Single-channel EMG Research Articles

A Cooperative game theory-based feature selection for efficient hand grasp classification using minimal number of sEMG signals

Deploying bio-electrical signals and image processing (visual) techniques are the two popular means to provide input to generate grasp control for robotic and prosthetic devices. Visual perception-based techniques rely on computationally expensive image processing algorithms and are affected by lighting conditions. In contrast, grasp control based on bio-electric signals such as surface electromyography (sEMG) is invariant to lighting conditions. It can reflect human intent to hand motion or grasp with lesser computational costs. In this article, we propose an efficient machine-learning pipeline to classify hand grasp using a minimal number of sEMG sensors. A cooperative game theory-based feature selection technique is applied to find the representative feature subset. The feature selection method uses a modified marginal contribution based on the class distribution coefficient to generate feature ranking. This feature ranking is further used to find the most representative feature subset from the extracted feature set. Our proposed pipeline has been evaluated on a benchmark dataset and has achieved a classification accuracy of 98.20%, using single-channel EMG when coupled with the XGBoost classifier. Thorough assessments were conducted to confirm the reliability of the results obtained. Our proposed pipeline holds the potential to facilitate the development of cost-effective sEMG prosthetics.

Signal to noise ratio of masticatory muscle activity of functional and non-functional oral tasks.

Electromyographic activity (EMG) of masticatory muscles during wakefulness is understudied. It is unclear if single channel ambulatory EMG devices are sensitive enough to detect masticatory muscle activity (MMA) during wakefulness. To compare the MMA of various oral tasks recorded with a single channel EMG device ((Grindcare4-datalogger Prototype device) (GC4-β)) and a conventional EMG (cEMG) device. EMG activity of 30 standardised oral tasks was recorded unilaterally from the masseter and anterior temporalis muscle in 24 healthy volunteers using GC4-β and a cEMG device. To compare the EMG data, signal-to-noise ratios (SNR) were calculated as a way to normalise EMG activity across tasks. Analysis of variance was used to compare the SNR between the devices, muscles and oral tasks. SNR measured from GC4-β was overall significantly higher than the cEMG device (p =.001). The SNR for maximum voluntary contraction (MVC) was significantly higher than all other tasks (p <.001). SNR for temporalis with GC4-β was significantly higher for MVC, hard food, soft food, gum chewing (dominant side), rhythmic clenching and upper lip biting compared to the cEMG device (p <.021). The SNR for masseter with GC4-β was significantly higher for hard food and gum chewing (dominant side), rhythmic clenching, rhythmic biting of an object and yawning compared to the cEMG device (p <.022). This study provides novel insight into the EMG patterns of numerous oral tasks enhancing knowledge of physiological differences between the masticatory muscles. Further, single channel EMG devices can effectively measure the EMG activity of various oral tasks during wakefulness.

Whole-body fasciculation detection in amyotrophic lateral sclerosis using motor unit MRI

ObjectiveCompare fasciculation rates between amyotrophic lateral sclerosis (ALS) patients and healthy controls in body regions relevant for diagnosing ALS using motor unit MRI (MUMRI) at baseline and 6 months follow-up, and relate this to single-channel surface EMG (SEMG). MethodsTongue, biceps brachii, paraspinals and lower legs were assessed with MUMRI and biceps brachii and soleus with SEMG in 10 healthy controls and 10 patients (9 typical ALS, 1 primary lateral sclerosis [PLS]). ResultsMUMRI-detected fasciculation rates in typical ALS patients were higher compared to healthy controls for biceps brachii (2.40 ± 1.90 cm-3min−1vs. 0.04 ± 0.10 cm-3min−1, p = 0.004), paraspinals (1.14 ± 1.61 cm-3min−1vs. 0.02 ± 0.02 cm-3min−1, p = 0.016) and lower legs (1.42 ± 1.27 cm-3min−1vs. 0.13 ± 0.10 cm-3min−1, p = 0.004), but not tongue (1.41 ± 1.94 cm-3min−1vs. 0.18 ± 0.18 cm-3min−1, p = 0.556). The PLS patient showed no fasciculation. At baseline, 6/9 ALS patients had increased fasciculation rates compared to healthy controls in at least 2 body regions. At follow-up every patient had increased fasciculation rates in at least 2 body regions. The MUMRI-detected fasciculation rate correlated with SEMG-detected fasciculation rates (τ = 0.475, p = 0.006). ConclusionMUMRI can non-invasively image fasciculation in multiple body regions and appears sensitive to disease progression in individual patients. SignificanceMUMRI has potential as diagnostic tool for ALS.

