Techniques of EMG signal analysis: detection, processing, classification and applications

Electromyography (EMG) signals can be used for clinical/biomedical applications, Evolvable Hardware Chip (EHW) development, and modern human computer interaction. EMG signals acquired from muscles require advanced methods for detection, decomposition, processing, and classification. The purpose of this paper is to illustrate the various methodologies and algorithms for EMG signal analysis to provide efficient and effective ways of understanding the signal and its nature. We further point up some of the hardware implementations using EMG focusing on applications related to prosthetic hand control, grasp recognition, and human computer interaction. A comparison study is also given to show performance of various EMG signal analysis methods. This paper provides researchers a good understanding of EMG signal and its analysis procedures. This knowledge will help them develop more powerful, flexible, and efficient applications.     

Optimized Tunable Q Wavelet Transform Based Drowsiness Detection from Electroencephalogram Signals

Early discernment of drivers drowsy state may prevent numerous worldwide road accidents. Electroencephalogram (EEG) signals provide valuable information about the neurological changes for discrimination of alert and drowsy state. A signal is decomposed into multi-components for the analysis of the physiological state. Tunable Q wavelet transform (TQWT) decomposes the signal into low-pass and high-pass sub-bands without a choice of wavelet. The information content captured by these sub-bands depends on the choice of decomposition parameters. Due to the non-stationary nature of EEG signals, the predefined decomposition parameters of TQWT lead to information loss and degrade system performance. Hence it is required to automate the decomposition parameters in accordance with the nature of signals. In this paper, an optimized tunable Q wavelet transform (O-TQWT) is proposed for the adaptive selection of decomposition parameters by using different optimization algorithms. Objective function as a mean square error (MSE) of decomposition is minimized by optimization algorithms. Optimum decomposition parameters are used to decompose the signals into sub-bands. Time-domain based features are excerpted from the sub-bands of O-TQWT. Highly discriminant features selected by using Kruskal Wallis test are used as an input to different classification techniques. Classification accuracy of 96.14% is achieved by least square support vector machine with radial basis function kernel which is better than the other existing methodologies using the same database.     

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

Many algorithms have been described in the literature for estimating amplitude, frequency variables and conduction velocity of the surface EMG signal detected during voluntary contractions. They have been used in different application areas for the non invasive assessment of muscle functions. Although many studies have focused on the comparison of different methods for information extraction from surface EMG signals, they have been carried out under different conditions and a complete comparison is not available. It is the purpose of this paper to briefly review the most frequently used algorithms for EMG variable estimation, compare them using computer generated as well as real signals and outline the advantages and drawbacks of each. In particular the paper focuses on the issue of EMG amplitude estimation with and without pre-whitening of the signal, mean and median frequency estimation with periodogram and autoregressive based algorithms both in stationary and non-stationary conditions, delay estimation for the calculation of muscle fiber conduction velocity.     

Analysis of phasic and tonic electromyographic signal characteristics: Electromyographic synthesis and comparison of novel morphological and linear-envelope approaches

The pattern of tonic and phasic components in an EMG signal reflects the underlying behaviour of the central nervous system (CNS) in controlling the musculature. One avenue for gaining a better understanding of this behaviour is to seek a quantitative characterisation of these phasic and tonic components. We propose that these signal characteristics can range between unvarying, tonic and intermittent, phasic activation through a continuum of EMG amplitude modulation. In this paper, we present two new algorithms for quantifying amplitude modulation: a linear-envelope approach, and a mathematical morphology approach. In addition we present an algorithm for synthesising EMG signals with known amplitude modulation. The efficacy of the synthesis algorithm is demonstrated using real EMG data. We present an evaluation and comparison of the two algorithms for quantifying amplitude modulation based on synthetic data generated by the proposed synthesis algorithm. The results demonstrate that the EMG synthesis parameters represent 91.9% and 96.2% of the variance of linear-envelopes extracted from lumbo-pelvic muscle EMG signals collected from subjects performing a repetitive-movement task. This depended, however, on the muscle and movement-speed considered (F = 4.02, p < 0.001). Coefficients of determination between input and output amplitude modulation variables were used to quantify the accuracy of the linear-envelope and morphological signal processing algorithms. The linear-envelope algorithm exhibited higher coefficients of determination than the most accurate morphological approach (and hence greater accuracy, T = 8.16, p < 0.001). Similarly, the standard deviation of the coefficients of determination was 1.691 times smaller (p < 0.001). This signal processing algorithm represents a novel tool for the quantification of amplitude modulation in continuous EMG signals and can be used in the study of CNS motor control of the musculature in repetitive-movement tasks.     

