Comparison of algorithms for estimation of EMG variables during voluntary isometric contractions

Instrumental Evaluation of the Effects of Vertebral Consolidation Surgery on Trunk Muscle Activations and Co-Activations in Patients with Multiple Myeloma: Preliminary Results

Multiple myeloma (MM) patients complain of pain and stiffness limiting motility. To determine if patients can benefit from vertebroplasty, we assessed muscle activation and co-activation before and after surgery. Five patients with MM and five healthy controls performed sitting-to-standing and lifting tasks. Patients performed the task before and one month after surgery. Surface electromyography (sEMG) was recorded bilaterally over the erector spinae longissimus and rectus abdominis superior muscles to evaluate the trunk muscle activation and co-activation and their mean, maximum, and full width at half maximum were evaluated. Statistical analyses were performed to compare MM patients before and after the surgery, MM and healthy controls and to investigate any correlations between the muscle's parameters and the severity of pain in patients. The results reveal increased activations and co-activations after vertebroplasty as well as in comparison with healthy controls suggesting how MM patients try to control the trunk before and after vertebroplasty surgery. The findings confirm the beneficial effects of vertebral consolidation on the pain experienced by the patient, despite an overall increase in trunk muscle activation and co-activation. Therefore, it is important to provide patients with rehabilitation treatment early after surgery to facilitate the CNS to correctly stabilize the spine without overloading it with excessive co-activations.

Myomatrix arrays for high-definition muscle recording

Neurons coordinate their activity to produce an astonishing variety of motor behaviors. Our present understanding of motor control has grown rapidly thanks to new methods for recording and analyzing populations of many individual neurons over time. In contrast, current methods for recording the nervous system's actual motor output - the activation of muscle fibers by motor neurons - typically cannot detect the individual electrical events produced by muscle fibers during natural behaviors and scale poorly across species and muscle groups. Here we present a novel class of electrode devices ('Myomatrix arrays') that record muscle activity at unprecedented resolution across muscles and behaviors. High-density, flexible electrode arrays allow for stable recordings from the muscle fibers activated by a single motor neuron, called a 'motor unit,' during natural behaviors in many species, including mice, rats, primates, songbirds, frogs, and insects. This technology therefore allows the nervous system's motor output to be monitored in unprecedented detail during complex behaviors across species and muscle morphologies. We anticipate that this technology will allow rapid advances in understanding the neural control of behavior and identifying pathologies of the motor system.

Myomatrix arrays for high-definition muscle recording

Neurons coordinate their activity to produce an astonishing variety of motor behaviors. Our present understanding of motor control has grown rapidly thanks to new methods for recording and analyzing populations of many individual neurons over time. In contrast, current methods for recording the nervous system's actual motor output - the activation of muscle fibers by motor neurons - typically cannot detect the individual electrical events produced by muscle fibers during natural behaviors and scale poorly across species and muscle groups. Here we present a novel class of electrode devices ("Myomatrix arrays") that record muscle activity at unprecedented resolution across muscles and behaviors. High-density, flexible electrode arrays allow for stable recordings from the muscle fibers activated by a single motor neuron, called a "motor unit", during natural behaviors in many species, including mice, rats, primates, songbirds, frogs, and insects. This technology therefore allows the nervous system's motor output to be monitored in unprecedented detail during complex behaviors across species and muscle morphologies. We anticipate that this technology will allow rapid advances in understanding the neural control of behavior and in identifying pathologies of the motor system.

Continuous Motion Estimation of Knee Joint Based on a Parameter Self-Updating Mechanism Model

Estimation of continuous motion of human joints using surface electromyography (sEMG) signals has a critical part to play in intelligent rehabilitation. Traditional methods always use sEMG signals as inputs to build regression or biomechanical models to estimate continuous joint motion variables. However, it is challenging to accurately estimate continuous joint motion in new subjects due to the non-stationarity and individual differences in sEMG signals, which greatly limits the generalisability of the method. In this paper, a continuous motion estimation model for the human knee joint with a parameter self-updating mechanism based on the fusion of particle swarm optimization (PSO) and deep belief network (DBN) is proposed. According to the original sEMG signals of different subjects, the method adaptively optimized the parameters of the DBN model and completed the optimal reconstruction of signal feature structure in high-dimensional space to achieve the optimal estimation of continuous joint motion. Extensive experiments were conducted on knee joint motions. The results suggested that the average root mean square errors (RMSEs) of the proposed method were 9.42° and 7.36°, respectively, which was better than the results obtained by common neural networks. This finding lays a foundation for the human-robot interaction (HRI) of the exoskeleton robots based on the sEMG signals.

Compensatory muscle activation and spinal curve changes in response to fatigue among adolescent male athletes

BACKGROUND

The prone plank test has been often used to assess the strength and endurance of trunk muscles. We aimed to develop a new measurement protocol to objectively monitor the changes in spinal curves and muscle activity simultaneously.

METHODS

Eleven adolescent male basketball athletes (13-17 years) performed a one-minute plank test. Spinal curvatures (thoracic kyphosis (TK) and lumbar lordosis (LL)) were determined at each time point by optical tracking of markers placed on the spinous processes of 10 vertebrae. Eleven muscles were measured by surface electromyography to determine muscle fatigue via changes in median frequency.

RESULTS

TK significantly increased (p = 0.003) from the first to the last 10 s of the plank test; changes in LL were mixed within the group. Only the rectus abdominis showed consistent and significant fatigue (p < 0.001). The increased spinal curves significantly correlated with the fatigue of biceps femoris (TK: r = -0.75, p = 0.012; LL: r = -0.71, p = 0.019) indicating a compensatory muscle activation and spinal curve changes in response to fatigue.

CONCLUSION

Our protocol may support future researches that aim to objectively evaluate the prone plank test and which posture-related muscles need strengthening for the individual.

