Multichannel Electromyography Research Articles

EMG gesture signal analysis towards diagnosis of upper limb using dual-pathway convolutional neural network

<abstract><p>This research introduces a novel dual-pathway convolutional neural network (DP-CNN) architecture tailored for robust performance in Log-Mel spectrogram image analysis derived from raw multichannel electromyography signals. The primary objective is to assess the effectiveness of the proposed DP-CNN architecture across three datasets (NinaPro DB1, DB2, and DB3), encompassing both able-bodied and amputee subjects. Performance metrics, including accuracy, precision, recall, and F1-score, are employed for comprehensive evaluation. The DP-CNN demonstrates notable mean accuracies of 94.93 ± 1.71% and 94.00 ± 3.65% on NinaPro DB1 and DB2 for healthy subjects, respectively. Additionally, it achieves a robust mean classification accuracy of 85.36 ± 0.82% on amputee subjects in DB3, affirming its efficacy. Comparative analysis with previous methodologies on the same datasets reveals substantial improvements of 28.33%, 26.92%, and 39.09% over the baseline for DB1, DB2, and DB3, respectively. The DP-CNN's superior performance extends to comparisons with transfer learning models for image classification, reaffirming its efficacy. Across diverse datasets involving both able-bodied and amputee subjects, the DP-CNN exhibits enhanced capabilities, holding promise for advancing myoelectric control.</p></abstract>

Effect of M-wave Amplitude on Inter-evaluator Concordance and Number of Detected Innervation Zones in the Medial Gastrocnemius Using Multichannel Electromyography

Effect of M-wave Amplitude on Inter-evaluator Concordance and Number of Detected Innervation Zones in the Medial Gastrocnemius Using Multichannel Electromyography

An Integrated Approach for Real-Time Monitoring of Knee Dynamics with IMUs and Multichannel EMG.

Measuring human joint dynamics is crucial for understanding how our bodies move and function, providing valuable insights into biomechanics and motor control. Cerebral palsy (CP) is a neurological disorder affecting motor control and posture, leading to diverse gait abnormalities, including altered knee angles. The accurate measurement and analysis of knee angles in individuals with CP are crucial for understanding their gait patterns, assessing treatment outcomes, and guiding interventions. This paper presents a novel multimodal approach that combines inertial measurement unit (IMU) sensors and electromyography (EMG) to measure knee angles in individuals with CP during gait and other daily activities. We discuss the performance of this integrated approach, highlighting the accuracy of IMU sensors in capturing knee joint movements when compared with an optical motion-tracking system and the complementary insights offered by EMG in assessing muscle activation patterns. Moreover, we delve into the technical aspects of the developed device. The presented results show that the angle measurement error falls within the reported values of the state-of-the-art IMU-based knee joint angle measurement devices while enabling a high-quality EMG recording over prolonged periods of time. While the device was designed and developed primarily for measuring knee activity in individuals with CP, its usability extends beyond this specific use-case scenario, making it suitable for applications that involve human joint evaluation.

Characteristics of multi-channel intermuscular directional coupling based on time-varying partial directional coherence analysis

The human body transmits directional information between muscles during upper limb movements, and this will be particularly evident when the dominant muscle changes during movement transitions. By capturing the electromyography (EMG) signals of wrist flexion and extension continuous transition movements, we investigated the characteristics of multichannel intermuscular directional coupling and directional information transmission, and consequently explored the control mechanism of Central nervous system (CNS) and the coordination mechanism of motor muscles. Multi-channel EMG was collected from 12 healthy subjects under continuous translational movements of wrist flexion and extension, and the time-varying biased directional coherence analysis (TVPDC) model was constructed using partial directional coherence analysis (PDC) frequency domain directionality to study the directional information transfer characteristics in the time–frequency domain, screen closely related muscle pairs and perform directional coupling significance analysis. Palmaris longus (PL) played a dominant role under wrist flexion movements(WF), Extensor Carpi Radialis (ECR) played a dominant role under wrist extension movements(WE), and the remaining muscles responded to them with information and Biceps Brachii (BB) played a responsive role throughout the movement; flexor pairs had the highest positive coupling values in the beta band during Conversion action1 (MC1) and WF phases, and extensor pairs had the highest positive coupling values in the gamma band during Conversion action2(MC2) phase and the highest coupling values in the beta band during WE phase. TVPDC can effectively analyze the multichannel intermuscular directional coupling and information transmission relationship of surface electromyography under wrist flexion and extension transition movements, providing a reference for exploring the control mechanism of CNS and abnormal control mechanism in patients with motor dysfunction in a new perspective.

