Electromyogram Signals Research Articles

Feature evaluation for myoelectric pattern recognition of multiple nearby reaching targets

Intention detection of the reaching movement is considerable for myoelectric human and machine collaboration applications. A comprehensive set of handcrafted features was mined from windows of electromyogram (EMG) of the upper-limb muscles while reaching nine nearby targets like activities of daily living. The feature selection-based scoring method, neighborhood component analysis (NCA), selected the relevant feature subset. Finally, the target was recognized by the support vector machine (SVM) model. The classification performance was generalized by a nested cross-validation structure that selected the optimal feature subset in the inner loop. According to the low spatial resolution of the target location on display and following the slight discrimination of signals between targets, the best classification accuracy of 77.11 % was achieved for concatenating the features of two segments with a length of 2 and 0.25 s. Due to the lack of subtle variation in EMG, while reaching different targets, a wide range of features was applied to consider additional aspects of the knowledge contained in EMG signals. Furthermore, since NCA selected features that provided more discriminant power, it became achievable to employ various combinations of features and even concatenated features extracted from different movement parts to improve classification performance.

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

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

Decomposition strategy for surface EMG with few channels: a simulation study

Objective. In the specific use of electromyogram (EMG) driven prosthetics, the user’s disability reduces the space available for the electrode array. We propose a framework for EMG decomposition adapted to the condition of a few channels (less than 30 observations), which can elevate the potential of prosthetics in terms of cost and applicability. Approach. The new framework contains a peel-off approach, a refining strategy for motor unit (MU) spike train and MU action potential and a re-subtracting strategy to adapt the framework to few channels environments. Simulated EMG signals were generated to test the framework. In addition, we quantify and analyze the effect of strategies used in the framework. Main results. The results show that the new algorithm has an average improvement of 19.97% in the number of MUs identified compared to the control algorithm. Quantitative analysis of the usage strategies shows that the re-subtracting and refining strategies can effectively improve the performance of the framework under the condition of few channels. Significance. These prove that the new framework can be applied to few channel conditions, providing a optimization space for neural interface design in cost and user adaptation.

Improved multi-layer wavelet transform and blind source separation based ECG artifacts removal algorithm from the sEMG signal: in the case of upper limbs.

Introduction: Surface electromyogram (sEMG) signals have been widely used in human upper limb force estimation and motion intention recognition. However, the electrocardiogram(ECG) artifact generated by the beating of the heart is a major factor that reduces the quality of the EMG signal when recording the sEMG signal from the muscle close to the heart. sEMG signals contaminated by ECG artifacts are difficult to be understood correctly. The objective of this paper is to effectively remove ECG artifacts from sEMG signals by a novel method. Methods: In this paper, sEMG and ECG signals of the biceps brachii, brachialis, and triceps muscle of the human upper limb will be collected respectively. Firstly, an improved multi-layer wavelet transform algorithm is used to preprocess the raw sEMG signal to remove the background noise and power frequency interference in the raw signal. Then, based on the theory of blind source separation analysis, an improved Fast-ICA algorithm was constructed to separate the denoising signals. Finally, an ECG discrimination algorithm was used to find and eliminate ECG signals in sEMG signals. This method consists of the following steps: 1) Acquisition of raw sEMG and ECG signals; 2) Decoupling the raw sEMG signal; 3) Fast-ICA-based signal component separation; 4) ECG artifact recognition and elimination. Results and discussion: The experimental results show that our method has a good effect on removing ECG artifacts from contaminated EMG signals. It can further improve the quality of EMG signals, which is of great significance for improving the accuracy of force estimation and motion intention recognition tasks. Compared with other state-of-the-art methods, our method can also provide the guiding significance for other biological signals.