Sensitivity and specificity of the flexion and extension relaxation ratios to identify altered paraspinal muscles' flexion relaxation phenomenon in nonspecific chronic low back pain patients

BACKGROUND

Among the main methods used to identify an altered flexion relaxation phenomenon (FRP) in nonspecific chronic low back pain (NSCLBP), it has been previously demonstrated that flexion relaxation ratio (FRR) and extension relaxation ratio (ERR) are more objective than the visual reference method.

OBJECTIVE

To determine the sensitivity and specificity of the different methods used to calculate the ratios in terms of their ability to identify an altered FRP in NSCLBP.

METHODS

Forty-four NSCLBP patients performed a standing maximal trunk flexion task. Surface electromyography (sEMG) was recorded along the erector spinae longissimus (ESL) and multifidus (MF) muscles. Altered FRP based on sEMG was visually identified by three experts (current standard). Six FRR methods and five ERR methods were used both for the ESL and MF muscles. ROC curves (with areas under the curve (AUC) and sensitivity/specificity) were generated for each ratio.

RESULTS

All methods used to calculate these ratios had an AUC higher than 0.9, excellent sensitivity (>90 %), and good specificity (80-100 %) for both ESL and MF muscles.

CONCLUSION

Both FRP ratios (FRR and ERR) for MF and ESL muscles, appear to be an objective, sensitive and specific method for identifying altered FRP in NSCLBP patients.

On the Genuine Relevance of the Data-Driven Signal Decomposition-Based Multiscale Permutation Entropy

Ordinal pattern-based approaches have great potential to capture intrinsic structures of dynamical systems, and therefore, they continue to be developed in various research fields. Among these, the permutation entropy (PE), defined as the Shannon entropy of ordinal probabilities, is an attractive time series complexity measure. Several multiscale variants (MPE) have been proposed in order to bring out hidden structures at different time scales. Multiscaling is achieved by combining linear or nonlinear preprocessing with PE calculation. However, the impact of such a preprocessing on the PE values is not fully characterized. In a previous study, we have theoretically decoupled the contribution of specific signal models to the PE values from that induced by the inner correlations of linear preprocessing filters. A variety of linear filters such as the autoregressive moving average (ARMA), Butterworth, and Chebyshev were tested. The current work is an extension to nonlinear preprocessing and especially to data-driven signal decomposition-based MPE. The empirical mode decomposition, variational mode decomposition, singular spectrum analysis-based decomposition and empirical wavelet transform are considered. We identify possible pitfalls in the interpretation of PE values induced by these nonlinear preprocessing, and hence, we contribute to improving the PE interpretation. The simulated dataset of representative processes such as white Gaussian noise, fractional Gaussian processes, ARMA models and synthetic sEMG signals as well as real-life sEMG signals are tested.

A Simulation Study to Assess the Factors of Influence on Mean and Median Frequency of sEMG Signals during Muscle Fatigue

Mean and Median frequency are typically used for detecting and monitoring muscle fatigue. These parameters are extracted from power spectral density whose estimate can be obtained by several techniques, each one characterized by advantages and disadvantages. Previous works studied how the implementation settings can influence the performance of these techniques; nevertheless, the estimation results have never been fully evaluated when the power density spectrum is in a low-frequency zone, as happens to the surface electromyography (sEMG) spectrum during muscle fatigue. The latter is therefore the objective of this study that has compared the Welch and the autoregressive parametric approaches on synthetic sEMG signals simulating severe muscle fatigue. Moreover, the sensitivity of both the approaches to the observation duration and to the level of noise has been analyzed. Results showed that the mean frequency greatly depends on the noise level, and that for Signal to Noise Ratio (SNR) less than 10dB the errors make the estimate unacceptable. On the other hand, the error in calculating the median frequency is always in the range 2-10 Hz, so this parameter should be preferred in the tracking of muscle fatigue. Results show that the autoregressive model always outperforms the Welch technique, and that the 3rd order continuously produced accurate and precise estimates; consequently, the latter should be used when analyzing severe fatiguing contraction.

Centre of pressure parameters for the assessment of biomechanical risk in fatiguing frequency-dependent lifting activities

Lifting tasks, among manual material handling activities, are those mainly associated with low back pain. In recent years, several instrumental-based tools were developed to quantitatively assess the biomechanical risk during lifting activities. In this study, parameters related to balance and extracted from the Centre of Pressure (CoP) data series are studied in fatiguing frequency-dependent lifting activities to: i) explore the possibility of classifying people with LBP and asymptomatic people during the execution of task; ii) examine the assessment of the risk levels associated with repetitive lifting activities, iii) enhance current understanding of postural control strategies during lifting tasks. Data were recorded from 14 asymptomatic participants and 7 participants with low back pain. The participants performed lifting tasks in three different lifting conditions (with increasing lifting frequency and risk levels) and kinetic and surface electromyography (sEMG) data were acquired. Kinetic data were used to calculated the CoP and parameters extracted from the latter show a discriminant capacity for the groups and the risk levels. Furthermore, sEMG parameters show a trend compatible with myoelectric manifestations of muscular fatigue. Correlation results between sEMG and CoP velocity parameters revealed a positive correlation between amplitude sEMG parameters and CoP velocity in both groups and a negative correlation between frequency sEMG parameters and CoP velocity. The current findings suggest that it is possible to quantitatively assess the risk level when monitoring fatiguing lifting tasks by using CoP parameters as well as identify different motor strategies between people with and without LBP.