Removal of ECG interference from surface respiratory electromyography

The signal to noise ratio (SNR) of surface respiratory electromyography signal is very low. Indeed EMG signal is contaminated by different types of noise especially the cardiac artefact ECG. This article explores the problem of removing ECG artefact from respiratory EMG signal. The new method uses an adaptive structure with an electrocardyographic ECG reference signal carried out by wavelet decomposition. The proposed algorithm requires only one channel to both estimating the adaptive filter input reference noise and the respiratory EMG signal. This new technique demonstrates how two steps will be combined: the first step decomposes the signal with forward discrete wavelet transform into sub-bands to get the wavelet coefficients. Then, an improved soft thresholding function was applied. And the ECG input reference signal is reconstructed with the transformed coefficients whereas, the second uses an adaptive filter especially the LMS one to remove the ECG signal. After trying statistical as well as mathematical analysis, the complete investigation ensures that all details and steps make proof that our rigorous method is appropriate. Compared to the results obtained using previous techniques, the results achieved using the new algorithm show a significant improvement in the efficiency of the ECG rejection.     

Use of surface EMG for studying motor unit recruitment during isometric linear force ramp.

The aim of this work was to demonstrate the rank order of motor unit (MU) recruitment by surface EMG based on a Laplacian detection technique and to document the MU features at their recruitment threshold. Surface EMG signals were recorded on the biceps brachii of 10 healthy subjects during linear force ramps. When achievable, the signals were decomposed into MU action potential (MUAP) trains. MU inter-pulse interval (IPI), conduction velocity (MUCV) and amplitude were estimated on the first 12 MUAPs of each detectable train in order to characterize the MU features at their firing onset. A strong correlation was found between MU recruitment threshold and IPI, MUCV, and amplitude, showing that the size principle can be demonstrated by a fully non-invasive EMG technique. However, signal decomposition was not possible on seven subjects due to the effects of the volume conductor when the skinfold thickness was too large. When requirements for an optimal detection of MUAP trains are met, surface EMG may be used to improve our understanding of MU activity.     

基于表面肌电信号的人体动作识别算法研究进展

表面肌电信号(Surface Electromyography,sEMG)是通过相应肌群表面的传感器记录下来的一维时间序列非平稳生物电信号,不但反映了神经肌肉系统活动,对于反映相应动作肢体活动信息同样重要。而模式识别是肌电应用领域的基础和关键。为了在应用基于表面肌电信号模式识别中选取合适算法,本文拟对基于表面肌电信号的人体动作识别算法进行回顾分析,主要包括模糊模式识别算法、线性判别分析算法、人工神经网络算法和支持向量机算法。模糊模式识别能自适应提取模糊规则,对初始化规则不敏感,适合处理s EMG这样具有严格不重复的生物电信号;线性判别分析对数据进行降维,计算简单,但不适合大数据;人工神经网络可以同时描述训练样本输入输出的线性关系和非线性映射关系,可以解决复杂的分类问题,学习能力强;支持向量机处理小样本、非线性的高维数据优势明显,计算速度快。比较各方法的优缺点,为今后处理此类问题模式识别算法选取提供了参考和依据。     