Sweat-adaptive adhesive hydrogel electronics enabled by dynamic hydrogen bond networks

Adhesive hydrogels offer an appealing way to the demand for flexible epidermal electronics. Despite the significant advances of adhesive hydrogel electronics, the unavoidable degradation of adhesion and associated diminished detection on sweaty skin are two long-standing bottlenecks for their practical applications. Herein, we present a sweat-adaptive adhesive poly(acrylamide)/cellulose (PAAm/Cel) hydrogel electronic via dynamic hydrogen bond networks. Increased sweat promotes the decoupling of hydrogen bonds within the hydrogel between PAAm and cellulose, leading to enhanced skin-hydrogel interfacial adhesion due to the strong binding of exposed abundant polar groups to the skin. The resulting PAAm/Cel hydrogel exhibits robust bioadhesion on sweating skin, with 268.3 J m−2 in interfacial toughness, 201.7 kPa in tensile strength, and 31.7 kPa in shear strength. Furthermore, the conformable and adhesive PAAm/Cel hydrogel electronics are demonstrated to produce high-quality and stable electromyogram (EMG) signals worked on persistent sweating skin. We believe that our designed adhesive hydrogel with dynamic hydrogen bond networks coupled with sweat is promising for tough bioadhesive electronics and enables bioadhesive technologies with high-level adaptivity in daily activities.

A systematic investigation of detectors for low signal-to-noise ratio EMG signals

Background Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients’ active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown. Methods This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: Gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy. Results The results indicate that the Modified Hodges detector – a simplified version of the threshold-based Hodges detector introduced in the current study – was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges. Conclusions Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood Ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.

TDITI: A time-delay information transfer index algorithm for corticomuscular coupling

Time delay (TD) across corticomuscular coupling (CMC) is a significant index to assess the information transmission between brain and muscle during movement execution. Larger methods have been widely used to calculate the time delay by estimating phase information, but fail to account for both linear and nonlinear characteristics in the bidirectional coupled systems. For this, this study proposed a novel time-delay estimation method, defined as time-delay information transfer index (TDITI), to explore the TD characteristics between two signal deriving from one system with time-delay coupling. To verify this, we introduced two models to generate a series of simulation signal with linearly unidirectional/ bidirectional coupling or nonlinearly unidirectional/ bidirectional coupling. Simulation results manifested that the TDITI method, compared with the information transfer index (ITI) and coherence methods, can not only describe the TD in the linearly or nonlinearly unidirectional systems, but was also suitable for the bidirectional coupled systems. We also found its robustness to data length, coupling strength and signal-noise ratio. After that, we applied it to explore the TD of CMC by synchronizing the electroencephalogram (EEG) and electromyogram (EMG) signal during steady-state task. Experimental results showed that the CMC between cortex and muscle were direction-dependent, and the average delay time from EEG to EMG (∼25 ms) was shorter than that in the opposition (∼30 ms). Both simulation and experimental data expound the effectiveness of the TDITI method to describe the time delay in the unidirectional or bidirectional coupled systems, and this study extends our perspective to the mechanism of motor control.

Online prediction of sustained muscle force from individual motor unit activities using adaptive surface EMG decomposition

Decoding movement intentions from motor unit (MU) activities to represent neural drive information plays a central role in establishing neural interfaces, but there remains a great challenge for obtaining precise MU activities during sustained muscle contractions. In this paper, we presented an online muscle force prediction method driven by individual MU activities that were decomposed from prolonged surface electromyogram (SEMG) signals in real time. In the training stage of the proposed method, a set of separation vectors was initialized for decomposing MU activities. After transferring each decomposed MU activity into a twitch force train according to its action potential waveform, a neural network was designed and trained for predicting muscle force. In the subsequent online stage, a practical double-thread-parallel algorithm was developed. One frontend thread predicted the muscle force in real time utilizing the trained network and the other backend thread simultaneously updated the separation vectors. To assess the performance of the proposed method, SEMG signals were recorded from the abductor pollicis brevis muscles of eight subjects and the contraction force was simultaneously collected. With the update procedure in the backend thread, the force prediction performance of the proposed method was significantly improved in terms of lower root mean square deviation (RMSD) of around 10% and higher fitness (R2) of around 0.90, outperforming two conventional methods. This study provides a promising technique for real-time myoelectric applications in movement control and health.

Automatic sleep-wake classification and Parkinson's disease recognition using multifeature fusion with support vector machine.