sEMG-based Gesture Recognition using Deep Learning from Noisy Labels

Gesture recognition for myoelectric prosthesis control utilizing sparse multichannel surface Electromyography (sEMG) is a challenging task, and from a Muscle-Computer Interface (MCI) standpoint, the performance is still far from optimal. However, the design of a well-performed sEMG recognition system depends on the flexibility of the input-output function and the dataset's quality. To improve the performance of MCI, we proposed a novel gesture recognition framework that (i) Enrich the spectral information of the sparse sEMG signals by constructing a fused map image (denoted as sEMG-Map) that integrates a multiresolution decomposition (by means of orthogonal wavelets) through the raw signals then rely upon the Convolutional Neural Network (CNN) capacity to exploit the composite hierarchies in the constructed sEMGMap input. (ii) deals with the label noise by proposing a data-centric method (denoted as ALR-CNN) that synchronously refines the falsely labeled samples and optimizes the CNN model based on two basic assumptions. First, the deep model accuracy improves as the training progress. Second, a set of successive learnable max-activated outputs of a well-performed deep model is a reliable estimator for motion detection in the muscle activation pattern. Our proposed framework is evaluated on three large-scale public databases. The average classification accuracy is 95.50%, 95.85%, and 85.58% for NinaPro DB2, NinaPro DB7, and NinaPro DB3, respectively. The experimental results verify the effectuality of the proposed method and show high accuracy.

Muscle activity in explicit and implicit sequence learning: Exploring additional measures of learning and certainty via tensor decomposition

Sequence learning in serial reaction time tasks (SRTTs) is usually inferred through the reaction time measured by a keyboard. However, this chronometric parameter offers no information beyond the time point of the button-press. We therefore examined whether sequence learning can be measured by muscle activations via electromyography (EMG) in a dual-task paradigm. The primary task was a SRTT, in which the stimuli followed a fixed sequence in some blocks, whereas the sequence was random in the control condition. The secondary task stimulus was always random. One group was informed about the fixed sequence, and the other not. We assessed three dependent variables. The chronometric parameter premotor time represents the duration between stimulus onset and the onset of EMG activity, which indicates the start of the response. The other variables describe the response itself considering the EMG activity after response start. The EMG integral was analyzed, and additionally, tensor decomposition was implemented to assess sequence dependent changes in the contribution of the obtained subcomponents. The results show explicit sequence learning in this dual-task setting. Specifically, the informed group show shorter premotor times in fixed than random sequences as well as larger EMG integral and tensor contributions. Further, increased activity seems to represent response certainty, since a decrease is found for both groups in trials following erroneous responses. Interestingly, the sensitivity to sequence and post-error effects varies between the subcomponents. The results indicate that muscle activity can be a useful indicator of response behavior in addition to chronometric parameters.

Distribution of innervation zone and muscle fiber conduction velocity in the biceps brachii muscle

The spatial distributions of muscle innervation zone (IZ) and muscle fiber conduction velocity (CV) were examined in nine healthy young male participants. High-density surface electromyography (EMG) was collected from the biceps brachii muscle when subjects performed isometric elbow flexions at 20% to 80% of the maximal voluntary contraction (MVC). A total of 9498 samples of IZs were identified and CVs were calculated using the Radon transform. The center and width of IZ sample distribution were compared within four different force levels and six medial to lateral electrode column positions using repeated measures ANOVA and multiple comparison tests. Significant shifts of IZ center were observed in the medial columns (Columns 5, 6, and 7) compared with the lateral columns (Columns 3 and 4) (p < 0.05). Similarly, significant differences in the IZ width were found in Column 7 and 8 compared to Column 3 (p < 0.05). In contrast, muscle CV was unaffected by column position. Instead, muscle CV was faster at 40% and 80% MVC compared to 20% MVC (p < 0.05). The findings of this study add further insights into the physiological properties of the biceps brachii muscle.

Influence of electrode configuration on muscle-fiber-conduction-velocity estimation using surface electromyography

OBJECTIVE

Muscle fiber conduction velocity (MFCV) is an important myoelectric parameter and can be estimated by analyzing surface electromyography (EMG). Among many factors, electrode configuration plays a key role on MFCV estimation. Most studies adopt bipolar configuration (BC) for CV estimation. However, a thorough understanding of the underlying mechanism is lacking, confusing the design of the most appropriate EMG measurement setup for CV estimation. The aim of this study is therefore to systematically investigate the influence of electrode configuration on MFCV estimation.

METHODS

Four possible configurations are considered, including BC, monopolar configuration (MC), common average reference (CAR), and a special monopolar configuration (SMC) using a fix channel on the active muscle as reference. For each configuration, mathematic models computing the time delay between adjacent channels are derived and evaluated by dedicated simulation as well as real EMG measurements. MFCV was calculated using the maximum likelihood algorithm with and without channel normalization.

RESULTS

The simulation results are in line with the mathematical models. The CVs estimated from the real EMG with and without normalization are 4.30.7 and 7.23.7 m/s, 5.71.3 and 20.44.7 m/s, 9.03.4 and 20.69.8 m/s, and 5.52.5 and 5.52.4 m/s for BC, MC, SMC, and CAR, respectively.

CONCLUSION

Our results show normalized BC to produce the most accurate CV estimation, in line with the mathematical models and the simulation results.

SIGNIFICANCE

These findings enable a better understanding of the influence of electrode configuration on MFCV estimation, providing useful information for EMG measurement setup design aiming at MFCV studies.