Review on electromyography signal acquisition and processing

Electromyography (EMG) is a technique for recording biomedical electrical signals obtained from the neuromuscular activities. These signals are used to monitor medical abnormalities and activation levels, and also to analyze the biomechanics of any animal movements. In this article, we provide a short review of EMG signal acquisition and processing techniques. The average efficiency of capture of EMG signals with current technologies is around 70%. Once the signal is captured, signal processing algorithms then determine the recognition accuracy, with which signals are decoded for their corresponding purpose (e.g., moving robotic arm, speech recognition, gait analysis). The recognition accuracy can go as high as 99.8%. The accuracy with which the EMG signal is decoded has already crossed 99%, and with improvements in deep learning technology, there is a large scope for improvement in the design hardware that can efficiently capture EMG signals.     

Flexible Analytic Wavelet Transform Based Features for Physical Action Identification Using sEMG Signals

ObjectivesElectromyography (EMG) is recording of the electrical activity produced by skeletal muscles. The classification of the EMG signals for different physical actions can be useful in restoring some or all of the lost motor functionalities in these individuals. Accuracy in classifying the EMG signal indicates efficient control of prosthesis.Material and methodsThe flexible analytic wavelet transform (FAWT) is used for classification of surface electromyography (sEMG) signals for identification of physical actions. FAWT is an efficient method for decomposition of sEMG signal into eight sub-bands, features namely neg-entropy, mean absolute value (MAV), variance (VAR), modified mean absolute value type 1 (MAV1), waveform length (WL), simple square integral (SSI), Tsallis entropy, integrated EMG (IEMG) are extracted from the sub-bands. Extracted features are fed into an extreme learning machine (ELM) classifier with sigmoid activation function.ResultsComprehensive experiments are conducted on the input sEMG signals and the accuracy, sensitivity and specificity scores are used for performance measurement. Experiments showed that among all sub-bands, the seventh sub-band provided the best performance where the recorded accuracy, sensitivity and specificity values were 99.36%, 99.36% and 99.93%, respectively. The comparison results showed best efficiency of proposed method as compared to other methods on the same dataset.ConclusionThis paper investigates the usage of the FAWT and ELM on sEMG signal classification. The results show that the proposed method is quite efficient in classification of the sEMG signals. It is also observed that the seventh sub-band of the FAWT provides the best discrimination property. In the future works, recent wavelet transform methods will be used for improving the classification performance.     

Decomposition of indwelling EMG signals.

Decomposition of indwelling electromyographic (EMG) signals is challenging in view of the complex and often unpredictable behaviors and interactions of the action potential trains of different motor units that constitute the indwelling EMG signal. These phenomena create a myriad of problem situations that a decomposition technique needs to address to attain completeness and accuracy levels required for various scientific and clinical applications. Starting with the maximum a posteriori probability classifier adapted from the original precision decomposition system (PD I) of LeFever and De Luca (25, 26), an artificial intelligence approach has been used to develop a multiclassifier system (PD II) for addressing some of the experimentally identified problem situations. On a database of indwelling EMG signals reflecting such conditions, the fully automatic PD II system is found to achieve a decomposition accuracy of 86.0% despite the fact that its results include low-amplitude action potential trains that are not decomposable at all via systems such as PD I. Accuracy was established by comparing the decompositions of indwelling EMG signals obtained from two sensors. At the end of the automatic PD II decomposition procedure, the accuracy may be enhanced to nearly 100% via an interactive editor, a particularly significant fact for the previously indecomposable trains.     

Optimal search space for clustering gene expression data via consensus.

Ensemble clustering methods have become increasingly important to ease the task of choosing the most appropriate cluster algorithm for a particular data analysis problem. The consensus clustering (CC) algorithm is a recognized ensemble clustering method that uses an artificial intelligence technique to optimize a fitness function. We formally prove the existence of a subspace of the search space for CC, which contains all solutions of maximal fitness and suggests two greedy algorithms to search this subspace. We evaluate the algorithms on two gene expression data sets and one synthetic data set, and compare the result with the results of other ensemble clustering approaches.     