Non-Surgical Lower-Limb Rehabilitation Enhances Quadriceps Strength in Inpatients with Hip Fracture: A Study on Force Capacity and Fatigue

Measuring muscle fatigue and resistance to fatigue is a topical theme in many clinical research studies. Multi-domain approaches, including electromyography (EMG), are employed to measure fatigue in rehabilitation contexts. In particular, spectral features, such as the reduction in the median frequency, are accepted biomarkers to detect muscle fatigue conditions. However, applications of fatigue detection in clinical scenarios are still limited and with margin for improvement. One of the potential applications of such methodology in clinics concerns the evaluation of the rehabilitation after hip fracture. In this work, 20 inpatients, in the acute phase after hip fracture surgery and with lower limb weakness, performed isometric contractions with their healthy lower limb (quadriceps muscle) and their resistance to fatigue before and after 2 weeks of rehabilitation program was measured. Multi-channel EMG and Maximum Voluntary Contractions (MVC, force) were recorded on five muscle heads. We found that, after performing the same number of repetitions (repetitions pre-treatment: 19.7 ± 1.34; repetitions post-treatment: 19.9 ± 0.36; p = 0.223), MVC improved (MVC pre-treatment: 278 ± 112 N; MVC post-treatment: 322 ± 88 N; p = 0.015) after rehabilitation for most of the patients and fatigue did not change. These results suggest that higher force exertion was performed after rehabilitation, with the same level of fatigue (fatigued muscles pre-treatment: 1.40 ± 1.70; fatigued muscles post-treatment: 1.15 ± 1.59; p = 0.175) after. Results are discussed addressing the potential of multifactorial instrumental assessments for describing patients’ status and provide data for clinical decision making.

Method for Assessing the Motor Coordination of Runners Based on the Analysis of Multichannel EMGs.

In this paper, we propose a method to evaluate the motor coordination of runners based on the analysis of amplitude and spatiotemporal dynamics of multichannel electromyography. A new diagnostic index for the coordination of runners was proposed, including the amplitude of electromyography, the spatiotemporal stability coefficient, and the symmetry coefficient of muscle force. The motor coordination of 13 professional runners was studied. Detailed anthropometric information was recorded about the professional runners. It has been found that professional athletes are characterized by the stability of movement repetition (more than 83%) and the high degree of symmetry of muscle efforts of the left and right legs (more than 81%) regardless of the changes in load during running at a speed of 8-12 km/hr. Scientific and technological means can support the scientific training of athletes. The end of the Winter Olympic Games has shown us the powerful power of a series of intelligent scientific equipment, including electro-magnetic gun, in sports training. We also look forward to the continuous innovation of these advanced technologies, which will contribute to the intelligent development of sports scientific research.

Surface EMG analysis of weakness distribution in upper limb muscles post-stroke.

Weakness is a common symptom after a stroke. This study aims to depict weakness distribution among forearm muscles given that joints in the upper limb are usually driven by a group of muscles. Multi-channel electromyography (EMG) was applied to assess the muscle group, and an EMG-based index was proposed to quantify the weakness of individual muscles. By using this method, four weakness distribution patterns were observed in extensor muscles from five out of eight subjects after stroke. Complex weakness distribution patterns were observed in flexor muscles from seven out of the eight subjects when they performed grasp, tripod pinch, and hook grip. The findings can help determine the weak muscles in a clinic and facilitate the development of appropriate interventions in stroke rehabilitation targeting specific muscle weakness.

Activity Distribution Among the Hamstring Muscles During the Nordic Hamstring Exercise: A Multichannel Surface Electromyography Study.

