Intramuscular EMG Research Articles

Fatigue-related changes in intermuscular electromyographic coherence across rotator cuff and deltoid muscles in individuals with and without subacromial pain.

Neuromuscular fatigue induces superior migration of the humeral head in individuals with subacromial pain. This has been attributed to weakness of rotator cuff muscles and overactive deltoid muscles. Investigation of common inputs to motoneuron pools of the rotator cuff and deltoid muscles offers valuable insight into the underlying mechanisms of neuromuscular control deficits associated with subacromial pain. This study aims to investigate intermuscular coherence across the rotator cuff and deltoid muscles during a sustained submaximal isometric fatiguing contraction in individuals with and without subacromial pain. Twenty symptomatic and 18 asymptomatic young adults participated in this study. Surface electromyogram (EMG) was recorded from the middle deltoid (MD) and infraspinatus (IS). Intramuscular EMG was recorded with fine-wire electrodes in the supraspinatus (SS). Participants performed an isometric fatiguing contraction of 30° scaption at 25% maximum voluntary contraction (MVC) until endurance limit. Pooled coherence of muscle pairs (SS-IS, SS-MD, IS-MD) in the 2-5 Hz (delta), 5-15 Hz (alpha), and 15-35 Hz (beta) frequency bands during the initial and final 30 s of the fatigue task were compared. SS-IS and SS-MD delta-band coherence increased with fatigue in the asymptomatic group but not the symptomatic group. In the alpha and beta bands, SS-IS and SS-MD coherence increased with fatigue in both groups. IS-MD beta-band coherence was greater in the symptomatic than the asymptomatic group. Individuals with subacromial pain failed to increase common drive across rotator cuff and deltoid muscles and have altered control strategies during neuromuscular fatigue. This may contribute to glenohumeral joint instability and subacromial pain experienced by these individuals.NEW & NOTEWORTHY Through the computation of shared neural drive across glenohumeral muscles, this study reveals that individuals with subacromial pain were unable to increase shared neural drive within the rotator cuff and across the supraspinatus and deltoid muscles during neuromuscular fatigue induced by sustained isometric contraction. These deficits in common drive across the shoulder muscles likely contribute to the joint instability and pain experienced by these individuals.

Development of a novel technique to insert intramuscular electromyography electrodes into the deep intrinsic foot muscles via the dorsum of the foot

This study aimed to develop an insertion technique for intramuscular EMG recording of the oblique head of adductor hallucis (AddH) and first dorsal interosseous (FDI) muscles in humans via the dorsum of the foot, and report feasibility of intramuscular EMG data acquisition during walking in shoes. In eight individuals without musculoskeletal pain or injury (5 males; 32 ± 8 years), intramuscular electrodes were inserted into AddH (oblique head) and FDI through the right foot’s dorsum (between metatarsals I-II) with ultrasound guidance. The ultrasound transducer was positioned on the plantar surface. Intramuscular EMG was also recorded from abductor hallucis, tibialis posterior, flexor digitorum longus and peroneus longus. Participants performed six overground walking trials wearing modified shoes, and rated pain associated with the intramuscular electrodes during walking (numerical rating scale, 0–10). High-quality EMG recordings were obtained from intrinsic and extrinsic foot muscles. Analyses of power spectral densities indicated that movement artefacts commonly observed during gait were removed by filtering. Pain associated with AddH/FDI electrodes during walking was low (median[IQR] 1[2]; range 0–4) and similar to other sites. Findings demonstrate that intramuscular EMG recording from AddH (oblique head) and FDI using this insertion technique is feasible and associated with minimal pain when walking in shoes.

External focus instruction using a paper balloon: impact on trunk and lower extremity muscle activity in isometric single-leg stance for healthy males.