Automatic decomposition of multichannel intramuscular EMG signals

We describe an automatic algorithm for decomposing multichannel EMG signals into their component motor unit action potential (MUAP) trains, including signals from widely separated recording sites in which MUAPs exhibit appreciable interchannel offset and jitter. The algorithm has two phases. In the clustering phase, the distinct, recurring MUAPs in each channel are identified, the ones that correspond to the same motor units are determined by their temporal relationships, and multichannel templates are computed. In the identification stage, the MUAP discharges in the signal are identified using matched filtering and superimposition resolution techniques. The algorithm looks for the MUAPs with the largest single channel components first, using matches in one channel to guide the search in other channels, and using information from the other channels to confirm or refute each identification. For validation, the algorithm was used to decompose 10 real 6-to-8-channel EMG signals containing activity from up to 25 motor units. Comparison with expert manual decomposition showed that the algorithm identified more than 75% of the total 176 MUAP trains with an accuracy greater than 95%. The algorithm is fast, robust, and shows promise to be accurate enough to be a useful tool for decomposing multichannel signals. It is freely available at http://emglab.stanford.edu.     

EMG signal decomposition: how can it be accomplished and used?

Electromyographic (EMG) signals are composed of the superposition of the activity of individual motor units. Techniques exist for the decomposition of an EMG signal into its constituent components. Following is a review and explanation of the techniques that have been used to decompose EMG signals. Before describing the decomposition techniques, the fundamental composition of EMG signals is explained and after, potential sources of information from and various uses of decomposed EMG signals are described.     

Tutorial: Analysis of motor unit discharge characteristics from high-density surface EMG signals

Recent work demonstrated that it is possible to identify motor unit discharge times from high-density surface EMG (HDEMG) decomposition. Since then, the number of studies that use HDEMG decomposition for motor unit investigations has increased considerably. Although HDEMG decomposition is a semi-automatic process, the analysis and interpretation of the motor unit pulse trains requires a thorough inspection of the output of the decomposition result. Here, we report guidelines to perform an accurate extraction of motor unit discharge times and interpretation of the signals. This tutorial includes a discussion of the differences between the extraction of global EMG signal features versus the identification of motor unit activity for physiological investigations followed by a comprehensive guide on how to acquire, inspect, and decompose HDEMG signals, and robust extraction of motor unit discharge characteristics.     

Machine Learning for Biomedical Literature Triage

This paper presents a machine learning system for supporting the first task of the biological literature manual curation process, called triage. We compare the performance of various classification models, by experimenting with dataset sampling factors and a set of features, as well as three different machine learning algorithms (Naive Bayes, Support Vector Machine and Logistic Model Trees). The results show that the most fitting model to handle the imbalanced datasets of the triage classification task is obtained by using domain relevant features, an under-sampling technique, and the Logistic Model Trees algorithm.     

Analysis and classification of compressed EMG signals by wavelet transform via alternative neural networks algorithms

We propose intelligent methods for classifying three different muscle types, i.e. biceps, frontallis and abductor pollicis brevis muscles, with low computational complexity. For this aim, electromyogram (EMG) signals are recorded and modelled by using an auto-regressive (AR) model. As the size of the EMG signals is usually large, the computational complexity of artificial neural network (ANN) systems drastically increases. Therefore, in the proposed scheme EMG signals are pre-processed by using a wavelet transform and then they are modelled by employing an AR approach. The AR coefficients are used to train and test the ANNs. Experimental results show that the highest achieved classification accuracy is more than 95% in the case of EMG signals pre-processed by wavelet transform. The wavelet transform-based pre-processing significantly increases the performance rates compared to standard multilayer perceptron and general regression neural networks algorithms.     

Model-based clustering and data transformations for gene expression data.

