Identification of isometric contractions based on High Density EMG maps

Identification of motion intention and muscle activation strategy is necessary to control human–machine interfaces like prostheses or orthoses, as well as other rehabilitation devices, games and computer-based training programs. Pattern recognition from sEMG signals has been extensively investigated in the last decades, however, most of the studies did not take into account different strengths and EMG distributions associated to the intended task. The identification of such quantities could be beneficial for the training of the subject or the control of assistive devices. Recent studies have shown the need to improve pattern-recognition classification by reducing sensitivity to changes in the exerted strength, muscle-electrode shifts and bad contacts. Surface High Density EMG (HD-EMG) obtained from 2-dimensional arrays can provide much more information than electrode pairs for inferring not only motion intention but also the strategy adopted to distribute the load between muscles as well as changes in the spatial distribution of motor unit action potentials within a single muscle because of it.The objectives of this study were: (a) the automatic identification of four isometric motor tasks associated with the degrees of freedom of the forearm: flexion–extension and supination–pronation and (b) the differentiation among levels of voluntary contraction at low-medium efforts. For this purpose, monopolar HD-EMG maps were obtained from five muscles of the upper-limb in healthy subjects. An original classifier is proposed, based on: (1) Two steps linear discriminant analysis of the EMG information for each type of contraction, and (2) features extracted from HD-EMG maps and related to its intensity and distribution in the 2D space. The classifier was trained and tested with different effort levels. Spatial distribution-based features by themselves are not sufficient to classify the type of task or the effort level with an acceptable accuracy; however, when calculated with the “isolated masses” method proposed in this study and combined with intensity-base features, the performance of the classifier is improved. The classifier is capable of identifying the tasks even at 10% of Maximum Voluntary Contraction, in the range of effort level developed by patients with neuromuscular disorders, showing that intention end effort of motion can be estimated from HD-EMG maps and applied in rehabilitation.     

High density electromyography data of normally limbed and transradial amputee subjects for multifunction prosthetic control

Pattern recognition based control of powered upper limb myoelectric prostheses offers a means of extracting more information from the available muscles than conventional methods. By identifying repeatable patterns of muscle activity across multiple muscle sites rather than relying on independent EMG signals it is possible to provide more natural, reliable control of myoelectric prostheses. The purposes of this study were to (1) determine if participants can perform distinctive muscle activation patterns associated with multiple wrist and hand movements reliably and (2) to show that high density EMG can be applied individually to determine the electrode location of a clinically acceptable number of electrodes (maximally eight) to classify multiple wrist and hand movements reliably in transradial amputees. Eight normally limbed subjects (five female, three male) and four transradial amputee subjects (two traumatic and congenital) subjects participated in this study, which examined the classification accuracies of a pattern recognition control system. It was found that tasks could be classified with high accuracy (85-98%) with normally limbed subjects (10-13 tasks) and with amputees (4-6) tasks. In healthy subjects, reducing the number of electrodes to eight did not affect accuracy significantly when those electrodes were optimally placed, but did reduce accuracy significantly when those electrodes were distributed evenly. In the amputee subjects, reducing the number of electrodes up to 4 did not affect classification accuracy or the number of tasks with high accuracy, independent of whether those remaining electrodes were evenly distributed or optimally placed. The findings in healthy subjects suggest that high density EMG testing is a useful tool to identify optimal electrode sites for pattern recognition control, but its use in amputees still has to be proven. Instead of just identifying the electrode sites where EMG activity is strong, clinicians will be able to choose the electrode sites that provide the most important information for classification.     