Core stability is crucial for preventing and rehabilitating lumbar spine injuries. An external focus instruction using a paper balloon is an effective way to activate the trunk muscles. However, the degree of trunk and lower extremity muscle activation during single leg stance with external focus instruction using a paper balloon is unknown. This study aimed to investigate the core muscle involving activity in the trunk and lower extremities on both the support and non-support sides with or without using external focus instruction using a paper balloon during isometric single-leg stance. Thirteen healthy males aged 20-28 years volunteered to take part in this study and performed a single leg stance task with and without an external focus instruction, pressing their non-supporting foot onto a paper balloon without crushing it. The participant's muscle electrical activity was recorded during the single leg task using surface EMG and intramuscular EMG for six trunk muscles (transversus abdominis, internal oblique, external oblique, rectus abdominis, multifidus, and lumbar erector spinae) and five lower extremity muscles (gluteus maximus, gluteus medius, adductor longus, rectus femoris, and biceps femoris). Compared to the normal single leg stance, the external focus instruction task using a paper balloon showed significantly increased transversus abdominis (p < 0.001, p < 0.001), internal oblique (p = 0.001, p < 0.001), external oblique (p = 0.002, p = 0.001), rectus abdominal (p < 0.001, p < 0.001), lumbar multifidus (p = 0.001, p < 0.001), lumbar erector spinae (p < 0.001, p = 0.001), adductor longus (p < 0.001, p < 0.001), rectus femoris (p < 0.001, p < 0.001), and biceps femoris (p < 0.010, p < 0.001) muscle activity on the support and non-support sides. In conclusion, external focus instruction using a paper balloon significantly activates the trunk and lower extremities muscles on both the support and non-support sides. This finding provides insights for designing programs to improve coordination and balance. The benefits extend to diverse individuals, encompassing athletes, tactical professionals, and the general population, mitigating the risk of injury or falls linked to inadequate lower limb balance.

Inferring position of motor units from high-density surface EMG

The spatial distribution of muscle fibre activity is of interest in guiding therapy and assessing recovery of motor function following injuries of the peripheral or central nervous system. This paper presents a new method for stable estimation of motor unit territory centres from high-density surface electromyography (HDsEMG). This completely automatic process applies principal component compression and a rotatable Gaussian surface fit to motor unit action potential (MUAP) distributions to map the spatial distribution of motor unit activity. Each estimated position corresponds to the signal centre of the motor unit territory. Two subjects were used to test the method on forearm muscles, using two different approaches. With the first dataset, motor units were identified by decomposition of intramuscular EMG and the centre position of each motor unit territory was estimated from synchronized HDsEMG data. These positions were compared to the positions of the intramuscular fine wire electrodes with depth measured using ultrasound. With the second dataset, decomposition and motor unit localization was done directly on HDsEMG data, during specific muscle contractions. From the first dataset, the mean estimated depth of the motor unit centres were 8.7, 11.6, and 9.1 mm, with standard deviations 0.5, 0.1, and 1.3 mm, and the respective depths of the fine wire electrodes were 8.4, 15.8, and 9.1 mm. The second dataset generated distinct spatial distributions of motor unit activity which were used to identify the regions of different muscles of the forearm, in a 3-dimensional and projected 2-dimensional view. In conclusion, a method is presented which estimates motor unit centre positions from HDsEMG. The study demonstrates the shifting spatial distribution of muscle fibre activity between different efforts, which could be used to assess individual muscles on a motor unit level.

Stylohyoid and Posterior Digastric Potential Evaluation for a Swallowing Detection With Intramuscular EMG

Stylohyoid and Posterior Digastric Potential Evaluation for a Swallowing Detection With Intramuscular EMG

Review of electromyography onset detection methods for real-time control of robotic exoskeletons

