Two-dimensional compression of surface electromyographic signals using column-correlation sorting and image encoders

BackgroundSurface electromyographic (S-EMG) signal processing has been emerging in the past few years due to its non-invasive assessment of muscle function and structure and because of the fast growing rate of digital technology which brings about new solutions and applications. Factors such as sampling rate, quantization word length, number of channels and experiment duration can lead to a potentially large volume of data. Efficient transmission and/or storage of S-EMG signals are actually a research issue. That is the aim of this work.MethodsThis paper presents an algorithm for the data compression of surface electromyographic (S-EMG) signals recorded during isometric contractions protocol and during dynamic experimental protocols such as the cycling activity. The proposed algorithm is based on discrete wavelet transform to proceed spectral decomposition and de-correlation, on a dynamic bit allocation procedure to code the wavelets transformed coefficients, and on an entropy coding to minimize the remaining redundancy and to pack all data. The bit allocation scheme is based on mathematical decreasing spectral shape models, which indicates a shorter digital word length to code high frequency wavelets transformed coefficients. Four bit allocation spectral shape methods were implemented and compared: decreasing exponential spectral shape, decreasing linear spectral shape, decreasing square-root spectral shape and rotated hyperbolic tangent spectral shape.ResultsThe proposed method is demonstrated and evaluated for an isometric protocol and for a dynamic protocol using a real S-EMG signal data bank. Objective performance evaluations metrics are presented. In addition, comparisons with other encoders proposed in scientific literature are shown.ConclusionsThe decreasing bit allocation shape applied to the quantized wavelet coefficients combined with arithmetic coding results is an efficient procedure. The performance comparisons of the proposed S-EMG data compression algorithm with the established techniques found in scientific literature have shown promising results.

Bioelectric signals are used to measure electrical potential, but there are different types of signals. The electromyography (EMG) is a type of bioelectric signal used to monitor and recode the electrical activity of the muscles. The current work aims to model and reproduce surface EMG (SEMG) signals using an artificial neural network. Such research can aid studies into life enhancement for those suffering from damage or disease affecting their nervous system. The SEMG signal is collected from the surface above the bicep muscle through dynamic (concentric and eccentric) contraction with various loads. In this paper, we use time domain features to analyze the relationship between the amplitude of SEMG signals and the load. We extract some features (e.g., mean absolute value, root mean square, variance and standard deviation) from the collected SEMG signals to estimate the bicep’ muscle force for the various loads. Further, we use the R-squared value to depict the correlation between the SEMG amplitude and the muscle loads by linear fitting. The best performance the ANN model with 60 hidden neurons for three loads used (3 kg, 5 kg and 7 kg) has given a mean square error of 1.145, 1.3659 and 1.4238, respectively. The R-squared observed are 0.9993, 0.99999 and 0.99999 for predicting (reproduction step) of smooth SEMG signals.

This paper proposes to monitor and recognize the fatigue state during football training by analyzing the surface electromyography (EMG) signals. The surface electromyography (EMG) signal is closely connected with the state during sports and training. First, power frequency interference, motion artifacts, and baseline drift in the surface electromyography (EMG) signal are removed; second, the authors extract 6 features: rectified average value (ARV), integrated electromyography myoelectric value (IEMG), root mean square of electromyography value (RMS), median frequency (MF), average power frequency (MPF), and electromyography power (TP) to represent the surface electromyography (EMG) signal; lastly, the extracted features are input into a one-class support vector machine to determine whether the player has been fatigued and are input into a weighted support vector machine to determine the degree of fatigue if the player has been fatigued. The experimental results show that more than 95% of the fatigue state can be recognized by surface electromyography (EMG) signal.

Inverse relationship between the complexity of midfoot kinematics and muscle activation in patients with medial tibial stress syndrome

Assessment of low back muscle fatigue by surface EMG signal analysis: methodological aspects

Various myoelectric prostheses controlled by electromyography (EMG) signals have been developed. However, there have been few studies that provide fast and accurate methods to predict handgrip force from EMG signals. Rapid and precise handgrip force prediction is required, especially for the real-time control system of myoelectric prostheses. In this study, extreme learning machine (ELM) is applied to predict handgrip force from surface EMG signals of forearm muscles. Furthermore, ELM is compared with support vector machine (SVM) and multiple nonlinear regression (MNLR). The below 10 % of the surface EMG and handgrip force signals were cut away, and then the root mean square feature extracted from the modified surface EMG signals was taken as input vector for these three kinds of predicting mechanisms. For the testing dataset, ELM achieved a slightly larger root mean squared error than SVM did and a smaller one than MNLR did. Meanwhile, all three methods showed high correlation coefficients. For the total processing time, ELM and MNLR consumed much less time than SVM did. Experimental results demonstrate that ELM possesses a relatively good accuracy and little consumed time, although SVM is effective for handgrip force estimation in terms of accuracy. Overall, ELM has a promising potential for predicting handgrip force rapidly and precisely.