This study assessed activity distribution among the hamstring muscles during the Nordic hamstring exercise (NHE). The objective was to compare muscle activity between and within muscles during the NHE to add insights in its underlying protective mechanism. Through multichannel electromyography, we measured muscle activity in male basketball players during the NHE. Electromyography was assessed at 15 locations: 5 for biceps femoris long head, 4 for semitendinosus, and 6 for semimembranosus. For each percent of the eccentric phase of the NHE, muscle activity was calculated for each electrode location within each hamstring muscle individually. To quantify whole muscle head activity, means and variances across electrodes within each muscle were calculated. Thirty-five noninjured participants were included (mean age, 18 [2]y; mass, 87 [12]kg; height, 192 [9]cm). Heterogeneous muscle activity was found between 38% and 62% and over the whole eccentric contraction phase within the semitendinosus and the semimembranosus, respectively. Muscle activity of the semitendinosus was significantly higher than that of the biceps femoris long head. During the NHE, the relative contribution of the semitendinosus is the highest among hamstring muscles. Its strong contribution may compensate for the biceps femoris long head, the most commonly injured hamstring muscle head.

Activity distribution among the hamstring muscles during high-speed running: A descriptive multichannel surface EMG study.

This study assessed activity distribution among the hamstring muscles during high-speed running. The objective was to compare within and between muscle activity, relative contribution and hip and knee joint angles at peak muscle activity during high-speed running. Through multichannel electromyography, we measured muscle activity in male basketball players during high-speed running on a treadmill at 15 locations: five for biceps femoris long head, four for semitendinosus, and six for semimembranosus. Muscle activity was calculated for each location within each hamstring muscle individually for each percent of a stride cycle. Twenty-nine non-injured basketball players were included (mean age: 17 ± 1 years; mass, 85 ± 9kg; height, 193 ± 9cm). Heterogeneous activity was found for all individual hamstring muscles across multiple events of the stride cycle. In the late-swing phase, muscle activity and relative contribution of the semimembranosus was significantly higher than of the semitendinosus. There was no significant difference in hip and knee joint angles at instant of peak muscle activity, assessed locally within individual hamstring muscles, as well as in general over the whole hamstring muscle. Hamstring muscles were most active in the late-swing phase during high-speed running. In this phase, the semimembranosus was most active and the semitendinosus was least active. Within the biceps femoris long head, the most proximal region was significantly more active in the late-swing phase, compared to other muscle regions. For each muscle and location, peak muscle activity occurred at similar hip and knee joint angles.

A Wearable Master–Slave Rehabilitation Robot Based on an Epidermal Array Electrode Sleeve and Multichannel Electromyography Network

Investigating electromyography (EMG) signals is vital to promote the development of both rehabilitative robots and understanding of the movement neural mechanism. Interactions between various muscle units are paramount to be measured through network analysis, aiming to reveal how information is propagated and integrated. Herein, an EMG network using an epidermal array electrode sleeve to record multichannel EMGs is constructed. Then, a master–slave rehabilitation robot by adopting the EMG network as a feature for movement intention recognition is built. The results demonstrate that the sleeve can record signals with high quality, characterized by better signal robustness and higher movement recognition performance. The different finger movements evoke the specific spatial network patterns, characterized by the dominated hub at the muscle in charge of the corresponding movement, and the proposed EMG network‐based approach consistently achieves the highest recognition accuracy. Moreover, the proposed approach also shows the relatively less influence of signal length and electrode positions on the movement recognition. Finally, the proposed robot system can achieve 98.21% ± 2.37 accuracy for online control. These results provide a novel theoretical and practical basis for neural prosthesis control and hemiplegic hand rehabilitation.

A Multichannel EMG System for Spatial Measurement of Diaphragm Activities

An important aspect of mechanical ventilation is the recognition and quantification of spontaneous respiratory effort. However, a measurement of flows and pressures often used for this purpose is prone to error. A promising alternative is to detect diaphragmatic contractions, directly. A method recently proposed is to acquire the diaphragm electromyography (EMG) signals using surface electrodes. However, this method is often limited by disturbances and electrode placements for some applications in which the patient is moving, such as rehabilitation or breathing training. In this work, we present a novel noninvasive method that addresses these problems. This method is based on a novel dry electrode belt, which can be used to comfortably derive EMG signals from the thorax, in combination with a developed electrical measurement system. The modular multichannel system is capable of simultaneously deriving and digitizing 32 differential EMG channels and sending them to a personal computer (PC). A specific digital signal processing chain allows combining the data into one robust overall signal. In addition, the signals derived from the thorax can be used to obtain information regarding the spatiotemporal propagation of the diaphragm EMG. To verify the functionality, the system is characterized. Subsequently, subject measurements are performed. From these, the spatiotemporal propagation of diaphragm EMG on the thorax can be identified. For better visualization, this propagation is graphically displayed in a 3-D model. In addition, it is shown how the combination of all signals can be used to obtain a robust overall signal that can be used to control ventilators.