BackgroundElectromyography (EMG) is a classical technique used to record electrical activity associated with muscle contraction and is widely applied in Biomechanics, Biomedical Engineering, Neuroscience and Rehabilitation Robotics. Determining muscle activation onset timing, which can be used to infer movement intention and trigger prostheses and robotic exoskeletons, is still a big challenge. The main goal of this paper was to perform a review of the state-of-the-art of EMG onset detection methods. Moreover, we compared the performance of the most commonly used methods on experimental EMG data.MethodsA total of 156 papers published until March 2022 were included in the review. The papers were analyzed in terms of application domain, pre-processing method and EMG onset detection method. The three most commonly used methods [Single (ST), Double (DT) and Adaptive Threshold (AT)] were applied offline on experimental intramuscular and surface EMG signals obtained during contractions of ankle and knee joint muscles.ResultsThreshold-based methods are still the most commonly used to detect EMG onset. Compared to ST and AT, DT required more processing time and, therefore, increased onset timing detection, when applied on experimental data. The accuracy of these three methods was high (maximum error detection rate of 7.3%), demonstrating their ability to automatically detect the onset of muscle activity. Recently, other studies have tested different methods (especially Machine Learning based) to determine muscle activation onset offline, reporting promising results.ConclusionsThis study organized and classified the existing EMG onset detection methods to create consensus towards a possible standardized method for EMG onset detection, which would also allow more reproducibility across studies. The three most commonly used methods (ST, DT and AT) proved to be accurate, while ST and AT were faster in terms of EMG onset detection time, especially when applied on intramuscular EMG data. These are important features towards movement intention identification, especially in real-time applications. Machine Learning methods have received increased attention as an alternative to detect muscle activation onset. However, although several methods have shown their capability offline, more research is required to address their full potential towards real-time applications, namely to infer movement intention.

Mechanisms underlying the prolonged activation of the genioglossus following arousal from sleep.

Transient arousal from sleep has been shown to elicit a prolonged increase in genioglossus muscle activity that persists following the return to sleep and which may protect against subsequent airway collapse. We hypothesized that this increased genioglossal activity following return to sleep after an arousal is due to persistent firing of inspiratory-modulated motor units (MUs) that are recruited during the arousal. Thirty-four healthy participants were studied overnight while wearing a nasal mask with pneumotachograph to measure ventilation and with 4 intramuscular genioglossus EMG electrodes. During stable N2 and N3 sleep, auditory tones were played to induce brief (3-15s) AASM arousals. Ventilation and genioglossus MUs were quantified before the tone, during the arousal and for 10 breaths after the return to sleep. A total of 1089 auditory tones were played and gave rise to 239 MUs recorded across arousal and the return to sleep in 20 participants (aged 23 ± 4.2 years and BMI 22.5 ± 2.2 kg/m2). Ventilation was elevated above baseline during arousal and the first post-arousal breath (p < .001). Genioglossal activity was elevated for five breaths following the return to sleep, due to increased firing rate and recruitment of inspiratory modulated MUs, as well as a small increase in tonic MU firing frequency. The sustained increase in genioglossal activity that occurs on return to sleep after arousal is primarily a result of persistent activity of inspiratory-modulated MUs, with a slight contribution from tonic units. Harnessing genioglossal activation following arousal may potentially be useful for preventing obstructive respiratory events.

Non-invasive estimation of muscle fibre size from high-density electromyography.

Because of the biophysical relation between muscle fibre diameter and the propagation velocity of action potentials along the muscle fibres, motor unit conduction velocity could be a non-invasive index of muscle fibre size in humans. However, the relation between motor unit conduction velocity and fibre size has been only assessed indirectly in animal models and in human patients with invasive intramuscular EMG recordings, or it has been mathematically derived from computer simulations. By combining advanced non-invasive techniques to record motor unit activity in vivo, i.e. high-density surface EMG, with the gold standard technique for muscle tissue sampling, i.e. muscle biopsy, here we investigated the relation between the conduction velocity of populations of motor units identified from the biceps brachii muscle, and muscle fibre diameter. We demonstrate the possibility of predicting muscle fibre diameter (R2 =0.66) and cross-sectional area (R2 =0.65) from conduction velocity estimates with low systematic bias (∼2% and ∼4% respectively) and a relatively low margin of individual error (∼8% and ∼16%, respectively). The proposed neuromuscular interface opens new perspectives in the use of high-density EMG as a non-invasive tool to estimate muscle fibre size without the need of surgical biopsy sampling. The non-invasive nature of high-density surface EMG for the assessment of muscle fibre size may be useful in studies monitoring child development, ageing, space and exercise physiology, although the applicability and validity of the proposed methodology need to be more directly assessed in these specific populations by future studies. KEY POINTS: Because of the biophysical relation between muscle fibre size and the propagation velocity of action potentials along the sarcolemma, motor unit conduction velocity could represent a potential non-invasive candidate for estimating muscle fibre size in vivo. This relation has been previously assessed in animal models and humans with invasive techniques, or it has been mathematically derived from simulations. By combining high-density surface EMG with muscle biopsy, here we explored the relation between the conduction velocity of populations of motor units and muscle fibre size in healthy individuals. Our results confirmed that motor unit conduction velocity can be considered as a novel biomarker of fibre size, which can be adopted to predict muscle fibre diameter and cross-sectional area with low systematic bias and margin of individual error. The proposed neuromuscular interface opens new perspectives in the use of high-density EMG as a non-invasive tool to estimate muscle fibre size without the need of surgical biopsy sampling.