Objective motor response onset detection in surface myoelectric signals

This study intends to explore the wavelet denoising for optimal MUAP detection through the wavelet analysis of surface electromyographic (SEMG) signals. We first derive an estimator for signal to noise ratio and show that this estimator correlates to the quality of the reconstructed simulated signal. When applying this estimator to evaluate the SEMG signal, we find that the reconstructed signal is insensitive to the selection of denoising methods. This finding is further confirmed by the identical plots of those reconstructed SEMG data. In addition, the close correspondence of MUAP occurrences in the reconstructed signal and those in the original signal suggests that the denoising procedure can preserve the features of MUAP in the original SEMG signals.

Muscle fatigue is defined as the long lasting deterioration of a performance of the human operator to create force. Walking fast can cause muscle fatigue, which is unhealthy and it is incurable when the level of fatigue is high. Muscle fatigue is a well-known research area. In order to completely comprehend the idea many research have been done on different type of muscle fatigue. There are many spectral variables that can be used to determine muscle fatigue during gait. Out of these variables, the amplitude and frequency of the surface EMG signal provide a more accurate reflection of motor unit pattern. In this research, Empirical mode decomposition (EMD) and wavelet Transform applied to the surface EMG (SEMG) signal for realizing the fatiguing contraction during human walking exercise. In this study, RMS, IAV and AIF values were used as spectral variable, which extensively identifies the difference between fatigue and normal muscle when using EMD method compared with other different wavelet functions (WFs). Furthermore, the outcome also proves that, the SEMG amplitude and frequency momentously changes from rest position to maximum contraction position. This research reports on the effectiveness of EMD-based filtering method applied to the surface EMG (SEMG) signal as a means of achieving reliable discrimination of the muscle fatigue.

Reliability of surface electromyography timing parameters in gait in cervical spondylotic myelopathy

Cross-correlation between surface electromyogram (EMG) signals is commonly used as a means of quantifying EMG cross talk during voluntary activation. To examine the reliability of this method, the relationship between cross talk and the cross-correlation between surface EMG signals was examined by using model simulation. The simulation results illustrate an increase in cross talk with increasing subcutaneous fat thickness. The results also indicate that the cross-correlation function decays more rapidly with increasing distance from the active fibers than cross talk, which was defined as the normalized EMG amplitude during activation of a single muscle. The influence of common drive and short-term motor unit synchronization on the cross-correlation between surface EMG signals was also examined. While common drive did not alter the maximum value of the cross-correlation function, the correlation increased with increasing motor unit synchronization. It is concluded that cross-correlation analysis is not a suitable means of quantifying cross talk or of distinguishing between cross talk and coactivation during voluntary contraction. Furthermore, it is possible that a high correlation between surface EMG signals may reflect an association between motor unit firing times, for example due to motor unit synchronization.

Advances in surface electromyographic (EMG) signal decomposition now allow investigators to analyze firing rate data for 20-50 motor units per contraction. To simplify data interpretation, some investigators have relied on group mean analysis of the mean firing rate versus recruitment threshold relationship. It is unclear, however, whether this association is consistently linear. PURPOSE: To determine whether the motor unit mean firing rate versus recruitment threshold relationship is strongest when analyzed via linear, quadratic, or cubic regression. METHODS: Twenty-one men (mean ± SD age = 24 ± 4 years) participated in this study. After determining maximal voluntary contraction (MVC) force of the dominant knee extensors, participants performed trapezoidal isometric contractions at 50% MVC by tracing a visual template displayed on a monitor directly in front of them. Participants were instructed to increase force from 0 to 50% in five seconds, maintain 50% MVC for 15 seconds, and decrease force from 50% to 0 in five seconds. Bipolar surface EMG signals were recorded from the vastus lateralis during each contraction. A surface EMG signal decomposition algorithm was used to calculate mean firing rate and recruitment threshold of each detected motor unit. Motor units with decomposition accuracy levels <90% were discarded. Polynomial regression was used to determine if each mean firing rate versus recruitment threshold relationship was best fit with a linear, quadratic, or cubic model. Data were interpreted on an individual participant basis. RESULTS: Statistically significant (p <.05) moderate to strong (r2=.599-.964) linear relationships existed for all 21 participants. Fourteen of the 21 participants demonstrated relationships that were best fit with a linear model (r2=.599-.964). Of the remaining seven participants, five were best fit with a quadratic model (r2=.864-.953) and two were best fit with a cubic model (r2=.977-.989). CONCLUSION: While moderate to strong linear relationships were found between the firing rate of motor units and their recruitment thresholds for all participants, in certain cases the strength of the association was enhanced when analyzed via a non-linear model. Our findings provide further support for the need to examine motor unit data on a participant-by-participant basis.