Alterations of tibialis anterior muscle activation pattern in subjects with type 2 diabetes and diabetic peripheral neuropathy

Diabetic peripheral neuropathy (DPN) is associated with loss of motor units (MUs), which can cause changes in the activation pattern of muscle fibres. This study investigated the pattern of muscle activation using high-density surface electromyography (HD-sEMG) signals from subjects with type 2 diabetes mellitus (T2DM) and DPN. Thirty-five adults participated in the study: 12 healthy subjects (HV), 12 patients with T2DM without DPN (No-DPN) and 11 patients with T2DM with DPN (DPN). HD-sEMG signals were recorded in the tibialis anterior muscle during an isometric contraction of ankle dorsiflexion at 50% of the maximum voluntary isometric contraction (MVIC) during 30-s. The calculated HD-sEMG signals parameters were the normalised root mean square (RMS), normalised median frequency (MDF), coefficient of variation (CoV) and modified entropy (ME). The RMS increased significantly (p = 0.001) with time only for the DPN group, while the MDF decreased significantly (p < 0.01) with time for the three groups. Moreover, the ME was significantly lower (p = 0.005), and CoV was significantly higher (p = 0.003) for the DPN group than the HV group. Using HD-sEMG, we have demonstrated a reduction in the number of MU recruited by individuals with DPN. This study provides proof of concept for the clinical utility of this technique for identifying neuromuscular impairment caused by DPN.

Muscle Fatigue Revisited – Insights From Optically Pumped Magnetometers

So far, surface electromyography (sEMG) has been the method of choice to detect and evaluate muscle fatigue. However, recent advancements in non-cryogenic quantum sensors, such as optically pumped magnetometers (OPMs), enable interesting possibilities to flexibly record biomagnetic signals. Yet, a magnetomyographic investigation of muscular fatigue is still missing. Here, we simultaneously used sEMG (4 surface electrode) and OPM-based magnetomyography (OPM-MMG, 4 sensors) to detect muscle fatigue during a 3 × 1-min isometric contractions of the left rectus femoris muscle in 7 healthy participants. Both signals exhibited the characteristic spectral compression distinctive for muscle fatigue. OPM-MMG and sEMG slope values, used to quantify the spectral compression of the signals, were positively correlated, displaying similarity between the techniques. Additionally, the analysis of the different components of the magnetic field vector enabled speculations regarding the propagation of the muscle action potentials (MAPs). Altogether these results show the feasibility of the magnetomyographic approach with OPMs and propose a potential alternative to sEMG for the study of muscle fatigue.

Comparing Machine Learning Methods and Feature Extraction Techniques for the EMG Based Decoding of Human Intention

With an increasing number of robotic and prosthetic devices, there is a need for intuitive Muscle-Machine Interfaces (MuMIs) that allow the user to have an embodied interaction with the devices they are controlling. Such MuMIs can be developed using machine learning based methods that utilize myoelectric activations from the muscles of the user to decode their intention. However, the choice of the learning method is subjective and depends on the features extracted from the raw Electromyography signals as well as on the intended application. In this work, we compare the performance of five machine learning methods and eight time-domain feature extraction techniques in discriminating between different gestures executed by the user of an EMG based MuMI. From the results, it can be seen that the Willison Amplitude performs consistently better for all the machine learning methods compared in this study, while the Zero Crossings achieves the worst results for the Decision Trees and the Random Forests and the Variance offers the worst performance for all the other learning methods. The Random Forests method is shown to achieve the best results in terms of achieved accuracies (has the lowest variance between subjects). In order to experimentally validate the efficiency of the Random Forest classifier and the Willison Amplitude technique, a series of gestures were decoded in a real-time manner from the myoelectric activations of the operator and they were used to control a robot hand.

UStEMG: an Ultrasound Transparent Tattoo-based sEMG System for Unobtrusive Parallel Acquisitions of Muscle Electro-mechanics

Human machine interfaces follow machine learning approaches to interpret muscles states, mainly from electrical signals. These signals are easy to collect with tiny devices, on tight power budgets, interfaced closely to the human skin. However, natural movement behavior is not only determined by muscle activation, but it depends on an orchestration of several subsystems, including the instantaneous length of muscle fibers, typically inspected by means of ultrasound (US) imaging systems. This work shows for the first time an ultra-lightweight (7 g) electromyography (sEMG) system transparent to ultrasound, which enables the simultaneous acquisition of sEMG and US signals from the same location. The system is based on ultrathin and skin-conformable temporary tattoo electrodes (TTE) made of printed conducting polymer, connected to a tiny, parallel-ultra-low power acquisition platform (BioWolf). US phantom images recorded with the TTE had mean axial and lateral resolutions of 0.90±0.02 mm and 1.058±0.005 mm, respectively. The root mean squares for sEMG signals recorded with the US during biceps contractions were at 57±10 µV and mean frequencies were at 92±1 Hz. We show that neither ultrasound images nor electromyographic signals are significantly altered during parallel and synchronized operation.Clinical relevance- Modern prosthetic engineering concepts use interfaces connected to muscles or nerves and employ machine learning models to infer on natural movement behavior of amputated limbs. However, relying only on a single data source (e.g., electromyography) reduces the quality of a fine-grained motor control. To address this limitation, we propose a new and unobtrusive device capable of capturing the electrical and mechanical behavior of muscles in a parallel and synchronized fashion. This device can support the development of new prosthetic control and design concepts, further supporting clinical movement science in the configuration of better simulation models.

A Hierarchical View Pooling Network for Multichannel Surface Electromyography-Based Gesture Recognition

Hand gesture recognition based on surface electromyography (sEMG) plays an important role in the field of biomedical and rehabilitation engineering. Recently, there is a remarkable progress in gesture recognition using high-density surface electromyography (HD-sEMG) recorded by sensor arrays. On the other hand, robust gesture recognition using multichannel sEMG recorded by sparsely placed sensors remains a major challenge. In the context of multiview deep learning, this paper presents a hierarchical view pooling network (HVPN) framework, which improves multichannel sEMG-based gesture recognition by learning not only view-specific deep features but also view-shared deep features from hierarchically pooled multiview feature spaces. Extensive intrasubject and intersubject evaluations were conducted on the large-scale noninvasive adaptive prosthetics (NinaPro) database to comprehensively evaluate our proposed HVPN framework. Results showed that when using 200 ms sliding windows to segment data, the proposed HVPN framework could achieve the intrasubject gesture recognition accuracy of 88.4%, 85.8%, 68.2%, 72.9%, and 90.3% and the intersubject gesture recognition accuracy of 84.9%, 82.0%, 65.6%, 70.2%, and 88.9% on the first five subdatabases of NinaPro, respectively, which outperformed the state-of-the-art methods.