Variational mode decomposition for surface and intramuscular EMG signal denoising

Electromyographic signals contaminated with noise during the acquisition process affect the results of follow-up applications such as disease diagnosis, motion recognition, gesture recognition, and human–computer interaction. This paper proposes a denoising technique based on the variational mode decomposition (VMD) for both surface electromyography signals (sEMG) and intramuscular electromyography signals (iEMG). sEMG and iEMG obtained from 5 healthy subjects were first decomposed using VMD into respective variational mode functions (VMFs), then thresholds were set to remove the noise, and finally, the denoised signal was reconstructed. The denoising efficacy of interval thresholding (IT) and iterative interval thresholding (IIT) techniques in combination with SOFT, HARD, and smoothly clipped absolute deviation (SCAD) thresholding operators was quantitatively evaluated by using Signal to Noise Ratio (SNR) and further statistically validated by Friedman test. The results demonstrated that IIT provides better SNR values than IT at all noise levels (P-value < 0.05) for sEMG signals. For iEMG, IIT outperformed IT at 0db and 5db noise levels, but at a noise level of 10db and 15db, IT outperformed IIT. However, the results for the 10db noise level were statistically insignificant. The SOFT thresholding operator outperforms HARD and SCAD at all noise levels for sEMG, as well as iEMG (P-value < 0.05). The study demonstrates that the combination of the IIT thresholding technique with the VMD-based SOFT thresholding operator yields the best denoising results while retaining the original signal characteristics. The proposed method can be used in the fields of disease diagnosis, pattern recognition, and movement classification.

An Accurate and Real-Time Method for Resolving Superimposed Action Potentials in MultiUnit Recordings.

Spike sorting of muscular and neural recordings requires separating action potentials that overlap in time (superimposed action potentials (APs)). We propose a new algorithm for resolving superimposed action potentials, and we test it on intramuscular EMG (iEMG) and intracortical recordings. Discrete-time shifts of the involved APs are first selected based on a heuristic extension of the peel-off algorithm. Then, the time shifts that provide the minimal residual Euclidean norm are identified (Discrete Brute force Correlation (DBC)). The optimal continuous-time shifts are then estimated (High-Resolution BC (HRBC)). In Fusion HRBC (FHRBC), two other cost functions are used. A parallel implementation of the DBC and HRBC algorithms was developed. The performance of the algorithms was assessed on 11,000 simulated iEMG and 14,000 neural recording superpositions, including two to eight APs, and eight experimental iEMG signals containing four to eleven active motor units. The performance of the proposed algorithms was compared with that of the Branch-and-Bound (BB) algorithm using the Rank-Product (RP) method in terms of accuracy and efficiency. The average accuracy of the DBC, HRBC and FHRBC methods on the entire simulated datasets was 92.16±17.70, 93.65±16.89, and 94.90±15.15 (%). The DBC algorithm outperformed the other algorithms based on the RP method. The average accuracy and running time of the DBC algorithm on 10.5 ms superimposed spikes of the experimental signals were 92.1±21.7 (%) and 2.3±15.3 (ms). The proposed algorithm is promising for real-time neural decoding, a central problem in neural and muscular decoding and interfacing.