Three-Way Analysis of Spectrospatial Electromyography Data: Classification and Interpretation

Classifying multivariate electromyography (EMG) data is an important problem in prosthesis control as well as in neurophysiological studies and diagnosis. With modern high-density EMG sensor technology, it is possible to capture the rich spectrospatial structure of the myoelectric activity. We hypothesize that multi-way machine learning methods can efficiently utilize this structure in classification as well as reveal interesting patterns in it. To this end, we investigate the suitability of existing three-way classification methods to EMG-based hand movement classification in spectrospatial domain, as well as extend these methods by sparsification and regularization. We propose to use Fourier-domain independent component analysis as preprocessing to improve classification and interpretability of the results. In high-density EMG experiments on hand movements across 10 subjects, three-way classification yielded higher average performance compared with state-of-the art classification based on temporal features, suggesting that the three-way analysis approach can efficiently utilize detailed spectrospatial information of high-density EMG. Phase and amplitude patterns of features selected by the classifier in finger-movement data were found to be consistent with known physiology. Thus, our approach can accurately resolve hand and finger movements on the basis of detailed spectrospatial information, and at the same time allows for physiological interpretation of the results.     

Further evaluation of an EMG technique for assessment of the deep cervical flexor muscles

A novel surface electromyographic (EMG) technique was recently described for the detection of deep cervical flexor muscle activity. Further investigation of this technique is warranted to ensure EMG activity from neighbouring muscles is not markedly influencing the signals recorded. This study compared deep cervical flexor (DCF) muscle activity with the activity of surrounding neck and jaw muscles during various anatomical movements of the neck and jaw in 10 volunteer subjects. DCF EMG activity was recorded with custom electrodes inserted via the nose and fixed by suction to the posterior mucosa of the oropharynx. Surface electrodes were placed over the sternocleidomastoid, anterior scalene, masseter and suprahyoid muscles. Positioned in supine, subjects performed isometric cranio-cervical flexion, cervical flexion, right and left cervical rotation, jaw clench and resisted jaw opening. Across all movements examined, EMG amplitude of the DCF muscles was greatest during neck movements that would require activity of the DCF muscles, particularly during cranio-cervical flexion, their primary anatomical action. The actions of jaw clench and resisted jaw opening demonstrated significantly less DCF EMG activity than the cranio-cervical flexion action (p < 0.05). Across all other movements, the neighbouring neck and jaw muscles demonstrated greatest EMG amplitude during their respective primary anatomical actions, which occurred in the absence of increased EMG amplitude recorded from the DCF muscles. The finding of substantial EMG activity of the DCF muscles only during neck actions that would require their activity, particularly cranio-cervical flexion, and not during actions involving the jaw, provide further assurance that the majority of myoelectric signals detected from the nasopharyngeal electrode are from the DCF muscles.     

Evaluation of training effectiveness for improving maximal voluntary contraction without noticeable hypertrophy of muscles

The goal of this study was to approbate a strength training protocol designed to improve motor skills at the maximum voluntary contraction (MVC) without hypertrophy of muscles. The main difference between this protocol and classical strength training was that the number of movements during a training session was increased to improve the motor skill, and the rest periods between the training movements were increased in order to minimize the damage of muscle fibers, which is one of the factors inducing muscle hypertrophy. Eleven subjects trained knee extensors of the right leg four times a week during four weeks. The evaluation of strength and speed characteristics with simultaneous recording the EMG activity was performed in both trained and untrained legs immediately before, during, and several times after the whole training period. Before and after the four-week training period, the size and contractile properties of the trained and contralateral knee extensors were evaluated by MRI and twitch interpolation technique. The maximal strength gains were about 17% in both trained and untrained legs; they did not differ significantly from each other. Noticeable increases in the EMG activity during the training period were observed. These changes were not accompanied by any significant changes in the muscle size, which demonstrates the “neural” nature of the training effects.     

Immediate effects of co-contraction training on motor control of the trunk muscles in people with recurrent low back pain

Although deficits in the activation of abdominal muscles are present in people with low back pain (LBP), this can be modified with motor training. Training of deep abdominal muscles in isolation from the other trunk muscles, as an initial phase of training, has been shown to improve the timing of activation of the trained muscles, and reduce symptoms and recurrence of LBP. The aim of this study was to determine if training of the trunk muscles in a non-isolated manner can restore motor control of these muscles in people with LBP. Ten subjects with non-specific LBP performed a single session of training that involved three tasks: “abdominal curl up”, “side bridge” and “birdog”. Electromyographic activity (EMG) of trunk and deltoid muscles was recorded with fine-wire and surface electrodes during rapid arm movements and walking, before and immediately following the intervention. Onset of trunk muscle EMG relative to that of the prime mover (deltoid) during arm movements and the mean, standard deviation (SD) and coefficient of variation of abdominal muscle EMG during walking were calculated. There was no significant change in the times of onset of trunk muscle EMG during arm movements nor was there any change in the variability of EMG of the abdominal muscles during walking. However, the mean amplitude and SD of abdominal EMG was reduced during walking after training. The results of this study suggest that unlike isolated voluntary training, co-contraction training of the trunk muscles does not restore the motor control of the deep abdominal muscles in people with LBP after a single session of training.     