The Impact of Linear Filter Preprocessing in the Interpretation of Permutation Entropy

Permutation Entropy (PE) is a powerful tool for measuring the amount of information contained within a time series. However, this technique is rarely applied directly on raw signals. Instead, a preprocessing step, such as linear filtering, is applied in order to remove noise or to isolate specific frequency bands. In the current work, we aimed at outlining the effect of linear filter preprocessing in the final PE values. By means of the Wiener-Khinchin theorem, we theoretically characterize the linear filter's intrinsic PE and separated its contribution from the signal's ordinal information. We tested these results by means of simulated signals, subject to a variety of linear filters such as the moving average, Butterworth, and Chebyshev type I. The PE results from simulations closely resembled our predicted results for all tested filters, which validated our theoretical propositions. More importantly, when we applied linear filters to signals with inner correlations, we were able to theoretically decouple the signal-specific contribution from that induced by the linear filter. Therefore, by providing a proper framework of PE linear filter characterization, we improved the PE interpretation by identifying possible artifact information introduced by the preprocessing steps.

Online Adaptive Prediction of Human Motion Intention Based on sEMG

Accurate and reliable motion intention perception and prediction are keys to the exoskeleton control system. In this paper, a motion intention prediction algorithm based on sEMG signal is proposed to predict joint angle and heel strike time in advance. To ensure the accuracy and reliability of the prediction algorithm, the proposed method designs the sEMG feature extraction network and the online adaptation network. The feature extraction utilizes the convolution autoencoder network combined with muscle synergy characteristics to get the high-compression sEMG feature to aid motion prediction. The adaptation network ensures the proposed prediction method can still maintain a certain prediction accuracy even the sEMG signals distribution changes by adjusting some parameters of the feature extraction network and the prediction network online. Ten subjects were recruited to collect surface EMG data from nine muscles on the treadmill. The proposed prediction algorithm can predict the knee angle 101.25 ms in advance with 2.36 degrees accuracy. The proposed prediction algorithm also can predict the occurrence time of initial contact 236±9 ms in advance. Meanwhile, the proposed feature extraction method can achieve 90.71±3.42% accuracy of sEMG reconstruction and can guarantee 73.70±5.01% accuracy even when the distribution of sEMG is changed without any adjustment. The online adaptation network enhances the accuracy of sEMG reconstruction of CAE to 87.65±3.83% and decreases the angle prediction error from 4.03∘ to 2.36∘. The proposed method achieves effective motion prediction in advance and alleviates the influence caused by the non-stationary of sEMG.

A database of high-density surface electromyogram signals comprising 65 isometric hand gestures

Control of contemporary, multi-joint prosthetic hands is commonly realized by using electromyographic signals from the muscles remaining after amputation at the forearm level. Although this principle is trying to imitate the natural control structure where muscles control the joints of the hand, in practice, myoelectric control provides only basic hand functions to an amputee using a dexterous prosthesis. This study aims to provide an annotated database of high-density surface electromyographic signals to aid the efforts of designing robust and versatile electromyographic control interfaces for prosthetic hands. The electromyographic signals were recorded using 128 channels within two electrode grids positioned on the forearms of 20 able-bodied volunteers. The participants performed 65 different hand gestures in an isometric manner. The hand movements were strictly timed using an automated recording protocol which also synchronously recorded the electromyographic signals and hand joint forces. To assess the quality of the recorded signals several quantitative assessments were performed, such as frequency content analysis, channel crosstalk, and the detection of poor skin-electrode contacts.

Evaluation of the effect of a newly developed steering unit with enhanced self-alignment and deadband on mental workload during driving of agricultural tractors

The aim of present study was to investigate the effect of a newly developed steering unit with enhanced self-alignment and deadband on mental workload (MW) during heavy vehicle operation. Fourteen participants performed two tasks consisting of a lane keeping and a double lane shift with two tractors equipped with 1) a conventional and 2) an enhanced steering system. Physiological measurements, i.e., electromyography, electrodermal activity and heart rate were recorded during the tasks. Furthermore, performance measurements and subjective perception of MW were collected. Present study demonstrated that participants perceived the enhanced steering system requiring less mental demands to operate. Participants improved their performance during the lane keeping task and tended to improve in the double lane shift task with the enhanced system. Physiological measurements did not reveal differences between the steering systems. This study highlighted the dissociation of subjective indices of mental workload from physiological indices in driving of heavy vehicles.

Self-Regulated Force and Neuromuscular Responses During Fatiguing Isometric Leg Extensions Anchored to a Rating of Perceived Exertion

The purpose of the study was to examine the fatigue-related patterns of responses for electromyography (EMG), mechanomyography (MMG), and force during a sustained isometric muscle action anchored to RPE = 5. Ten men (22.9 ± 2.0 year) performed maximal voluntary isometric contractions (MVIC) prior to and following an isometric leg extension muscle action, which was sustained for a maximal time-limit of 5 min or until it could not be maintained at RPE = 5 (actual time-limit). EMG amplitude (AMP), EMG mean power-frequency (MPF), MMG AMP, MMG MPF, and force values were determined every 5% of the actual time-limit. Regression analyses were used to examine the neuromuscular parameters and force responses, and a t test was used to examine MVIC. The pretest MVIC (62.4 ± 14.3 kg) was significantly (p < 0.001; d = 1.07) greater than posttest (47.9 ± 12.8 kg). The percent decline in force during the sustained isometric muscle action was 47.5 ± 19.6%, and there was a significant, negative force versus time relationship (p < 0.001; R = - 0.980). There was a significant, negative EMG AMP versus time relationship (p < 0.001; R = -0.789), but no significant (p > 0.05) relationships for EMG MPF, MMG AMP, or MMG MPF versus time. The findings indicated that it was necessary to reduce force and EMG AMP to maintain RPE = 5. We hypothesize that the maintenance of RPE = 5 was initially accomplished by an anticipatory feedforward mechanism and then continuous integrations of afferent feedback, which resulted in reductions of EMG AMP and force, due to reductions in neural drive, to attenuate the impact of metabolic byproducts.