사용자 환경에 따라 적용 가능한 EMG 기반 손동작 인식 기법

Recognition and prediction of hand gestures using electromyography(EMG) has various applications, such as in devices for human robot interactions, rehabilitation of paralytic patients, and prostheses for amputees. These application can be broadly divided into specific user-only environment and universal user environment. However, in multi-channel EMG used in many recent studies, there are numerous individual differences in the acquired data depending on the user, which cause serious performance degradation in the universal user environment. In this study, EMG data were collected from five subjects for 15 hand gestures using an 8 channel armband EMG sensor at a sampling frequency of 1000 Hz, and the individual differences in the EMG intensity (voltage) and activation channels were analyzed. In addition, the hand gestures were recognized using a convolutional recurrent neural network (CRNN) deep- learning architecture as a classifier, and an average accuracy of 95% was obtained in the experiments considering the user-only environment. In the experiments considering the universal user environment, 15 hand gestures were recognized with an average accuracy of 87.7% by applying the transfer learning technique. Thus, for hand gestures used in everyday life, we propose a recognition method that can be applied according to the user environment, from user-only environments to universal user environments.

An enhanced EMG-driven Musculoskeletal model based on non-negative matrix factorization

In recent years, electromyography (EMG) signals have been widely used in human–machine interfaces (HMIs). Musculoskeletal models (MMs) have been employed to decode human movement intentions from EMG signals in HMIs. Non-negative matrix factorization (NMF) has been adopted to extract neural control information from surface EMG signals. The aim of this study was to investigate if the NMF could extract the control information from surface EMG signals to substitute muscle activations of the deep muscles of the MM. An enhanced MM based on NMF (NMF-MM) was proposed to predict wrist pronation/supination (Pro/Sup) joint angles from surface EMG signals. We extracted the muscle activations of a pair of virtual agonist–antagonistic muscles with NMF from multi-channel EMG signals and inputted the extracted signals into the MM. Eight able-bodied subjects were recruited and tested in four different upper limb postures. Eight bipolar electrodes were attached to the upper forearm to record EMG signals. The Pearson’s correlation coefficient (r) and the normalized root mean square error (NRMSE) between measured and predicted joint angles were adopted to quantify the performance of the decoding methods. The performance of the proposed NMF-MM was compared with that of the NMF, linear regression (LR), artificial neural network (ANN), LR based on NMF (NMF-LR), ANN based on NMF (NMF-ANN), LR based on time-domain features (TD-LR), and ANN based on time-domain features (TD-ANN). The results demonstrated that the NMF-MM outperformed the other methods with higher prediction accuracy and better robustness. This study proposed a promising method for predicting continuous and coordinated movements in HMIs.

Synergistic Upper-Limb Functional Muscle Connectivity Using Acoustic Mechanomyography.

Functional muscle network is a critical concept in describing functional synergistic muscle synchronization and functional connectivity needed for the execution of complex motor tasks. Muscle network is typically derived from decomposition of intermuscular coherence (IMC) at different frequency bands of multichannel electromyography (EMG) measurements, which potentially limits out-of-clinic applications. In this investigation, we introduce muscle network analysis to assess the functional coordination and functional connectivity of muscles based on mechanomyography (MMG). We focus on a targeted group of muscles vital for activities of daily living (ADLs) in the upper-limb. Functional muscle networks are evaluated for ten able-bodied participants and three upper-limb amputees. Muscle activity was acquired from a custom-made wearable armband of MMG sensors placed over four superficial muscles around the forearm (flexor carpi radialis (FCR), brachioradialis (BR), extensor digitorum communis (EDC), and flexor carpi ulnaris (FCU)) while participants performed four different hand gestures. Muscle connectivity analysis at multiple frequency bands shows significant topographical differences across gestures for low (i.e., 5 Hz) and high (i.e., 12 Hz) activation frequencies as well as observable network differences between amputee and non-amputee subjects. Results demonstrate MMG can be used for the analysis of functional muscle connectivity and mapping of synergistic functional synchronization of upper-limb muscles in complex movement tasks. The new physiological modality provides key insights into neural circuitry of motor coordination. Findings further offer the concomitant outcomes of demonstrating feasibility of MMG to map muscle coherence from a neurophysiological perspective and providing a mechanistic basis for its translation in human-robot interface.