Detection of active segments of lower limbs EMG signal based on time-domain variance combined with short-term energy

Using EMG signal to realize gesture recognition is a technical difficulty in the application of EMG signal. In order to solve this problem and ensure the accuracy and timeliness of action classification and recognition, it is proposed to use time-domain variance combined with short-term energy to set a double threshold algorithm to detect effective activity segments. Based on the short-term energy and the zero-crossing rate, the minimum energy threshold and the frame window data variance value are designed. Then the original signal is processed by frame length and frameshift, and the complete signal data is divided into several small Windows. Finally, the effective activity segment is intercepted after comparing the upper and lower limits of the time-domain feature extraction variance with the set threshold. The experimental results show that the algorithm is effective in realizing the detection and interception of the start and end points of actions when processing single-channel or multi-channel EMG signals.

Remove Artifacts from a Single-Channel EEG Based on VMD and SOBI.

With the development of portable EEG acquisition systems, the collected EEG has gradually changed from being multi-channel to few-channel or single-channel, thus the removal of single-channel EEG signal artifacts is extremely significant. For the artifact removal of single-channel EEG signals, the current mainstream method is generally a combination of the decomposition method and the blind source separation (BSS) method. Between them, a combination of empirical mode decomposition (EMD) and its derivative methods and ICA has been used in single-channel EEG artifact removal. However, EMD is prone to modal mixing and it has no relevant theoretical basis, thus it is not as good as variational modal decomposition (VMD) in terms of the decomposition effect. In the ICA algorithm, the implementation method based on high-order statistics is widely used, but it is not as effective as the implementation method based on second order statistics in processing EMG artifacts. Therefore, aiming at the main artifacts in single-channel EEG signals, including EOG and EMG artifacts, this paper proposed a method of artifact removal combining variational mode decomposition (VMD) and second order blind identification (SOBI). Semi-simulation experiments show that, compared with the existing EEMD-SOBI method, this method has a better removal effect on EOG and EMG artifacts, and can preserve useful information to the greatest extent.

Does Trans-radial Longitudinal Compression Influence Myoelectric Control?

Existing trans-radial prosthetic socket designs are not optimised to facilitate reliable myoelectric control. Many socket designs pre-date the introduction of myoelectric devices. However, socket designs featuring improved biomechanical stability, notably longitudinal compression sockets, have emerged in more recent years. Neither the subsequent effects, if any, of stabilising the limb on myoelectric control nor in which arrangement to apply the compression have been reported. Twelve able-bodied participants completed two tasks whilst wearing a longitudinal compression socket simulator in three different configurations: 1) compressed, where the compression strut was placed on top of the muscle of interest, 2) relief, where the compression struts were placed either side of the muscle being recorded and 3) uncompressed, with no external compression. The tasks were 1) a single-channel myoelectric target tracking exercise, followed by 2), a high-intensity grasping task. The wearers' accuracy during the tracking task, the pressure at opposing sides of the simulator during contractions and the rate at which the limb fatigued were observed. No significant difference between the tracking-task accuracy scores or rate of fatigue was observed for the different compression configurations. Pressure recordings from the compressed configuration showed that pressure was maintained at opposing sides of the simulator during muscle contractions. Longitudinal compression does not inhibit single-channel EMG control, nor improve fatigue performance. Longitudinal compression sockets have the potential to improve the reliability of multi-channel EMG control due to the maintenance of pressure during muscle contractions.

Single-channel surface electromyography (sEMG) based control of a multi-functional prosthetic hand

Patients suffering from upper limb amputation experience a significant reduction in their ability to perform various tasks. The currently available myoelectric prostheses seek to reinstate the lost abilities of the amputees. However, most users abandon their devices due to high cost, large size, heavy weight, complexity, and limited functional control. This paper presents a multifunctional prosthetic hand that can perform six hand activities deploying a single-channel surface electromyography (sEMG) sensor. EMG signals for fifteen subjects (five amputees and ten intact) were acquired for six contraction levels of forearm muscles using the designed sensor. These levels were further classified to recognize six predefined hand gestures by a fuzzy logic classifier. The proposed system showed an excellent success (> 95%) and other performance parameters above 96%. The intended classification-based control scheme was further realized in real-time to achieve six grip patterns for the developed prosthetic prototype. The hand was tested on five subjects (two amputees and three intact) showed a percentage of success above 91% for accomplishing the dexterous grasping operations. The proposed approach is modest, efficient, and provides a low-cost solution to amputees with multiple degrees of freedom with a single channel EMG system.