Reliable measurement of incisal bite force for understanding the control of masticatory muscles

OBJECTIVE

In the present study, we aimed at evaluating the steadiness of incisal bite force during isometric contractions of masticatory muscles.

DESIGN

Two separate experiments were carried out in 11 healthy young women. A first experiment was performed to test the reliability of our protocol for measurement of incisal bite force steadiness. The second experiment aimed to evaluate the steadiness of incisal bite force at four submaximal (i.e., percentage of maximum voluntary contraction, MVC) levels (5 %MVC, 10 %MVC, 15 %MVC, and 20 %MVC), along with the bilateral myoelectric activity of two masticatory muscles (temporalis and masseter).

RESULTS

The results from the first experiment showed that our protocol is substantially reliable (intraclass correlation coefficient, ICC > 0.80) for estimating force variability and moderate reliable (0.60 < ICC < 0.80) for estimating spectral properties of force signals. In the second experiment, we found that force standard deviation (SD) increased proportionally to the power of mean force, and coefficient of variation (CoV) was higher at low-intensity contractions and maintained at an approximately constant level for high-intensity contractions. The force-EMG relationships were linear for both muscles at the contraction intensities evaluated in the study (5 %MVC to 20 %MVC), and the median frequency did not change with contraction intensity.

CONCLUSION

Therefore, we presented a reliable method to estimate the incisal bite force, along with additional data on force control and myoelectric activity of jaw elevator muscles during isometric steady contractions.

Advanced Hand Gesture Prediction Robust to Electrode Shift with an Arbitrary Angle

Recent advances in myoelectric controlled techniques have made the surface electromyogram (sEMG)-based sensing armband a promising candidate for acquiring bioelectric signals in a simple and convenient way. However, inevitable electrode shift as a non-negligible defect commonly causes a trained classifier requiring continuous recalibrations. In this study, a novel hand gesture prediction is firstly proposed; it is robust to electrode shift with arbitrary angle. Unlike real-time recognition which outputs target gestures only after the termination of hand motions, our proposed advanced prediction can provide the same results, even before the completion of signal collection. Moreover, by combining interpolated peak location and preset synchronous gesture, the developed simplified rapid electrode shift detection and correction at random rather than previous fixed angles are realized. Experimental results demonstrate that it is possible to achieve both electrode shift detection with high precision and gesture prediction with high accuracy. This study provides a new insight into electrode shift robustness which brings gesture prediction a step closer to practical applications.

Real-Time Quality Assessment of Long-Term ECG Signals Recorded by Wearables in Free-Living Conditions

OBJECTIVE

Nowadays, methods for ECG quality assessment are mostly designed to binary distinguish between good/bad quality of the whole signal. Such classification is not suitable to long-term data collected by wearable devices. In this paper, a novel approach to estimate long-term ECG signal quality is proposed.

METHODS

The real-time quality estimation is performed in a local time window by calculation of continuous signal-to-noise ratio (SNR) curve. The layout of the data quality segments is determined by analysis of SNR waveform. It is distinguished between three levels of ECG signal quality: signal suitable for full wave ECG analysis, signal suitable only for QRS detection, and signal unsuitable for further processing.

RESULTS

The SNR limits for reliable QRS detection and full ECG waveform analysis are 5 and 18 dB respectively. The method was developed and tested using synthetic data and validated on real data from wearable device.

CONCLUSION

The proposed solution is a robust, accurate and computationally efficient algorithm for annotation of ECG signal quality that will facilitate the subsequent tailored analysis of ECG signals recorded in free-living conditions.

SIGNIFICANCE

The field of long-term ECG signals self-monitoring by wearable devices is swiftly developing. The analysis of massive amount of collected data is time consuming. It is advantageous to characterize data quality in advance and thereby limit consequent analysis to useable signals.

Adaptive Calibration of Electrode Array Shifts Enables Robust Myoelectric Control

OBJECTIVE

The objective of this work is to develop a novel method for adaptive calibration of the electrode array shifts toward achieving robust myoelectric pattern-recognition control.

METHODS

This work is inspired by the idea of image object detection when high-density surface electromyogram signals recorded from a two-dimensional electrode array carry rich spatial information and can serve as a muscular activation image. A convolutional neural network involving transfer learning (from a network for image recognition) is used to learn muscular activity patterns at an original/baseline position of an electrode array. The shift of an electrode array can be estimated by identifying and matching partially overlapped regions between the training images of muscular activation and the testing images at any other position, in an unsupervised manner. Given the calibration of an electrode array shift, the identification of muscular activity patterns is implemented accordingly. The performance of the proposed method was evaluated with data recorded by a 10 × 10 electrode array placed over the forearm extensors of 10 subjects performing 6 wrist and finger extension tasks.

RESULTS

The proposed method achieved high task classification accuracies around 95% and outperformed five traditional methods under conditions with multiple designated shifts in offline experiments and a random shift in online testing.

CONCLUSION

The proposed method is demonstrated to be a promising solution for the automatic and adaptive calibration of electrode array shifts.

SIGNIFICANCE

This work will enhance the robustness of myoelectric control systems.

