author={Angkoon Phinyomark and Franck Quaine and Yann Laurillau and Sirinee Thongpanja and Chusak Limsakul and Pornchai Phukpattaranont},
  journal={Fluctuation and Noise Letters},
To develop an advanced muscle–computer interface (MCI) based on surface electromyography (EMG) signal, the amplitude estimations of muscle activities, i.e., root mean square (RMS) and mean absolute value (MAV) are widely used as a convenient and accurate input for a recognition system. Their classification performance is comparable to advanced and high computational time-scale methods, i.e., the wavelet transform. However, the signal-to-noise-ratio (SNR) performance of RMS and MAV depends on a… 

Figures and Tables from this paper

A robust measure of probability density function of various noises in electromyography (EMG) signal acquisition

The results show that the L-kurtosis can identify the PDF of all studied noises in EMG signal acquisition correctly, in contrast to other estimating methods, which are inaccuracy in at least one noise type.

Probability Density Functions of Stationary Surface EMG Signals in Noisy Environments

The results show that at low SNR (<;5 dB), all noise types affect the statistical descriptors for the pdf of a noisy EMG signal, and KR2 performs the best among these descriptors, because it is computed based on the quantiles of the data.

Analysis of Electromyography in Dynamic Hand Motions Using L-Kurtosis

The results show that the L-kurtosis can identify the PDF of EMG for all cases, and the kurtosis is inaccuracy and less robust when measured EMG signals have a higher amplitude and are more non-stationary during a transient period.

Surface Electromyography (EMG) Signal Processing, Classification, and Practical Considerations

In this chapter, state-of-the-art EMG signal processing and classification techniques that address these dynamic factors and practical considerations are presented and hands-busy conditions and cross-user classification models that present additional challenges for gesture recognition tasks are explored.

A Multichannel Surface EMG System for Hand Motion Recognition

An EMG feature named differential root mean square (DRMS) is proposed that somewhat takes the relationship between neighboring EMG channels into account and outperforms traditional root meansquare (RMS) by 29.0% and 36.8%, respectively in the task of four hand motion discrimination by K-mean and fuzzy C-means.

A Comparative Study of Different EMG Features for Acoustics-to-EMG Mapping

AEI mapping performance using the BLSTM network reveals that the Hilbert envelope based feature is predicted from speech with the highest accuracy, among all the features, and could be the most representative feature of the underlying muscle activation during speech production.

Wavelet based feature extraction for classification of motor imagery signals

An EEG classification technique based on a combination of wavelet transform analysis and Neural Networks (NN) is presented, which shows Integrated EEG (IEEG) feature set has been found to possess the highest classification accuracy.

EEG-Based Classification of Imagined Fists Movements using Machine Learning and Wavelet Transform Analysis

Compared with the related research work reported in the literature, the proposed system showed a good performance for the classification of fists movements, which enables the control of many computer applications via imagination.

EEG Mouse:A Machine Learning-Based Brain Computer Interface

The main idea of the current work is to use a wireless Electroencephalography headset as a remote control for the mouse cursor of a personal computer using EEG signals as a communication link between brains and computers.



Probability density of the surface electromyogram and its relation to amplitude detectors

The expected (inferior) SNR performance of MAV processing with the Gaussian model is derived and it is shown that the MAV processor is the maximum likelihood estimator of the EMG amplitude for the Laplacian model.


From the viewpoints of maximum class separability, robustness, and complexity, scaling exponent obtained from the DFA method shows the appropriateness to be used as a feature in the classification of the EMG signal.

Influence of smoothing window length on electromyogram amplitude estimates

It was found that SNR increased with window length in a square root fashion, consistent with classic theoretical predictions, however none of the processors achieved the absolute performance level predicted by the theory.

Dynamic Hand Motion Recognition Based on Transient and steady-State EMG signals

The results indicate that the recognition accuracy can be greatly improved and the detection delay of the motions can be significantly compressed in the transient stages of the hand motions.

Study of stability of time-domain features for electromyographic pattern recognition

Investigating the stability of time-domain EMG features during changes in the EMG signals and identifying the feature sets that would provide the most robust EMG pattern recognition and developing effective classifier training strategies are suggested to further improve the robustness of HMIs based on EMg pattern recognition.

Study of the SEMG probability distribution of the paretic tibialis anterior muscle

The surface electromyographic signal is a stochastic signal that has been modeled as a Gaussian process, with a zero mean. It has been experimentally proved that this probability distribution can be

The probability density function of vibromyographic and electromyographic signals for different levels of contraction of human quadriceps muscles

  • D.F. YuanY. ZhangW. Herzog
  • Engineering
    Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society
  • 1994
The probability density function (pdf) of random vibromyographic (VMG) and electromyographic (EMG) signals were studied. VMG and EMG signals were obtained from the quadriceps muscles of four subjects

Empirical copula-Based Templates to Recognize Surface EMG signals of Hand Motions

Comparison results have demonstrated that the proposed Empirical Copula-based methods can successfully classify different hand motions from different subjects with better recognition rates than Gaussian mixture models (GMMs).