Sleep disturbance is a prevalent nonmotor symptom of Parkinson's disease (PD), however, assessing sleep conditions is always time-consuming and labor-intensive. In this study, we performed an automatic sleep-wake state classification and early diagnosis of PD by analyzing the electrocorticography (ECoG) and electromyogram (EMG) signals of both normal and PD rats. The study utilized ECoG power, EMG amplitude, and corticomuscular coherence values extracted from normal and PD rats to construct sleep-wake scoring models based on the support vector machine algorithm. Subsequently, we incorporated feature values that could act as diagnostic markers for PD and then retrained the models, which could encompass the identification of vigilance states and the diagnosis of PD. Features extracted from occipital ECoG signals were more suitable for constructing sleep-wake scoring models than those from frontal ECoG (average Cohen's kappa: 0.73 vs. 0.71). Additionally, after retraining, the new models demonstrated increased sensitivity to PD and accurately determined the sleep-wake states of rats (average Cohen's kappa: 0.79). This study accomplished the precise detection of substantia nigra lesions and the monitoring of sleep-wake states. The integration of circadian rhythm monitoring and disease state assessment has the potential to improve the efficacy of therapeutic strategies considerably.

Adaptive Online Decomposition of Surface EMG Using Progressive FastICA Peel-Off.

This study presents a method for adaptive online decomposition of high-density surface electromyogram (SEMG) signals to overcome the performance degradation during long-term recordings. The proposed method utilized the progressive FastICA peel-off (PFP) method and integrated a practical double-thread-parallel algorithm into the conventional two-stage calculation approach. During the offline initialization stage, a set of separation vectors was computed. In the subsequent online decomposition stage, a backend thread was implemented to periodically update the separation vectors using the constrained FastICA algorithm and the automatic PFP method. Concurrently, the frontend thread employed the newly updated separation vectors to accurately extract motor unit (MU) spike trains in real time. To assess the effectiveness of the proposed method, simulated and experimental SEMG signals from abductor pollicis brevis muscles of ten subjects were used for evaluation. The results demonstrated that the proposed method outperformed the conventional method, which relies on fixed separation vectors. Specifically, the proposed method showed an improved matching rate by 3.63% in simulated data and 1.98% in experimental data, along with an increased motor unit number by 2.39 in simulated data and 1.30 in experimental data. These findings illustrated the feasibility of the proposed method to enhance the performance of online SEMG decomposition. As a result, this work holds promise for various applications that require accurate MU firing activities in decoding neural commands and building neural-machine interfaces.

Unsupervised neural decoding for concurrent and continuous multi-finger force prediction

Reliable prediction of multi-finger forces is crucial for neural-machine interfaces. Various neural decoding methods have progressed substantially for accurate motor output predictions. However, most neural decoding methods are performed in a supervised manner, i.e., the finger forces are needed for model training, which may not be suitable in certain contexts, especially in scenarios involving individuals with an arm amputation. To address this issue, we developed an unsupervised neural decoding approach to predict multi-finger forces using spinal motoneuron firing information. We acquired high-density surface electromyogram (sEMG) signals of the finger extensor muscle when subjects performed single-finger and multi-finger tasks of isometric extensions. We first extracted motor units (MUs) from sEMG signals of the single-finger tasks. Because of inevitable finger muscle co-activation, MUs controlling the non-targeted fingers can also be recruited. To ensure an accurate finger force prediction, these MUs need to be teased out. To this end, we clustered the decomposed MUs based on inter-MU distances measured by the dynamic time warping technique, and we then labeled the MUs using the mean firing rate or the firing rate phase amplitude. We merged the clustered MUs related to the same target finger and assigned weights based on the consistency of the MUs being retained. As a result, compared with the supervised neural decoding approach and the conventional sEMG amplitude approach, our new approach can achieve a higher R2 (0.77 ± 0.036 vs. 0.71 ± 0.11 vs. 0.61 ± 0.09) and a lower root mean square error (5.16 ± 0.58 %MVC vs. 5.88 ± 1.34 %MVC vs. 7.56 ± 1.60 %MVC). Our findings can pave the way for the development of accurate and robust neural-machine interfaces, which can significantly enhance the experience during human-robotic hand interactions in diverse contexts.

Prediction of jaw opening function after mandibular reconstruction using subject-specific musculoskeletal modelling.