A training strategy to reduce classification degradation due to electrode displacements in pattern recognition based myoelectric control

Pattern recognition based myoelectric control systems rely on detecting repeatable patterns at given electrode locations. This work describes an experiment to determine the effect of electrode displacements on pattern classification accuracy, and a classifier training strategy to accommodate this degradation. The results show that electrode displacements adversely affect classification accuracy, but training the system to recognize plausible displacement locations mitigates the effect. Furthermore, a combination of time-domain and autoregressive features appears to yield the best classification accuracy and is least affected by electrode displacements.     

Multi-channel surface EMG classification using support vector machines and signal-based wavelet optimization

The study proposes a method for supervised classification of multi-channel surface electromyographic signals with the aim of controlling myoelectric prostheses. The representation space is based on the discrete wavelet transform (DWT) of each recorded EMG signal using unconstrained parameterization of the mother wavelet. The classification is performed with a support vector machine (SVM) approach in a multi-channel representation space. The mother wavelet is optimized with the criterion of minimum classification error, as estimated from the learning signal set. The method was applied to the classification of six hand movements with recording of the surface EMG from eight locations over the forearm. Misclassification rate in six subjects using the eight channels was (mean ± S.D.) 4.7 ± 3.7% with the proposed approach while it was 11.1 ± 10.0% without wavelet optimization (Daubechies wavelet). The DWT and SVM can be implemented with fast algorithms, thus, the method is suitable for real-time implementation.     

Pain-induced changes in cervical muscle activation do not affect muscle fatigability during sustained isometric contraction

This study investigated whether pain-induced changes in cervical muscle activation affect myoelectric manifestations of cervical muscle fatigue. Surface EMG signals were detected from the sternocleidomastoid and splenius capitis muscles bilaterally from 14 healthy subjects during 20-s cervical flexion contractions at 25% of the maximal force. Measurements were performed before and after the injection of 0.5 ml of hypertonic (painful) or isotonic (control) saline into either the sternocleidomastoid or splenius capitis in two experimental sessions. EMG average rectified value and mean power spectral frequency were estimated throughout the sustained contraction. Sternocleidomastoid or splenius capitis muscle pain resulted in lower sternocleidomastoid EMG average rectified value on the side of pain (P < 0.01). However, changes over time of sternocleidomastoid EMG average rectified value and mean frequency (myoelectric manifestations of fatigue) during sustained flexion were not changed during muscle pain. These results demonstrate that pain-induced modifications of cervical muscle activity do not change myoelectric manifestations of fatigue. This finding has implications for interpreting the mechanisms underlying greater cervical muscle fatigue in people with neck pain disorders.     

Rise rate and timing variability of surface electromyographic activity during rhythmic drumming movements in the world’s fastest drummer

The winner of an international contest to find the world’s fastest drummer (WFD) can perform repetitive wrist tapping movements with one hand using a handheld drumstick at 10 Hz, much faster than the maximum tapping frequency of 5-7 Hz in the general population. The muscle activity facilitating this improved performance, however, has only recently been explored. The present study investigated the rise rate and timing variability of surface electromyographic (EMG) activity of wrist flexor/extensor muscles in the WFD, and compared them with those in two control groups: non-drummers (NDs) and ordinary drummers (ODs). The WFD showed more rapid EMG amplitude rise, earlier decline of EMG activity, and more stable muscle activation time than the NDs and ODs. In addition, there was a significant correlation between the EMG rise rate and the duration of drum training in the group of drummers (i.e., ODs and WFD). These results indicate that the 10-Hz performance of the WFD was achieved by a ‘sharper’ and ‘less noisy’ burst pattern of wrist muscles, and that drum training would have the effect to increase the speed of development of muscle tension.     