Accuracy of clinical diagnostic criteria for sleep bruxism (ICSD3) using a single-channel EMG as a reference standard

Accuracy of clinical diagnostic criteria for sleep bruxism (ICSD3) using a single-channel EMG as a reference standard

Consensus-based clinical guidelines for ambulatory electromyography and contingent electrical stimulation in sleep bruxism.

As yet, there are still no evidence‐based clinical diagnostic and management guidelines for ambulatory single‐channel EMG devices, like the BUTLER® GrindCare® (GrindCare), that are used in patients with sleep bruxism. Therefore, a consensus meeting was organised with GrindCare developers, researchers, and academic and non‐academic clinicians experienced with the use of ambulatory EMG devices. The aim of the meeting was to discuss and develop recommendations for clinical guidelines for GrindCare usage, based on the existing clinical and research experience of the consensus meeting's participants. As an important outcome of the consensus meeting, clinical guidelines were proposed in which an initial 2‐week baseline phase with the device in its inactive (non‐stimulus) mode for habituation and assessment of the number of jaw‐muscle activities is followed by a 4‐week active phase with contingent electrical stimuli suppressing the jaw‐muscle activities. As to avoid the commonly reported reduction in sensitivity to the stimuli, a 2‐week inactive phase is subsequently installed, followed by a repetition of active and inactive phases until a lasting reduction in the number of jaw‐muscle activities and/or associated complaints has been achieved. This proposal has the characteristics of a single‐patient clinical trial. From a research point of view, adoption of this approach by large numbers of GrindCare users creates a great opportunity to recruit relatively large numbers of study participants that follow the same protocol.

Single channel surface EMG control of advanced prosthetic hands: A simple, low cost and efficient approach

Surface EMGs have been the primary sources for control of prosthetic hands due to their comfort and naturalness. The recent advances in the development of the prosthetic hands with many degrees of freedom and many actuators, requires many EMG channels to take the full advantage of the complex prosthetic terminals. Some EMG wearable devices were developed lately, that are able to detect several gestures. However, the main drawbacks of these systems are the cost, the size and the system complexity. In this paper, we suggest a simple, fast and low-cost system which can recognize up to 4 gestures with a single channel surface EMG signal. Gestures include hand closing, hand opening, wrist flexion and double wrist flexion. These gestures can be used to control a prosthetic terminal based on predefined grasp postures. We show that by using a high-dimensional feature space, together with a support vector machine algorithm, it is possible to classify these four gestures. Overall, the system showed satisfactory results in terms of classification accuracy, real time gesture recognition, and tolerance to hand movements through integration of a lock gesture. Calibration took only 30 seconds and session independence was demonstrated by high classification accuracy on different test sessions without repeating the calibration. As a case study we use this system to control a previously developed soft prosthetic hand. This is particularly interesting because we show that a simple hardware that has only a single channel EMG, can afford the control of a multi-DOF prosthetic hands. In addition, such system may be used as a general purpose Human Machine Interface for gaming,for controlling multimedia devices, or to control robots.

Diagnostic validity of the use of a portable single-channel electromyography device for sleep bruxism.

The aim of this study was to determine an appropriate cutoff value and the number of nights of sleep with the portable single-channel EMG device (GrindCare) necessary for a valid sleep bruxism (SB) diagnosis. Twenty consecutive post-graduate students and staff at Bauru School of Dentistry composed the sample. Each participant underwent the GrindCare for five consecutive nights and the polysomnography (PSG). The discrimination between bruxers and non-bruxers was based only on the PSG analysis. Data about electromyography per hour with GrindCare (EMG/h) and PSG (bursts/h) were scored. There were positive correlations between the two devices for EMG/h and bursts/h in three and five consecutive nights. Bland-Altman analysis of the EMG bursts/h showed positive agreement between the methods. The receiver operating characteristic (ROC) analyses also showed that using a minimum of 18 EMG/h for three nights and 19 EMG/h for five nights in GrindCare as cutoffs resulted in a 90% specificity and positive likelihood ratio equal to 5. GrindCare is able to discriminate SB diagnosed by PSG and gold standard criteria, when used for three or five consecutive nights, and it may be a valid choice in clinical practice for SB assessment.