Low back muscle action potential conduction velocity estimated using high-density electromyography

While a decreasing spectral content of surface electromyography reflects low back muscle fatigue development, reliability of these decreases may be insufficient. Decreasing frequency content is largely determined by decreasing average motor unit action potential conduction velocities (CV), which is considered a more direct measure of muscle fatigue development. However, for the low back muscles it has been proven difficult to identify propagating potentials and consequently estimate the CV. The aim of this study was to estimate the low back muscle CV from high-density multi-channel electromyography by using peak-delay and cross-correlation methods. Fourteen healthy male participants without a history of low-back pain performed a 30 degrees lumbar flexion trial until exhaustion while standing. For 10 out of the 14 participants (118 out of 560 sites) realistic CV estimates were obtained using both methods, the majority likely over the iliocostalis lumborum muscle. Between-method CV differences appeared to be small. Close to the spine a considerable number of sites (79) yielded systematically overestimated low back muscle CV values. Estimating low back muscle CV may allow additional insight into low back muscle fatigue development and potentially improve its monitoring using (high-density) surface electromyography.

Long-term results of pathogenetically-grounded methods of treatment of patients with postthrombotic syndrome of the lower extremities according to three-year follow-up

The aim of this study was to evaluate the effectiveness of surgical treatment using a modified method of correction of venous hemodynamic disorders of the lower extremities by the state of function of the leg muscle pump during long-term follow-up in the postoperative period of patients with postthrombotic syndrome of the lower extremities. 148 patients with lower limb postthrombotic syndrome (С5, 6, S, Es, As, d, p, Pr, LI by CEAP classification) were divided in two groups. The first group included 71 patients, which were treated by traditional methods of surgical intervention (crossectomy and venecseresis). The second group consisted of 77 patients who underwent closed separation of the perforating veins and paratibial fasciotomy in the complex of surgical treatment. The function of the leg muscle pump was studied using three methods: a 6-minute marching test measuring the circumference of the limbs, the amplitude indices of movements in the ankle joint with a protractor, and electromyography using a multichannel electromyography with skin electrode application. The quality of life was studied using the CIVIQ questionnaire, the severity of venous pathology by the VCSS scale and disability rates by the VDS disability scale. The examination was performed before the surgery, after 1 year and after 3 years of observation. In both groups of patients, there was a decrease in the basal levels of a 6-minute marching test, the movement amplitude in the ankle joint, the electromyography indicators, the presence of a strong correlation between these parameters, indicating venous dysfunction in the lower extremities. In the postsurgical period (in 1 and 3 years), there was a reduced circumference of the legs during the marching test, an increased amplitude of movements in the ankle joint and electromyography indicators – the mean and maximum amplitude of oscillations. In patients of group II, the results were better than in patients of group I. In the pre-surgical period, a significant deterioration of the life quality was observed in terms of the CIVIQ questionnaire, the severity of venous pathology – by the VCSS scale and a decrease in working capacity – by the VDS disability scale in both groups. In the long-term postsurgical period, there was an improvement of these indicators, more pronounced in patients of group II. Clinical study of long-term results of the closed separation of perforating veins and paratibial fasciotomy operation confirmed the high efficiency of this method and allowed us to consider it as a pathogenetically-grounded method of surgical treatment of patients with postthrombotic syndrome of the lower extremities.

Myoclonus and tremor in chronic inflammatory demyelinating polyneuropathy: a multichannel electromyography analysis.