Mandibular reconstruction patients often suffer abnormalities in the mandibular kinematics. In silico simulations, such as musculoskeletal modelling, can be used to predict post-operative mandibular kinematics. It is important to validate the mandibular musculoskeletal model and analyse the factors influencing its accuracy. To investigate the jaw opening-closing movements after mandibular reconstruction, as predicted by the subject-specific musculoskeletal model, and the factors influencing its accuracy. Ten mandibular reconstruction patients were enrolled in this study. Cone-beam computed tomography images, mandibular movements, and surface electromyogram signals were recorded preoperatively. A subject-specific mandibular musculoskeletal model was established to predict surgical outcomes using patient-averaged muscle parameter changes as model inputs. Jaw bone geometry was replaced by surgical planning results, and the muscle insertion sites were registered based on the non-rigid iterative closest point method. The predicted jaw kinematic data were validated based on 6-month post-operative measurements. Correlations between the prediction accuracy and patient characteristics (age, pathology and surgical scope) were further analysed. The root mean square error (RMSE) for lower incisor displacement was 31.4%, and the error for peak magnitude of jaw opening was 4.9 mm. Age, post-operative infection and radiotherapy influenced the prediction accuracy. The amount of masseter detachment showed little correlation with jaw opening. The mandibular musculoskeletal model successfully predicted short-range jaw opening functions after mandibular reconstruction. It provides a novel surgical planning method to predict the risk of developing trismus.

A systematic investigation of detectors for low signal-to-noise ratio EMG signals.

Active participation of stroke survivors during robot-assisted movement therapy is essential for sensorimotor recovery. Robot-assisted therapy contingent on movement intention is an effective way to encourage patients' active engagement. For severely impaired stroke patients with no residual movements, a surface electromyogram (EMG) has been shown to be a viable option for detecting movement intention. Although numerous algorithms for EMG detection exist, the detector with the highest accuracy and lowest latency for low signal-to-noise ratio (SNR) remains unknown. This study, therefore, investigates the performance of 13 existing EMG detection algorithms on simulated low SNR (0dB and -3dB) EMG signals generated using three different EMG signal models: Gaussian, Laplacian, and biophysical model. The detector performance was quantified using the false positive rate (FPR), false negative rate (FNR), and detection latency. Any detector that consistently showed FPR and FNR of no more than 20%, and latency of no more than 50ms, was considered an appropriate detector for use in robot-assisted therapy. The results indicate that the Modified Hodges detector - a simplified version of the threshold-based Hodges detector introduced in the current study - was the most consistent detector across the different signal models and SNRs. It consistently performed for ~90% and ~40% of the tested trials for 0dB and -3dB SNR, respectively. The two statistical detectors (Gaussian and Laplacian Approximate Generalized Likelihood Ratio) and the Fuzzy Entropy detectors have a slightly lower performance than Modified Hodges. Overall, the Modified Hodges, Gaussian and Laplacian Approximate Generalized Likelihood Ratio, and the Fuzzy Entropy detectors were identified as the potential candidates that warrant further investigation with real surface EMG data since they had consistent detection performance on low SNR EMG data.

Multi-Session Electrocardiogram–Electromyogram Database for User Recognition

Current advancements in biosignal-based user recognition technology are paving the way for a next-generation solution that addresses the limitations of face- and fingerprint-based user recognition methods. However, existing biosignal benchmark databases (DBs) for user recognition often suffer from limitations, such as data collection from a small number of subjects in a single session, hindering comprehensive analysis of biosignal variability. This study introduces CSU_MBDB1 and CSU_MBDB2, databases containing electrocardiogram (ECG) and electromyogram (EMG) signals from diverse experimental subjects recorded across multiple sessions. These in-house DBs comprise ECG and EMG data recorded in multiple sessions from 36 and 58 subjects, respectively, with a time interval of more than one day between sessions. During the experiments, subjects performed a total of six gestures while comfortably seated at a desk. CSU_MBDB1 and CSU_MBDB2 consist of three identical gestures, providing expandable data for various applications. When the two DBs are expanded, ECGs and EMGs from 94 subjects can be used, which is the largest number among the multi-biosignal benchmark DBs built by multi-sessions. To assess the usability of the constructed DBs, a user recognition experiment was conducted, resulting in an accuracy of 66.39% for ten subjects. It is important to emphasize that we focused on demonstrating the applicability of the constructed DBs using a basic neural network without signal denoising capabilities. While this approach results in a sacrifice in accuracy, it concurrently provides substantial opportunities for performance enhancement through the implementation of optimized algorithms. Adapting signal denoising processes to the constructed DBs and designing a more sophisticated neural network would undoubtedly contribute to improving the recognition accuracy. Consequently, these constructed DBs hold promise in user recognition, offering valuable research for future investigations. Additionally, DBs can be used in research to analyze the nonlinearity characteristics of ECG and EMG.