The objective of this study is to characterize complexity of lower-extremity muscle coactivation and coordination during gait in children with cerebral palsy (CP), children with typical development (TD) and healthy adults, by applying recently developed multivariate multi-scale entropy (MMSE) analysis to surface electromyographic (EMG) signals. Eleven CP children (CP group), eight TD children and seven healthy adults (considered as an entire control group) were asked to walk while surface EMG signals were collected from five thigh muscles and three lower leg muscles on each leg (16 EMG channels in total). The 16-channel surface EMG data, recorded during a series of consecutive gait cycles, were simultaneously processed by multivariate empirical mode decomposition (MEMD), to generate fully aligned data scales for subsequent MMSE analysis. In order to conduct extensive examination of muscle coactivation complexity using the MEMD-enhanced MMSE, 14 data analysis schemes were designed by varying partial muscle combinations and time durations of data segments. Both TD children and healthy adults showed almost consistent MMSE curves over multiple scales for all the 14 schemes, without any significant difference (p > 0.09). However, distinct diversity in MMSE curve was observed in the CP group when compared with the control group. There appears to be diverse neuropathological processes in CP that may affect dynamical complexity of muscle coactivation and coordination during gait. The abnormal complexity patterns emerging in the CP group can be attributed to different factors such as motor control impairments, loss of muscle couplings, and spasticity or paralysis in individual muscles. This study expands our knowledge of neuropathology of CP from a novel point of view of muscle co-activation complexity, which might be useful to derive a quantitative index for assessing muscle activation characteristics as well as motor function in CP.

The subject of the study is the methods of controlling a robotic manipulator based on surface electromyography (EMG) signals using individualized normalization and classification of gestures by a convolutional neural network (CNN). The aim of the work is to create an effective control system that combines pre-normalization of EMG signals and deep learning to increase the accuracy of gesture recognition and stability in real time. For this purpose, the following were used: signal collection using the Myo Armband, pre-processing (min-max and zero-mean), signal conversion into images through a sliding window, CNN training (ResNet, Adam optimization) and comparison with SVM and Random Forest models. The results obtained showed a classification accuracy of 97.27% in the test environment and 91.71% in real time. The CNN model outperformed traditional methods by 18–19%, and zero-mean increased the accuracy by 2.34% compared to min-max normalization. The system remained stable even with variations in the bracelet position due to individual normalization. Conclusions: the proposed system demonstrates high accuracy, reliability and adaptability in real time. The scientific novelty lies in the combination of individualized normalization of EMG signals with ResNet, which provides stability and exceeds the accuracy of traditional algorithms. In the future, it is planned to expand the set of gestures, study more complex conditions and optimize neural networks for embedded systems.

In this work, a system for monitoring human postures, seizures, and falls from bed using received signal strength indicator (RSSI) and surface electromyography (sEMG) signals is studied through experiments. In this proposed system, a person who is located inside a wireless link is monitored by considering the change in measured RSSI signals as the 2.4 GHz IEEE 802.15.4 signals received at a receiver. Human motions in bed that affect RSSI levels can be captured. Thus, with this technique, it does not raise a privacy concern compared with vision-based technology. Additionally, sEMG signals associated with muscle movements from human postures are recorded from the human body’s abdominal muscles. Eight different activities, including normal and critical events, are tested and evaluated. Experimental results indicate that the proposed system could automatically monitor different human postures in real-time. RSSI and sEMG signals correlated to each posture have their own patterns. Furthermore, the relationship between human behaviors and RSSI and sEMG levels is summarized.