Effect of Feedback during Virtual Training of Grip Force Control with a Myoelectric Prosthesis

The aim of this study was to determine whether virtual training improves grip force control in prosthesis use, and to examine which type of augmented feedback facilitates its learning most. Thirty-two able-bodied participants trained grip force with a virtual ball-throwing game for five sessions in a two-week period, using a myoelectric simulator. They received either feedback on movement outcome or on movement execution. Sixteen controls received training that did not focus on force control. Variability over learning was examined with the Tolerance-Noise-Covariation approach, and the transfer of grip force control was assessed in five test-tasks that assessed different aspects of force control in a pretest, a posttest and a retention test. During training performance increased while the variability in performance was decreased, mainly by reduction in noise. Grip force control only improved in the test-tasks that provided information on performance. Starting the training with a task that required low force production showed no transfer of the learned grip force. Feedback on movement execution was detrimental to grip force control, whereas feedback on movement outcome enhanced transfer of grip force control to tasks other than trained. Clinical implications of these results regarding virtual training of grip force control are discussed.     

A mixture model with a reference-based automatic selection of components for disease classification from protein and/or gene expression levels

Background

Identification of discourse relations, such as causal and contrastive relations, between situations mentioned in text is an important task for biomedical text-mining. A biomedical text corpus annotated with discourse relations would be very useful for developing and evaluating methods for biomedical discourse processing. However, little effort has been made to develop such an annotated resource.

Results

We have developed the Biomedical Discourse Relation Bank (BioDRB), in which we have annotated explicit and implicit discourse relations in 24 open-access full-text biomedical articles from the GENIA corpus. Guidelines for the annotation were adapted from the Penn Discourse TreeBank (PDTB), which has discourse relations annotated over open-domain news articles. We introduced new conventions and modifications to the sense classification. We report reliable inter-annotator agreement of over 80% for all sub-tasks. Experiments for identifying the sense of explicit discourse connectives show the connective itself as a highly reliable indicator for coarse sense classification (accuracy 90.9% and F1 score 0.89). These results are comparable to results obtained with the same classifier on the PDTB data. With more refined sense classification, there is degradation in performance (accuracy 69.2% and F1 score 0.28), mainly due to sparsity in the data. The size of the corpus was found to be sufficient for identifying the sense of explicit connectives, with classifier performance stabilizing at about 1900 training instances. Finally, the classifier performs poorly when trained on PDTB and tested on BioDRB (accuracy 54.5% and F1 score 0.57).

Conclusion

Our work shows that discourse relations can be reliably annotated in biomedical text. Coarse sense disambiguation of explicit connectives can be done with high reliability by using just the connective as a feature, but more refined sense classification requires either richer features or more annotated data. The poor performance of a classifier trained in the open domain and tested in the biomedical domain suggests significant differences in the semantic usage of connectives across these domains, and provides robust evidence for a biomedical sublanguage for discourse and the need to develop a specialized biomedical discourse annotated corpus. The results of our cross-domain experiments are consistent with related work on identifying connectives in BioDRB.     

Awareness during electromyographic biofeedback: Of signal or process?

During relaxation training, awareness of trial-to-trial changes in frontalis-muscle tension levels was assessed with and without auditory electromyographic(EMG) biofeedback. Immediately after each 128-sec training trial, the subject was required to guess whether muscle tension indexed by EMG activity increased(“Up”) or decreased(“Down”) relative to the immediately preceding trial. The probability of correct guessing, P(c), improved as the absolute difference in EMG increased between trials only when biofeedback was presented. For subjects not receiving biofeedback, P(c) remained low even when the absolute difference between trials was large. Subjects in each condition employed a strategy to guess “Down” more often consistent with the expectation that they were being trained to relax. The “Down” set strategy was shown to be separable from the informational basis of P(c) provided by biofeedback. This procedure can be employed to evaluate central assumptions of biofeedback relating to posttraining awareness of changes in muscle tension and the relationship between awareness and control of muscle tension.     