Development and Analysis of an Origami-Based Elastomeric Actuator and Soft Gripper Control with Machine Learning and EMG Sensors.

This study investigates the characteristics of a novel origami-based, elastomeric actuator and a soft gripper, which are controlled by hand gestures that are recognized through machine learning algorithms. The lightweight paper-elastomer structure employed in this research exhibits distinct actuation features in four key areas: (1) It requires approximately 20% less pressure for the same bending amplitude compared to pneumatic network actuators (Pneu-Net) of equivalent weight, and even less pressure compared to other actuators with non-linear bending behavior; (2) The control of the device is examined by validating the relationship between pressure and the bending angle, as well as the interaction force and pressure at a fixed bending angle; (3) A soft robotic gripper comprising three actuators is designed. Enveloping and pinch grasping experiments are conducted on various shapes, which demonstrate the gripper's potential in handling a wide range of objects for numerous applications; and (4) A gesture recognition algorithm is developed to control the gripper using electromyogram (EMG) signals from the user's muscles.

Framework for the Classification of Facial Emotions Using Soft Computing Techniques

Background:: Facial emotion recognition (FER) technology is enumerated as a productive interface in several operations, which has been specifically focused on as a substitute communication path among a user and an appliance for human computer interface in the previous decade. The efficiency of the facial identification model straightaway relies on the capability of classification methods. In addition, an appropriate swap between recognition efficiency and computational cost is reckoned as the most important factor for planning such models. Methods:: The objective of this paper was to classify the facial emotion electromyogram (EMG) signals by means of a neural network algorithm (NN), support vector machine (SVM) algorithm, and Naive-Bayes algorithm. This research work was directed towards the correlation among the classification accuracies by applying distinct feature extraction procedures on fEMGs. At first, eight participants (six male and two female) were recruited for data recording. Four electrodes were placed on each participant's face for capturing facial gestures (happy, angry, sad, and fear) and two electrodes were placed on the wrist for grounding purposes. Data were recorded by using BIOPAC MP150. After this, the signals were filtered using a band-pass filter and segmentation techniques for enhanced processing. After that, the time-domain and frequency-domain feature extraction procedures were carried out. Time domain and frequency domain features were applied to recorded signals. In this research, we used LabVIEW and MATLAB to produce a set of characteristics from fEMG signals for four emotional conditions, such as anger, sad, fear, and happy. After the feature extraction process, the extracted features were aligned into respective emotions by applying classifiers. The extracted features were further trained and classified by applying the SVM classifier, neural network classifier, and Naive Bayes classifier in MATLAB 2020. Results:: The SVM classifier and neural network classifier generated an accuracy of 93.80% and 96.90%, respectively, whereas the Naive Bayes classifier generated an accuracy of 90.60%. Conclusion:: Facial emotion recognition (FER) is foresighted as a progressive or futuristic model, which has attracted the attention of researchers in several areas of learning due to its higher prospects in distinct applications. Acknowledgment of the emotions through biomedical signals produced from movements of facial muscles is lately presented using an explicit and authentic route.

Delay estimation for cortical-muscular interaction with wavelet coherence time lag

BackgroundCortico-muscular coherence (CMC) between the cerebral cortex and muscle activity is an effective tool for studying neural communication in the motor control system. To accurately evaluate the coherence between electroencephalogram (EEG) and electromyogram (EMG) signals, it is necessary to accurately calculate the time delay between physiological signals to ensure signal synchronization. New methodWe proposed a new delay estimation method, named wavelet coherence time lag (WCTL) and the significant increase areas (SIA) index as a measure of the specific region enhancement effect of the magnitude squared coherence (MSC) image. ResultsThe grip strength level had a small effect on the information transmission time from the cortex to the muscles, while the transmission time from the cortex to different muscle channels was different for the same task. A positive correlation was found between the grip strength level and the SIA index on the β band of C3-B and the α and β bands of C3-FDS.Comparison with Existing Method: The WCTL method was found to accurately calculate the delay time even when the number of repeated segments was low in a simple motor control model, and the results were more accurate than the rate of voxels change (RVC) and CMC with time lag (CMCTL) methods. ConclusionsThe WCTL is an effective method for detecting the transmission time of information between the cortex and muscles, laying the foundation for future rehabilitation treatment for stroke patients.

