA, GM and So activation latency, measured by electromyography (EMG). In forward perturbations, coactivation of the three muscles was observed, with greater activation amplitude of the GM and lesser amplitude of the So and TA muscles. For backward, the pattern of response observed was activation of the TA muscle, a decrease in the EMG signal, which characterizes reciprocal inhibition of the GM muscle and maintenance of the basal state of the So muscle. This result indicates that backward perturbations are more challenging.

A system for monitoring human postures, seizures, and falls from bed using radio and surface electromyography signals

In this work, a system for monitoring human postures, seizures, and falls from bed using received signal strength indicator (RSSI) and surface electromyography (sEMG) signals is studied through experiments. In this proposed system, a person who is located inside a wireless link is monitored by considering the change in measured RSSI signals as the 2.4 GHz IEEE 802.15.4 signals received at a receiver. Human motions in bed that affect RSSI levels can be captured. Thus, with this technique, it does not raise a privacy concern compared with vision-based technology. Additionally, sEMG signals associated with muscle movements from human postures are recorded from the human body’s abdominal muscles. Eight different activities, including normal and critical events, are tested and evaluated. Experimental results indicate that the proposed system could automatically monitor different human postures in real-time. RSSI and sEMG signals correlated to each posture have their own patterns. Furthermore, the relationship between human behaviors and RSSI and sEMG levels is summarized.

Development and External Validation of a Motor Intention–Integrated Prediction Model for Upper Extremity Motor Recovery After Intention-Driven Robotic Hand Training for Chronic Stroke

ObjectiveTo derive and validate a prediction model for minimal clinically important differences (MCIDs) in upper extremity (UE) motor function after intention-driven robotic hand training using residual voluntary electromyography (EMG) signals from affected UE. DesignA prospective longitudinal multicenter cohort study. We collected preintervention candidate predictors: demographics, clinical characteristics, Fugl-Meyer assessment of UE (FMAUE), Action Research Arm Test scores, and motor intention of flexor digitorum and extensor digitorum (ED) measured by EMG during maximal voluntary contraction (MVC). For EMG measures, recognizing challenges for stroke survivors to move paralyzed hand, peak signals were extracted from 8 time windows during MVC-EMG (0.1-5s) to identify subjects’ motor intention. Classification and regression tree algorithm was employed to predict survivors with MCID of FMAUE. Relationship between predictors and motor improvements was further investigated. SettingNine rehabilitation centers. ParticipantsChronic stroke survivors (N=131), including 87 for derivation sample, and 44 for validation sample. InterventionsAll participants underwent 20-session robotic hand training (40min/session, 3-5sessions/wk). Main Outcome MeasuresPrediction efficacies of models were assessed by area under the receiver operating characteristic curve (AUC). The best effective model was final model and validated using AUC and overall accuracy. ResultsThe best model comprised FMAUE (cutoff score, 46) and peak activity of ED from 1-second MVC-EMG (MVC-EMG 4.604 times higher than resting EMG), which demonstrated significantly higher prediction accuracy (AUC, 0.807) than other time windows or solely using clinical scores (AUC, 0.595). In external validation, this model displayed robust prediction (AUC, 0.916). Significant quadratic relationship was observed between ED-EMG and FMAUE increases. ConclusionsThis study presents a prediction model for intention-driven robotic hand training in chronic stroke survivors. It highlights significance of capturing motor intention through 1-second EMG window as a predictor for MCID improvement in UE motor function after 20-session robotic training. Survivors in 2 conditions showed high percentage of clinical motor improvement: moderate-to-high motor intention and low-to-moderate function; as well as high intention and high function.

Multi-View Fusion Network-Based Gesture Recognition Using sEMG Data.

sEMG(surface electromyography) signals have been widely used in rehabilitation medicine in the past decades because of their non-invasive, convenient and informative features, especially in human action recognition, which has developed rapidly. However, the research on sparse EMG in multi-view fusion has made less progress compared to high-density EMG signals, and for the problem of how to enrich sparse EMG feature information, a method that can effectively reduce the information loss of feature signals in the channel dimension is needed. In this article, a novel IMSE (Inception-MaxPooling-Squeeze- Excitation) network module is proposed to reduce the loss of feature information during deep learning. Then, multiple feature encoders are constructed to enrich the information of sparse sEMG feature maps based on the multi-core parallel processing method in multi-view fusion networks, while SwT (Swin Transformer) is used as the classification backbone network. By comparing the feature fusion effects of different decision layers of the multi-view fusion network, it is experimentally obtained that the fusion of decision layers can better improve the classification performance of the network. In NinaPro DB1, the proposed network achieves 93.96% average accuracy in gesture action classification with the feature maps obtained in 300ms time window, and the maximum variation range of action recognition rate of individuals is less than 11.2%. The results show that the proposed framework of multi-view learning plays a good role in reducing individuality differences and augmenting channel feature information, which provides a certain reference for non-dense biosignal pattern recognition.

User Perspectives and Psychophysiological Manifestations of Fatigue with Trunk Orthosis for Dystrophinopathy Patients.

The chair-mounted passive trunk orthosis (CMPTO) is designed to enhance wheelchair safety for individuals with dystrophinopathy during their daily activities. Given the disease's progressive nature, it is crucial to ensure that assistive devices are carefully evaluated to prevent overexertion. This study aims to assess the CMPTO's user experience and its impact on fatigue-related psychophysiological measurements. We conducted electromyography (EMG) evaluations of four trunk muscles and assessed perceived exertion using the Borg CR-10 scale in 40 healthy subjects while they performed seated maximal reaching tasks with the CMPTO. Additionally, fifteen dystrophinopathy patients evaluated the CMPTO for usability with the System Usability Scale. Paired t-tests were employed to compare the median frequency (MDF) of EMG signals, the Wilcoxon signed-rank test for evaluating exertion, and the Mann-Whitney U test to compare the usability reported by patients to those of healthy subjects. The 4-way ANOVA revealed that MDF patterns were significantly influenced by task orientation for each muscle. The CMPTO did not cause a significant reduction in the MDF. Tasks requiring greater trunk rotation were perceived as more exhaustive. Patients reported acceptable usability with the CMPTO, with scores higher than those of healthy subjects. The CMPTO's usability was comprehensively evaluated in both healthy subjects and patients with dystrophinopathy. Our findings indicate that the CMPTO can be safely used by individuals with dystrophinopathy as an assistive device to improve seated comfort and functional abilities.