Identification of Motor Unit Firings in H-Reflex of Soleus Muscle Recorded by High-Density Surface Electromyography.

We developed and tested the methodology that supports the identification of individual motor unit (MU) firings from the Hoffman (or H) reflex recorded by surface high-density EMG (HD-EMG). Synthetic HD-EMG signals were constructed from simulated 10% to 90% of maximum voluntary contraction (MVC), followed by 100 simulated H-reflexes. In each H-reflex the MU firings were normally distributed with mean latency of 20 ms and standard deviations (SDLAT) ranging from 0.1 to 1.3 ms. Experimental H-reflexes were recorded from the soleus muscle of 12 men (33.6 ± 5.8 years) using HD-EMG array of 5×13 surface electrodes. Participants performed 15 to 20 s long voluntary plantarflexions with contraction levels ranging from 10% to 70% MVC. Afterwards, at least 60 H-reflexes were electrically elicited at three levels of background muscle activity: rest, 10% and 20% MVC. HD-EMGs of voluntary contractions were decomposed using the Convolution Kernel Compensation method to estimate the MU filters. When applied to HD-EMG signals with synthetic H reflexes, MU filters demonstrated high MU identification accuracy, especially for [Formula: see text] ms. When applied to experimental H-reflex recordings, the MU filters identified 14.1 ± 12.1, 18.2 ± 12.1 and 20.8 ± 8.7 firings per H-reflex, with individual MU firing latencies of 35.9 ± 3.3, 35.1 ± 3.0 and 34.6 ± 3.3 ms for rest, 10% and 20% MVC background muscle activity, respectively. Standard deviation of MU latencies across experimental H-reflexes were 1.0 ± 0.8, 1.3 ± 1.1 and 1.5 ± 1.2 ms, in agreement with intramuscular EMG studies.

Intramuscular EMG feature extraction and evaluation at different arm positions and hand postures based on a statistical criterion method.

Prostheses control using electromyography signals have shown promising aspects in various fields including rehabilitation sciences and assistive technology controlled devices. Pattern recognition and machine learning methods have been observed to play a significant role in evaluating features and classifying different limb motions for enhanced prosthetic executions. This paper proposes feature extraction and evaluation method using intramuscular electromyography (iEMG) signals at different arm positions and hand postures based on the RES Index value statistical criterion method. Sixteen-time domain features were selected for the study at two main circumstances; fixed arm position (FAP) and fixed hand posture (FHP). Eight healthy male participants (30.62 ± 3.87 years) were asked to execute five motion classes including hand grip, hand open, rest, hand extension, and hand flexion at four different arm positions that comprise of 0°, 45°, 90°, and 135°. The classification process is accomplished via the application of the k-nearest neighbor (KNN) classifier. Then RES index was calculated to investigate the optimal features based on the proposed statistical criterion method. From the RES Index, we concluded that Variance (VAR) is the best feature while WAMP, Zero Crossing (ZC), and Slope Sign Change (SSC) are the worst ones in FAP conditions. On the contrary, we concluded that Average Amplitude Change (AAC) is the best feature while WAMP and Simple Square Integral (SSI) resulted in least RES Index values for FHP conditions. The proposed study has possible iEMG based applications such as assistive control devices, robotics. Also, working with the frequency domain features encapsulates the future scope of the study.

Pterygoid muscle activity in speech: A preliminary investigation.