Support Vector Machine-Based EMG Signal Classification Techniques: A Review

This paper gives an overview of the different research works related to electromyographic signals (EMG) classification based on Support Vector Machines (SVM). The article summarizes the techniques used to make the classification in each reference. Furthermore, it includes the obtained accuracy, the number of signals or channels used, the way the authors made the feature vector, and the type of kernels used. Hence, this article also includes a compilation about the bands used to filter signals, the number of signals recommended, the most commonly used sampling frequencies, and certain features that can create the characteristics of the vector. This research gathers articles related to different kinds of SVM-based classification and other tools for signal processing in the field.

Fatiguing effects of indirect vibration stimulation in upper limb muscles: pre, post and during isometric contractions superimposed on upper limb vibration

Whole-body vibration and upper limb vibration (ULV) continue to gain popularity as exercise intervention for rehabilitation and sports applications. However, the fatiguing effects of indirect vibration stimulation are not yet fully understood. We investigated the effects of ULV stimulation superimposed on fatiguing isometric contractions using a purpose developed upper limb stimulation device. Thirteen healthy volunteers were exposed to both ULV superimposed to fatiguing isometric contractions (V) and isometric contractions alone Control (C). Both Vibration (V) and Control (C) exercises were performed at 80% of the maximum voluntary contractions. The stimulation used was 30 Hz frequency of 0.4 mm amplitude. Surface-electromyographic (EMG) activity of the Biceps Brachii, Triceps Brachii and Flexor Carpi Radialis were measured. EMG amplitude (EMGrms) and mean frequency (MEF) were computed to quantify muscle activity and fatigue levels. All muscles displayed significantly higher reduction in MEFs and a corresponding significant increase in EMGrms with the V than the Control, during fatiguing contractions (p < 0.05). Post vibration, all muscles showed higher levels of MEFs after recovery compared to the control. Our results show that near-maximal isometric fatiguing contractions superimposed on vibration stimulation lead to a higher rate of fatigue development compared to the isometric contraction alone in the upper limb muscles. Results also show higher manifestation of mechanical fatigue post treatment with vibration compared to the control. Vibration superimposed on isometric contraction not only seems to alter the neuromuscular function during fatiguing efforts by inducing higher neuromuscular load but also post vibration treatment.

A Learning Scheme for EMG Based Decoding of Dexterous, In-Hand Manipulation Motions

Electromyography (EMG) based interfaces are the most common solutions for the control of robotic, orthotic, prosthetic, assistive, and rehabilitation devices, translating myoelectric activations into meaningful actions. Over the last years, a lot of emphasis has been put into the EMG based decoding of human intention, but very few studies have been carried out focusing on the continuous decoding of human motion. In this work, we present a learning scheme for the EMG based decoding of object motions in dexterous, in-hand manipulation tasks. We also study the contribution of different muscles while performing these tasks and the effect of the gender and hand size in the overall decoding accuracy. To do that, we use EMG signals derived from 16 muscle sites (8 on the hand and 8 on the forearm) from 11 different subjects and an optical motion capture system that records the object motion. The object motion decoding is formulated as a regression problem using the Random Forests methodology. Regarding feature selection, we use the following time-domain features: root mean square, waveform length and zero crossings. A 10-fold cross validation procedure is used for model assessment purposes and the feature variable importance values are calculated for each feature. This study shows that subject specific, hand specific, and object specific decoding models offer better decoding accuracy that the generic models.

EMG-Based Real-Time Linear-Nonlinear Cascade Regression Decoding of Shoulder, Elbow, and Wrist Movements in Able-Bodied Persons and Stroke Survivors

OBJECTIVE

This study aimed to decode shoulder, elbow and wrist dynamic movements continuously and simultaneously based on multi-channel surface electromyography signals, useful for electromyography controlled exoskeleton robots for upper-limb rehabilitation.

METHODS

Ten able-bodied subjects and ten stroke subjects were instructed to voluntarily move the shoulder, elbow and wrist joints back and forth in a horizontal plane with an exoskeleton robot. The shoulder, elbow and wrist movements and surface electromyography signals from six muscles crossing the joints were recorded. A set of three parallel linear-nonlinear cascade decoders was developed to continuously estimate the selected shoulder, elbow and wrist movements based on a generalized linear model using the anterior deltoid, posterior deltoid, biceps brachii, long head triceps brachii, flexor carpi radialis, and extensor carpi radialis muscle electromyography signals as the model inputs.

RESULTS

The decoder performed well for both healthy and stroke populations. As movement smoothness decreased, decoding performance decreased for the stroke population.

CONCLUSION

The proposed method is capable of simultaneously and continuously estimating multi-joint movements of the human arm in real-time by characterizing the nonlinear mappings between muscle activity and kinematic signals based on linear regression.

SIGNIFICANCE

This may prove useful in developing myoelectric controlled exoskeletons for motor rehabilitation of neurological disorders.

Extraction of Multi-Labelled Movement Information from the Raw HD-sEMG Image with Time-Domain Depth

In contemporary muscle-computer interfaces for upper limb prosthetics there is often a trade-off between control robustness and range of executable movements. As a very low movement error rate is necessary in practical applications, this often results in a quite severe limitation of controllability; a problem growing ever more salient as the mechanical sophistication of multifunctional myoelectric prostheses continues to improve. A possible remedy for this could come from the use of multi-label machine learning methods, where complex movements can be expressed as the superposition of several simpler movements. Here, we investigate this claim by applying a multi-labeled classification scheme in the form of a deep convolutional neural network (CNN) to high density surface electromyography (HD-sEMG) recordings. We use 16 independent labels to model the movements of the hand and forearm state, representing its major degrees of freedom. By training the neural network on 16 × 8 sEMG image sequences 24 samples long with a sampling rate of 2048 Hz to detect these labels, we achieved a mean exact match rate of 78.7% and a mean Hamming loss of 2.9% across 14 healthy test subjects. With this, we demonstrate the feasibility of highly versatile and responsive sEMG control interfaces without loss of accuracy.