Information regarding involuntary movements in chronic inflammatory polyneuropathy (CIDP) is gradually increasing. Our goal is to identify the types of involuntary movements in CIDP. All patients who were followed with the diagnosis of CIDP were invited for clinical and electrophysiological evaluations. Demographic and clinical findings (age, gender, duration of illness, diagnosis, treatments) were noted. Clinical examination and multichannel surface electromyography were done. We also performed routine upper and lower extremity peripheral nerve conduction studies, F-waves, long latency reflexes, blink reflex, mixed nerve silent period and cutaneous silent period in all patients. Twenty-two patients accepted the invitation. Eleven patients with CIDP had involuntary movements. Ten (45.5%) patients with CIDP had tremor and seven (31.8%) had short-duration and high-amplitude myoclonus. Regarding demographic, clinical and electrophysiological features, there was no significant difference between patients with and without tremor. The latencies of R1, R2 and R2c components of BR were longer among CIDP patients without tremor compared to CIDP patients with tremor. Presence of myoclonus (p = 0.007) and delayed F-waves (p = 0.008) were associated with the presence of tremor. Tremor and myoclonus were frequent in CIDP. The fact that myoclonus was detected in the majority of patients only by multichannel surface EMG who were clinically evaluated as pure tremor suggests that a more detailed electrophysiological evaluation is required. There was no difference in the medications used or other clinical features between patients with and without tremor.

Spatio-temporal warping for myoelectric control: an offline, feasibility study

Objective. The efficacy of an adopted feature extraction method directly affects the classification of the electromyographic (EMG) signals in myoelectric control applications. Most methods attempt to extract the dynamics of the multi-channel EMG signals in the time domain and on a channel-by-channel, or at best pairs of channels, basis. However, considering multi-channel information to build a similarity matrix has not been taken into account. Approach. Combining methods of long and short-term memory (LSTM) and dynamic temporal warping, we developed a new feature, called spatio-temporal warping (STW), for myoelectric signals. This method captures the spatio-temporal relationships of multi-channels EMG signals. Main results. Across four online databases, we show that in terms of average classification error and standard deviation values, the STW feature outperforms traditional features by 5%–17%. In comparison to the more recent deep learning models, e.g. convolutional neural networks (CNNs), STW outperformed by 5%–18%. Also, STW showed enhanced performance when compared to the CNN + LSTM model by 2%–14%. All differences were statistically significant with a large effect size. Significance. This feasibility study provides evidence supporting the hypothesis that the STW feature of the EMG signals can enhance the classification accuracy in an explainable way when compared to recent deep learning methods. Future work includes real-time implementation of the method and testing for prosthesis control.

Clusterization of multi-channel electromyograms into muscle-specific activations to drive a subject-specific musculoskeletal model: towards fast and accurate clinical decision-making.

Current clinical decision-making is based on rapid and subjective functional tests such as 10 m walking. Moreover, greater accuracy can be achieved at the expense of rapidity and costs. In biomechanical laboratories, advanced technologies and musculoskeletal modeling can quantitatively describe the biomechanical reasons underlying gait disorders. Our work aims to blend clinical rapidity and biomechanical accuracy through multi-channel (MC) electromyography (EMG) clustering and real-time neuro-musculoskeletal (NMS) modeling techniques integrated into a sensorized wearable garment that is quick to set up. Here we present a unique pipeline that goes from MC EMG signals to ankle torque estimation following two steps: (1) non-negative matrix factorization (NNMF)-based EMG clustering for the extraction of muscle-specific activations and (2) subject-specific EMG-driven NMS modeling. The results show the potential of NNMF as an electrode clustering tool, as well as the ability to predict joint torque during movements that were not used for the EMG clustering.

Toward Deep Generalization of Peripheral EMG-Based Human-Robot Interfacing: A Hybrid Explainable Solution for NeuroRobotic Systems

This letter investigates the feasibility of a generalizable solution for human-robot interfaces through peripheral multichannel Electromyography (EMG) recording. We propose a tangential approach in comparison to the literature to minimize the need for (re)calibration of the system for new users. The proposed algorithm decodes the signal space and detects the common underlying global neurophysiological components, which can be detected robustly across various users, minimizing the need for retraining and (re)calibration. The research question is how to go beyond techniques that detect a high number of gestures for a given individual (which requires extensive calibration) and achieve an algorithm that can detect a lower number of classes but without the need for (re)calibration. The outcomes of this letter address a challenge affecting the usability and acceptance of advanced myoelectric prostheses. For this, the paper proposes an explainable generalizable hybrid deep learning architecture that incorporates CNN and LSTM. We also utilize the GradCAM analysis to explain and optimize the structure of the generalized model, securing higher computational performance whiles proposing a shallower design.