Feasibility of using combined EMG and kinematic signals for prosthesis control: A simulation study using a virtual reality environment

Transhumeral amputation has a significant effect on a person’s independence and quality of life. Myoelectric prostheses have the potential to restore upper limb function, however their use is currently limited due to lack of intuitive and natural control of multiple degrees of freedom. The goal of this study was to evaluate a novel transhumeral prosthesis controller that uses a combination of kinematic and electromyographic (EMG) signals recorded from the person’s proximal humerus. Specifically, we trained a time-delayed artificial neural network to predict elbow flexion/extension and forearm pronation/supination from six proximal EMG signals, and humeral angular velocity and linear acceleration. We evaluated this scheme with ten able-bodied subjects offline, as well as in a target-reaching task presented in an immersive virtual reality environment. The offline training had a target of 4° for flexion/extension and 8° for pronation/supination, which it easily exceeded (2.7° and 5.5° respectively). During online testing, all subjects completed the target-reaching task with path efficiency of 78% and minimal overshoot (1.5%). Thus, combining kinematic and muscle activity signals from the proximal humerus can provide adequate prosthesis control, and testing in a virtual reality environment can provide meaningful data on controller performance.     

Myocontrol in aging

Myoelectric (EMG) signals are used in assistive technology for prostheses, computer and domestic control. An experimental study previously conducted with young participants was replicated with elderly persons in order to assess the effect of age on the ability to control myoelectric amplitude (or myocontrol). Participants performed pointing tasks as the myoelectric amplitude was captured by a surface electrode in two modalities (sustained: stabilize the amplitude after reaching the desired level; impulsion: return immediately to resting amplitude). There was a significant decrease of performance with Age. However, the patterns of performance of young and aged were noticeably similar. The Impulsion modality was difficult (high rates of failure) and the speed-accuracy trade-offs predicted by Fitts' law were absent (bow-shaped patterns as function of target amplitude instead of logarithmic increase). Conversely, the reach phase of the Sustained modality followed the predictions of Fitts' law. However, the slope of the regression line with Fitts' index of difficulty was quite steeper in aged than in young participants. These findings suggest that 1) all participants, young and aged, adapt their reaching strategies to the anticipated state (sustained amplitude or not) and/or to the difficulty of the task, 2) myocontrol in aged persons is more fragile, i.e., performance is markedly degraded as the difficulty of the task increases. However, when individual performance was examined, some aged individuals were found to perform as well as the young participants, congruently with the literature on good aging.     

Anticipation mechanism in body sway control and effect of muscle fatigue

The aim of this work is to quantify the occurrence of an anticipatory mechanism in the control of quiet standing by measuring the lag between the myoelectric activity of the lateral gastrocnemius muscle and the stabilometric signal, as well as to determine the influence of the muscle fatigue on this process. Stabilometric and electromyographic (EMG) signals were synchronously collected from 22 subjects. Gastrocnemius fatigue was induced by a sustained plantar flexed posture until muscle failure. The data acquisition lasted for 120 s before and after the induced fatigue. After mean removal, the root mean square values of the EMG (RMS-EMG) were calculated for each 20 ms period. The normalized cross-correlation function was estimated to find the time delay between RMS-EMG and stabilometric signals. Anticipation values up to 1.62 s were found both before and after fatigue conditions (p < 0.05), indicating that this mechanism plays an important role in body sway control. The fatigue caused a significant increase in the latency between the myoelectric activity of the gastrocnemius muscle and the movements of the center of pressure (p < 0.05).     