MOTIVATION: Clustering is a useful exploratory technique for the analysis of gene expression data. Many different heuristic clustering algorithms have been proposed in this context. Clustering algorithms based on probability models offer a principled alternative to heuristic algorithms. In particular, model-based clustering assumes that the data is generated by a finite mixture of underlying probability distributions such as multivariate normal distributions. The issues of selecting a 'good' clustering method and determining the 'correct' number of clusters are reduced to model selection problems in the probability framework. Gaussian mixture models have been shown to be a powerful tool for clustering in many applications. RESULTS: We benchmarked the performance of model-based clustering on several synthetic and real gene expression data sets for which external evaluation criteria were available. The model-based approach has superior performance on our synthetic data sets, consistently selecting the correct model and the number of clusters. On real expression data, the model-based approach produced clusters of quality comparable to a leading heuristic clustering algorithm, but with the key advantage of suggesting the number of clusters and an appropriate model. We also explored the validity of the Gaussian mixture assumption on different transformations of real data. We also assessed the degree to which these real gene expression data sets fit multivariate Gaussian distributions both before and after subjecting them to commonly used data transformations. Suitably chosen transformations seem to result in reasonable fits. AVAILABILITY: MCLUST is available at http://www.stat.washington.edu/fraley/mclust. The software for the diagonal model is under development. CONTACT: kayee@cs.washington.edu. SUPPLEMENTARY INFORMATION: http://www.cs.washington.edu/homes/kayee/model.     

Comparative analysis of algorithms for signal quantitation from oligonucleotide microarrays

MOTIVATION: Recent years' exponential increase in DNA microarrays experiments has motivated the development of many signal quantitation (SQ) algorithms. These algorithms perform various transformations on the actual measurements aimed to enable researchers to compare readings of different genes quantitatively within one experiment and across separate experiments. However, it is relatively unclear whether there is a 'best' algorithm to quantitate microarray data. The ability to compare and assess such algorithms is crucial for any downstream analysis. In this work, we suggest a methodology for comparing different signal quantitation algorithms for gene expression data. Our aim is to enable researchers to compare the effect of different SQ algorithms on the specific dataset they are dealing with. We combine two kinds of tests to assess the effect of an SQ algorithm in terms of signal to noise ratio. To assess noise, we exploit redundancy within the experimental dataset to test the variability of a given SQ algorithm output. For the effect of the SQ on the signal we evaluate the overabundance of differentially expressed genes using various statistical significance tests. RESULTS: We demonstrate our analysis approach with three SQ algorithms for oligonucleotide microarrays. We compare the results of using the dChip software and the RMAExpress software to the ones obtained by using the standard Affymetrix MAS5 on a dataset containing pairs of repeated hybridizations. Our analysis suggests that dChip is more robust and stable than the MAS5 tools for about 60% of the genes while RMAExpress is able to achieve an even greater improvement in terms of signal to noise, for more than 95% of the genes.     

Separation of propagating and non propagating components in surface EMG

Surface electromyogram (EMG) detected by electrode arrays along the muscle fibre direction can be approximated by the sum of propagating and non propagating components. A technique to separate propagating and non propagating components in surface EMG signals is developed. The first step is an adaptive filter, which allows obtaining an estimation of the delay between signals detected at different channels and a first estimate of propagating and non propagating components; the second step is used to optimise the estimation of the two components. The method is applicable to signals with one propagating and one non propagating component. It was optimised on simulated signals, and then applied to single motor unit action potentials (MUAP) and to electrically elicited EMG (M-waves).

The new method was first tested on phenomenological signals constituted by the sum of a propagating and a non propagating signal and then applied to simulated and experimental EMG signals. Simulated signals were generated by a cylindrical, layered volume conductor model. Experimental signals were monopolar surface EMG signals collected from the abductor pollicis brevis muscle and M-waves recorded during transcutaneous electrical stimulation of the biceps muscle. The technique may find different applications: in single motor unit (MU) studies (a) for decreasing the variability and bias of CV estimates due to the presence of the non propagating components, (b) for estimating automatically the length of the muscle fibres from only three detected channels and (c) for removal of the stimulation artifact M-waves.