SlumberNet: deep learning classification of sleep stages using residual neural networks

Sleep research is fundamental to understanding health and well-being, as proper sleep is essential for maintaining optimal physiological function. Here we present SlumberNet, a novel deep learning model based on residual network (ResNet) architecture, designed to classify sleep states in mice using electroencephalogram (EEG) and electromyogram (EMG) signals. Our model was trained and tested on data from mice undergoing baseline sleep, sleep deprivation, and recovery sleep, enabling it to handle a wide range of sleep conditions. Employing k-fold cross-validation and data augmentation techniques, SlumberNet achieved high levels of overall performance (accuracy = 97%; F1 score = 96%) in predicting sleep stages and showed robust performance even with a small and diverse training dataset. Comparison of SlumberNet's performance to manual sleep stage classification revealed a significant reduction in analysis time (~ 50 × faster), without sacrificing accuracy. Our study showcases the potential of deep learning to facilitate sleep research by providing a more efficient, accurate, and scalable method for sleep stage classification. Our work with SlumberNet further demonstrates the power of deep learning in mouse sleep research.

Organohydrogel‐Based Soft SEMG Electrodes for Algorithm‐Assisted Gesture Recognition

AbstractEpidermal electronics that can monitor physiological signals such as surface electromyogram (sEMG) signals attract widespread attentions in personalized healthcare, human–machine interfaces (HMI) and virtual/augmented reality (AR/VR). However, conventional electromyographic electrodes suffer from skin discomfort, susceptibility to motion artifact interference, and short service lifetime. Here, an organohydrogel‐based sEMG electrode endows with high conductivity, low modulus and long‐term stability is developed by doping partially reduced graphene oxide (pRGO) into highly cross‐linked organohydrogel network. The as‐fabricated polyacrylamide/sodium alginate/tannic acid/partially reduced graphene oxide (PAM/SA/TA/pRGO) organohydrogel possesses farewell conductivity (4.22 S m−1) while preserving tissue‐like compliance (Young's modulus ≈32 KPa), excellent stretchability (≈600%), high adhesion as well as superior anti‐drying properties. In addition, a stretchable sEMG electrode for long‐term reliable service is fabricated via immobilizing the organohydrogel electrodes onto a flexible very high bond (VHB) substrate. As a result, the integrated electrodes show high signal‐to‐noise ratio (SNR) (35.15 db) comparable to that of the commercial electrodes. Furthermore, with assistance of deep learning, the proposed sEMG electrodes obtain high identification accuracy of 97.11% in distinguishing sophisticated gestures. This system can be further exploited for real‐time tele‐operations and offers broad prospects in human–machine immersive interactive application.

A Wearable Upper Limb Exoskeleton System and Intelligent Control Strategy.

Heavy lifting operations frequently lead to upper limb muscle fatigue and injury. In order to reduce muscle fatigue, auxiliary force for upper limbs can be provided. This paper presents the development and evaluation of a wearable upper limb exoskeleton (ULE) robot system. A flexible cable transmits auxiliary torque and is connected to the upper limb by bypassing the shoulder. Based on the K-nearest neighbors (KNN) algorithm and integrated fuzzy PID control strategy, the ULE identifies the handling posture and provides accurate active auxiliary force automatically. Overall, it has the quality of being light and easy to wear. In unassisted mode, the wearer's upper limbs minimally affect the range of movement. The KNN algorithm uses multi-dimensional motion information collected by the sensor, and the test accuracy is 94.59%. Brachioradialis muscle (BM), triceps brachii (TB), and biceps brachii (BB) electromyogram (EMG) signals were evaluated by 5 kg, 10 kg, and 15 kg weight conditions for five subjects, respectively, during lifting, holding, and squatting. Compared with the ULE without assistance and with assistance, the average peak values of EMG signals of BM, TB, and BB were reduced by 19-30% during the whole handling process, which verified that the developed ULE could provide practical assistance under different load conditions.