Speaking depends on refined control of jaw opening and closing movements. The medial pterygoid muscle (MPT), involved in jaw closing, and the lateral pterygoid muscle (LPT), involved in jaw opening, are two key mandibular muscles in mastication and are likely to be recruited for controlled movements in speech. Three hypotheses were investigated, that during speech the MPT and LPT: (1) were both active, (2) but exhibited different patterns of activity, (3) which fluctuated with the vowels and consonants in speech. Intramuscular EMG recordings were made from the right inferior head of the LPT and/or the right MPT in five participants during production of 40 target nonsense words (NWs) consisting of three syllables in the form /V1 C1 V2 C2 ə/ (V=vowel; C=consonant; ə=unstressed, reduced vowel), spoken by each participant 10 times per NW; analysis focussed on the target syllable, C1 V2 . Both MPT and LPT exhibited robust increases in EMG activity during utterance of most NWs, relative to rest. Peak LPT activation was time-locked to the final part of the target consonant (C1 ) interval when the jaw begins opening for the target vowel (V2 ), whereas peak MPT activation occurred around the temporal midpoint of V2 , when the jaw begins closing for C2 . EMG amplitude peaks differed in magnitude between "high" vowels, i.e., for which the tongue/jaw are high (e.g., in SEEK), and "low" vowels, i.e., for which the tongue/jaw are low (e.g., in SOCK). These novel findings suggest a key role for the LPT and MPT in the fine control of speech production. They imply that speech may impose major synergistic demands on the activities of the MPT and the LPT, and thereby provide insights into the possible interactions between speech activities and orofacial activities (e.g. mastication) and conditions (e.g. Temporomandibular Disorders) that involve the masticatory muscles.

Intermuscular Coherence Of Rotator Cuff And Deltoid Muscles Varies With Force Output

PURPOSE:To identify intermuscular EMG coherence patterns between the rotator cuff and deltoid muscles at different force levels. METHODS:Surface EMG electrodes were used to record activity from the anterior deltoid (AD), middle deltoid (MD), and infraspinatus (IS) muscles of the dominant shoulder in 7 healthy individuals (mean age ± SD = 19 ± 1, 6 females, 1 male). An intramuscular fine-wire EMG electrode was inserted into supraspinatus (SS). Participants performed 30s contractions of isometric shoulder abduction in the scapular plane at 30° at 25% (low-load), 50% (medium-load) and 75% (high-load) of maximum voluntary contraction with visual feedback of the force output. EMG amplitudes and coherence of each muscle pair in the common drive (0-5 Hz), physiological force tremor (5-12 Hz), beta (15-35 Hz), low-gamma (35-60 Hz) and high-gamma (60-100 Hz) bands were compared across the 3 force levels. RESULTS:EMG amplitudes of all muscles increased as force level increased (all p < 0.05). EMG coherence between IS and deltoid muscles increased as force level increased in the low-gamma band (p < 0.05). SS-IS coherence was also the highest during high-load task in the low-gamma band. These data indicate that additional neural drive with higher force levels stemming from subcortical origin likely mediate the increase in coherence between these muscles. However, SS-IS coherence during the medium and high load tasks were lower than that during the low-load task in the common drive band (p < 0.05), indicating that the increase in drive to these muscles for increasing force output is not targeted at common last-order neurons. Similarly, SS-AD coherence during the high-load task was lower than that during the medium-load task in the beta band (p < 0.05) and SS-AD and SS-MD was lower in the tremor band (p < 0.05) at higher force loads. The reduction in coherence between the SS and deltoid muscles and the SS and IS may serve to protect the humeral head from migrating superiorly at higher force loads. CONCLUSIONS:Increasing force output led to decreased coherence within the rotator cuff muscles and between supraspinatus and the deltoid muscles, but increased coherence between infraspinatus and the deltoid muscles. This likely serves as a protective mechanism against superior humeral head migration.

Evaluation of Simple Algorithms for Proportional Control of Prosthetic Hands Using Intramuscular Electromyography.