Effects of 7-day intake of hydrogen-rich water on physical performance of trained and untrained subjects

Hydrogen-rich water (HRW) is used as a supplement to improve performance and reduce fatigue in athletes. However, the potentially beneficial effects of HRW intake could be mediated by the training status of athletes. The purpose of the study was to analyse the ergogenic effect of intake of HRW for one week on aerobic and anaerobic performance, both in trained and untrained individuals. Thirty-seven volunteers participated in the study and were divided into two experimental groups: trained cyclists and untrained subjects. A double-blind crossover design was performed in which all subjects took a placebo (PW) and nano-bubble HRW (pH: 7.5; hydrogen concentration: 1.9 ppm; oxidation-reduction potential (ORP): -600 mV). At the end of 7-day intake, performance was assessed by an incremental VO₂max test and by a maximum anaerobic test. After HRW intake, only trained cyclists improved their performance in the anaerobic test with an increase in peak power (from 766.2 ± 125.6 to 826.5 ± 143.4 W; d = .51) and mean power (from 350.0 ± 53.5 to 380.2 ± 71.3 W; d = .51), and a decrease in the fatigue index (from 77.6 ± 5.8 to 75.1 ± 5.9%; d = .45). The findings demonstrate that the ergogenic effect of HRW is mediated by the training status, and that 7-day intake of HRW would be an effective strategy for improving anaerobic performance in trained cyclists.     

Biofeedback-based stress management training with a population of business managers

A biofeedback-based stress management training program was experimentally evaluated using populations of middle-level managers from a large corporation. The training program, once-weekly 1-hour sessions for 6 weeks, combined frontal and other site EMG biofeedback, progressive relaxation and breathing exercises, cognitive stress management, and generalization techniques. Control groups participated in either the assessment procedures only or the assessment procedures and six once-weekly discussions of stress and the job on both an individual(two sessions) and group(four sessions) basis. Significant effects were found in self-report measures, state and trait anxiety, experience of stress; in physiological measures, basal frontal EMG and frontal EMG during recovery from stress, and finger temperature; and in ratings of overall job performance. However, no consistent advantage for the training group or either control group was found. Several possible explanations for the failure of the biofeedback-based stress management training condition to achieve a consistent advantage over the control conditions are presented.     

Bispectrum-based features classification for myoelectric control

Surface electromyographic signals provide useful information about motion intentionality. Therefore, they are a suitable reference signal for control purposes. A continuous classification scheme of five upper limb movements applied to a myoelectric control of a robotic arm is presented. This classification is based on features extracted from the bispectrum of four EMG signal channels. Among several bispectrum estimators, this paper is focused on arithmetic mean, median, and trimmed mean estimators, and their ensemble average versions. All bispectrum estimators have been evaluated in terms of accuracy, robustness against outliers, and computational time. The median bispectrum estimator shows low variance and high robustness properties. Two feature reduction methods for the complex bispectrum matrix are proposed. The first one estimates the three classic means (arithmetic, harmonic, and geometric means) from the module of the bispectrum matrix, and the second one estimates the same three means from the square of the real part of the bispectrum matrix. A two-layer feedforward network for movement's classification and a dedicated system to achieve the myoelectric control of a robotic arm were used. It was found that the classification performance in real-time is similar to those obtained off-line by other authors, and that all volunteers in the practical application successfully completed the control task.     

Sequence specific motor performance gains after memory consolidation in children and adolescents

Memory consolidation for a trained sequence of finger opposition movements, in 9- and 12-year-old children, was recently found to be significantly less susceptible to interference by a subsequent training experience, compared to that of 17-year-olds. It was suggested that, in children, the experience of training on any sequence of finger movements may affect the performance of the sequence elements, component movements, rather than the sequence as a unit; the latter has been implicated in the learning of the task by adults. This hypothesis implied a possible childhood advantage in the ability to transfer the gains from a trained to the reversed, untrained, sequence of movements. Here we report the results of transfer tests undertaken to test this proposal in 9-, 12-, and 17-year-olds after training in the finger-to-thumb opposition sequence (FOS) learning task. Our results show that the performance gains in the trained sequence partially transferred from the left, trained hand, to the untrained hand at 48-hours after a single training session in the three age-groups tested. However, there was very little transfer of the gains from the trained to the untrained, reversed, sequence performed by either hand. The results indicate sequence specific post-training gains in FOS performance, as opposed to a general improvement in performance of the individual, component, movements that comprised both the trained and untrained sequences. These results do not support the proposal that the reduced susceptibility to interference, in children before adolescence, reflects a difference in movement syntax representation after training.