Surface-Electromyography-Based Gesture Recognition by Multi-View Deep Learning

Gesture recognition using sparse multichannel surface electromyography (sEMG) is a challenging problem, and the solutions are far from optimal from the point of view of muscle-computer interface. In this paper, we address this problem from the context of multi-view deep learning. A novel multi-view convolutional neural network (CNN) framework is proposed by combining classical sEMG feature sets with a CNN-based deep learning model. The framework consists of two parts. In the first part, multi-view representations of sEMG are modeled in parallel by a multistream CNN, and a performance-based view construction strategy is proposed to choose the most discriminative views from classical feature sets for sEMG-based gesture recognition. In the second part, the learned multi-view deep features are fused through a view aggregation network composed of early and late fusion subnetworks, taking advantage of both early and late fusion of learned multi-view deep features. Evaluations on 11 sparse multichannel sEMG databases as well as five databases with both sEMG and inertial measurement unit data demonstrate that our multi-view framework outperforms single-view methods on both unimodal and multimodal sEMG data streams.

Effects of different vibration frequencies, amplitudes and contraction levels on lower limb muscles during graded isometric contractions superimposed on whole body vibration stimulation

BACKGROUND

Indirect vibration stimulation, i.e., whole body vibration or upper limb vibration, has been investigated increasingly as an exercise intervention for rehabilitation applications. However, there is a lack of evidence regarding the effects of graded isometric contractions superimposed on whole body vibration stimulation. Hence, the objective of this study was to quantify and analyse the effects of variations in the vibration parameters and contraction levels on the neuromuscular responses to isometric exercise superimposed on whole body vibration stimulation.

METHODS

In this study, we assessed the 'neuromuscular effects' of graded isometric contractions, of 20%, 40%, 60%, 80% and 100% of maximum voluntary contraction, superimposed on whole body vibration stimulation (V) and control (C), i.e., no-vibration in 12 healthy volunteers. Vibration stimuli tested were 30 Hz and 50 Hz frequencies and 0.5 mm and 1.5 mm amplitude. Surface electromyographic activity of the vastus lateralis, vastus medialis and biceps femoris were measured during V and C conditions with electromyographic root mean square and electromyographic mean frequency values used to quantify muscle activity and their fatigue levels, respectively.

RESULTS

Both the prime mover (vastus lateralis) and the antagonist (biceps femoris) displayed significantly higher (P < 0.05) electromyographic activity with the V than the C condition with varying percentage increases in EMG root-mean-square (EMGrms) values ranging from 20% to 200%. For both the vastus lateralis and biceps femoris, the increase in mean EMGrms values depended on the frequency, amplitude and muscle contraction level with 50 Hz-0.5 mm stimulation inducing the largest neuromuscular activity.

CONCLUSIONS

These results show that the isometric contraction superimposed on vibration stimulation leads to higher neuromuscular activity compared to isometric contraction alone in the lower limbs. The combination of the vibration frequency with the amplitude and the muscle tension together grades the final neuromuscular output.

A Novel Interpretation of Sample Entropy in Surface Electromyographic Examination of Complex Neuromuscular Alternations in Subacute and Chronic Stroke

The objective of this paper was to develop sample entropy (SampEn) as a novel surface electromyogram (EMG) biomarker to quantitatively examine post-stroke neuromuscular alternations. The SampEn method was performed on surface EMG interference patterns recorded from biceps brachii muscles of nine healthy control subjects, fourteen subjects with subacute stroke, and eleven subjects with chronic stroke, respectively. Measurements were collected during isometric contractions of elbow flexion at different constant force levels. By producing diagnostic decisions for individual muscles, two categories of abnormalities in some paretic muscles were discriminated in terms of abnormally increased and decreased SampEn. The efficiency of the SampEn was demonstrated by its comparable performance with a previously reported clustering index (CI) method. Mixed SampEn (or CI) patterns were observed in paretic muscles of subjects with stroke indicating complex neuromuscular changes at work as a result of a hemispheric brain lesion. Although both categories of SampEn (or CI) abnormalities were observed in both subacute and chronic stages of stroke, the underlying processes contributing to the SampEn abnormalities might vary a lot in stroke stage. The SampEn abnormalities were also found in contralateral muscles of subjects with chronic stroke indicating the necessity of applying interventions to contralateral muscles during stroke rehabilitation. Our work not only presents a novel method for quantitative examination of neuromuscular changes, but also explains the neuropathological mechanisms of motor impairments and offers guidelines for a better design of effective rehabilitation protocols toward improved motor recovery.

Muscle fatigue assessment through electrodermal activity analysis during isometric contraction

We studied the effects of muscle fatigue on the Autonomic Nervous System (ANS) dynamics. Specifically, we monitored the electrodermal activity (EDA) on 32 healthy subjects performing isometric biceps contraction. As assessed by means of an electromyography (EMG) analysis, 15 subjects showed muscle fatigue and 17 did not. EDA signals were analyzed using the recently proposed cvxEDA model in order to decompose them into their phasic and tonic components and extract effective features to study ANS dynamics. A statistical comparison between the two groups of subjects was performed. Results revealed that relevant phasic EDA features significantly increased in the fatigued group. Moreover, a pattern recognition system was applied to the EDA dataset in order to automatically discriminate between fatigued and non-fatigued subjects. The proposed leave-one-subject-out KNN classifier showed an accuracy of 75.69%. These results suggest the use of EDA as correlate of muscle fatigue, providing integrative information to the standard indices extracted from the EMG signals.