Although seemingly effortless, the control of the human hand is backed by an elaborate neuro-muscular mechanism. The end result is typically a smooth action with the precise positioning of the joints of the hand and an exerted force that can be modulated to enable precise interaction with the surroundings. Unfortunately, even the most sophisticated technology cannot replace such a comprehensive role but can offer only basic hand functionalities. This issue arises from the drawbacks of the prosthetic hand control strategies that commonly rely on surface EMG signals that contain a high level of noise, thus limiting accurate and robust multi-joint movement estimation. The use of intramuscular EMG results in higher quality signals which, in turn, lead to an improvement in prosthetic control performance. Here, we present the evaluation of fourteen common/well-known algorithms (mean absolute value, variance, slope sign change, zero crossing, Willison amplitude, waveform length, signal envelope, total signal energy, Teager energy in the time domain, Teager energy in the frequency domain, modified Teager energy, mean of signal frequencies, median of signal frequencies, and firing rate) for the direct and proportional control of a prosthetic hand. The method involves the estimation of the forces generated in the hand by using different algorithms applied to iEMG signals from our recently published database, and comparing them to the measured forces (ground truth). The results presented in this paper are intended to be used as a baseline performance metric for more advanced algorithms that will be made and tested using the same database.

Review on electromyography based intention for upper limb control using pattern recognition for human-machine interaction.

Upper limb myoelectric prosthetic control is an essential topic in the field of rehabilitation. The technique controls prostheses using surface electromyogram (sEMG) and intramuscular EMG (iEMG) signals. EMG signals are extensively used in controlling prosthetic upper and lower limbs, virtual reality entertainment, and human-machine interface (HMI). EMG signals are vital parameters for machine learning and deep learning algorithms and help to give an insight into the human brain's function and mechanisms. Pattern recognition techniques pertaining to support vector machine (SVM), k-nearest neighbor (KNN) and Bayesian classifiers have been utilized to classify EMG signals. This paper presents a review on current EMG signal techniques, including electrode array utilization, signal acquisition, signal preprocessing and post-processing, feature selection and extraction, data dimensionality reduction, classification, and ultimate application to the community. The paper also discusses using alternatives to EMG signals, such as force sensors, to measure muscle activity with reliable results. Future implications for EMG classification include employing deep learning techniques such as artificial neural networks (ANN) and recurrent neural networks (RNN) for achieving robust results.

Highly Accurate Real-Time Decomposition of Single Channel Intramuscular EMG.

Real-time intramuscular electromyography (iEMG) decomposition, as an identification procedure of individual motor neuron (MN) discharge timings from a streaming iEMG recording, has the potential to be used in human-machine interfacing. However, for these applications, the decomposition accuracy and speed of current approaches need to be improved. In our previous work, a real-time decomposition algorithm based on a Hidden Markov Model of EMG, using GPU-implemented Bayesian filter to estimate the spike trains of motor units (MU) and their action potentials (MUAPs), was proposed. In this paper, a substantially extended version of this algorithm that boosts the accuracy while maintaining real-time implementation, is introduced. Specifically, multiple heuristics that aim at resolving the problems leading to performance degradation, are applied to the original model. In addition, the recursive maximum likelihood (RML) estimator previously used to estimate the statistical parameters of the spike trains, is replaced by a linear regression (LR) estimator, which is computationally more efficient, in order to ensure real-time decomposition with the new heuristics. The algorithm was validated using twenty-one experimental iEMG signals acquired from the tibialis anterior muscle of five subjects by fine wire electrodes. All signals were decomposed in real time. The decomposition accuracy depended on the level of muscle activation and was when less than 10 MUs were identified, substantially exceeding previous real-time results. Single channel iEMG signals can be very accurately decomposed in real time with the proposed algorithm. The proposed highly accurate algorithm for single-channel iEMG decomposition has the potential of providing neural information on motor tasks for human interfacing.

Intramuscular EMG-Driven Musculoskeletal Modelling: Towards Implanted Muscle Interfacing in Spinal Cord Injury Patients.