How Close Can Single-Channel EMG Data Come to PSG Scoring of Rhythmic Masticatory Muscle Activity?

How Close Can Single-Channel EMG Data Come to PSG Scoring of Rhythmic Masticatory Muscle Activity?

Design and Optimization of Levenberg-Marquardt based Neural Network Classifier for EMG Signals to Identify Hand Motions

This paper presents an application of artificial neural network for the classification of single channel EMG signal in the context of hand motion detection. Seven statistical input features that are extracted from the preprocessed single channel EMG signals recorded for four predefined hand motions have been used for neural network classifier. Different structures of neural network, based on the number of hidden neurons and two prominent training algorithms, have been considered in the research to find out their applicability for EMG signal classification. The classification performances are analyzed for different architectures of neural network by considering the number of input features, number of hidden neurons, learning algorithms, correlation between network outputs and targets, and mean square error. Between the Levenberg-Marquardt and scaled conjugate gradient learning algorithms, the aforesaid algorithm shows better classification performance. The outcomes of the research show that the optimal design of Levenberg-Marquardt based neural network classifier can perform well with an average classification success rate of 88.4%. A comparison of results has also been presented to validate the effectiveness of the designed neural network classifier to discriminate EMG signals.

“Clustering Index method”: A new technique for differentiation between neurogenic and myopathic changes using surface EMG

Objective To establish a non-invasive and quantitative analysis method using single-channel surface EMG (SEMG) for diagnosing neurogenic and myopathic changes. Methods The subjects consisted of 66 healthy controls, 12 patients with neurogenic diseases, and 18 patients with myopathic diseases. The tibialis anterior muscle was examined using a belly to the adjacent bone lead. From each subject, 20–40 signals of 1 s length were collected of various strengths. A new parameter, the “Clustering Index (CI)”, was developed to quantify the uneven distribution of the SEMG signal, and was plotted against the SEMG area. The results were expressed as the Z-score of each subject calculated using linear regression from the normative data. Results When ±2.5 was used as the cut-off value of the Z-score, the specificity was 95%, whereas the sensitivity was 92% (11/12) and 61% (11/18) for the neurogenic and myopathic patients, respectively. There was no overlap of the Z-score values between the neurogenic and myopathic groups. Conclusions The CI method achieved a reasonably high diagnostic yield in detecting neurogenic or myopathic changes. Significance This is a new simple and quantitative analysis method using SEMG with good reproducibility, and is promising as a non-invasive complement to needle EMG.

Relationship between grasping force and features of single-channel intramuscular EMG signals

The surface electromyographic (sEMG) signal can be used for force prediction and control in prosthetic devices. Because of technological advances on implantable sensors, the use of intramuscular EMG (iEMG) is becoming a potential alternative to sEMG for the control of multiple degrees-of-freedom (DOF). An invasive system is not affected by crosstalk, typical of sEMG, and provides more stable and independent control sites. However, intramuscular recordings provide more local information because of their high selectivity, and may thus be less representative of the global muscle activity with respect to sEMG. This study investigates the capacity of selective single-channel iEMG recordings to represent the grasping force with respect to the use of sEMG with the aim of assessing if iEMG can be an effective method for proportional myoelectric control. sEMG and iEMG were recorded concurrently from 10 subjects who exerted six grasping force profiles from 0 to 25/50N. The linear correlation coefficient between features extracted from iEMG and force was ∼0.9 and was not significantly different from the degree of correlation between sEMG and force. This result indicates that a selective iEMG recording is representative of the applied grasping force and can be used for proportional control.

Electrical stimulation and multichannel EMG recording for identification of functional neural tissue during cauda equina surgery.

Electrical stimulation of structures within the surgical field was used to identify functional neural elements during 25 cauda equina operations. EMG responses from anterior thigh, posterior thigh, and anal sphincter muscles were recorded simultaneously using a multichannel signal averager. During nine operations, stimulation of a presumed filum terminale or other tissue produced clear EMG responses, prompting modification of surgical procedures. In one patient, this resulted in preservation of a flattened spinal cord which resembled a band of scar tissue. Some EMG responses were restricted to a single muscle group; these neural structures would probably not have been identified if only a single-channel EMG recording was used. Visual examination alone was not adequate for identifying functional neural elements, or for determining whether atretic-appearing nerve roots were functional. Electrical stimulation with multichannel EMG recording facilitates the preservation of functional neural elements and the optimization of surgical results in cauda equina surgery.