Surface EMG-driven modelling has been proposed as a means to control assistive devices by estimating joint torques. Implanted EMG sensors have several advantages over wearable sensors but provide a more localized information on muscle activity, which may impact torque estimates. Here, we tested and compared the use of surface and intramuscular EMG measurements for the estimation of required assistive joint torques using EMG driven modelling. Four healthy subjects and three incomplete spinal cord injury (SCI) patients performed walking trials at varying speeds. Motion capture marker trajectories, surface and intramuscular EMG, and ground reaction forces were measured concurrently. Subject-specific musculoskeletal models were developed for all subjects, and inverse dynamics analysis was performed for all individual trials. EMG-driven modelling based joint torque estimates were obtained from surface and intramuscular EMG. The correlation between the experimental and predicted joint torques was similar when using intramuscular or surface EMG as input to the EMG-driven modelling estimator in both healthy individuals and patients. We have provided the first comparison of non-invasive and implanted EMG sensors as input signals for torque estimates in healthy individuals and SCI patients. Implanted EMG sensors have the potential to be used as a reliable input for assistive exoskeleton joint torque actuation.

End-to-End Estimation of Hand- and Wrist Forces From Raw Intramuscular EMG Signals Using LSTM Networks.

Processing myoelectrical activity in the forearm has for long been considered a promising framework to allow transradial amputees to control motorized prostheses. In spite of expectations, contemporary muscle–computer interfaces built for this purpose typically fail to satisfy one or more important desiderata, such as accuracy, robustness, and/or naturalness of control, in part due to difficulties in acquiring high-quality signals continuously outside laboratory conditions. In light of such problems, surgically implanted electrodes have been made a viable option that allows for long-term acquisition of intramuscular electromyography (iEMG) measurements of spatially precise origin. As it stands, the question of how information embedded in such signals is best extracted and combined across multiple channels remains open. This study presents and evaluates an approach to this end that uses deep neural networks based on the Long Short-Term Memory (LSTMs) architecture to regress forces exerted by multiple degrees of freedom (DoFs) from multichannel iEMG. Three deep learning models, representing three distinct regression strategies, were evaluated: (I) One-to-One, wherein each DoF is separately estimated by an LSTM model processing a single iEMG channel, (II) All-to-One, wherein each DoF is separately estimated by an LSTM model processing all iEMG channels, and (III) All-to-All, wherein a single LSTM model with access to all iEMG channels estimates all DoFs simultaneously. All models operate on raw iEMG, with no preliminary feature extraction required. When evaluated on a dataset comprising six iEMG channels with concurrent force measurements acquired from 14 subjects, all LSTM strategies were found to significantly outperform a baseline feature-based linear control regression method. This finding indicates that recurrent neural networks can learn to transform raw forearm iEMG signals directly into representations that correlate with forces exerted at the level of the hand to a greater degree than simple features do. Furthermore, the All-to-All and All-to-One strategies were found to exhibit better performance than the One-to-One strategy. This finding suggests that, in spite of the spatially local nature of signals, iEMG from muscles not directly actuating the relevant DoF can provide contextual information that aid in decoding motor intent.

Inter-classifier comparison for upper extremity EMG signal at different hand postures and arm positions using pattern recognition.

The utilization of surface EMG and intramuscular EMG signals has been observed to create significant improvement in pattern recognition approaches and myoelectric control. However, there is less data of different arm positions and hand postures available. Hand postures and arm positions tend to affect the combination of surface and intramuscular EMG signal acquisition in terms of classifier accuracy. Hence, this study aimed to find a robust classifier for two scenarios: (1) at fixed arm position (FAP) where classifiers classify different hand postures and (2) at fixed hand posture (FHP) where classifiers classify different arm positions. A total of 20 healthy male participants (30.62 ± 3.87 years old) were recruited for this study. They were asked to perform five motion classes including hand grasp, hand open, rest, hand extension, and hand flexion at four different arm positions at 0°, 45°, 90°, and 135°. SVM, KNN, and LDA classifier were deployed. Statistical analysis in the form of pairwise comparisons was carried out using SPSS. It is concluded that there is no significant difference among the three classifiers. SVM gave highest accuracy of 75.35% and 58.32% at FAP and FHP respectively for each motion classification. KNN yielded the highest accuracies of 69.11% and 79.04% when data was pooled and was classified at different arm positions and at different hand postures respectively. The results exhibited that there is no significant effect of changing arm position and hand posture on the classifier accuracy.