A Laplacian-Gaussian Mixture Model for Surface EMG Signals from Upper Limbs

Kusuru, Durgesh; Turlapaty, Anish C.; Thakur, Mainak

doi:10.1109/embc46164.2021.9630143

Cited by 2 publications

(12 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Knowledge of the EMG signal filling process is of great value in prosthesis control, where analysis of the EMG signal is extensively applied [1], [2], [3] in order to determine the intended degree of muscle activation [4], [5]. One of the main limitations for robust control is related to the stochastic behaviour of the signals [6], and reliable modelling of the EMG signal as a random process is found to be be useful in these applications [7], [8], [9], [10], [11]. Another important application of EMG recruitment analysis deals with motor unit (MU) firing pattern extraction [1] and its use in the investigation of neural drive strategies [5].…”

Section: Emg Probability Density Function: a New Way To Look At Emg S...mentioning

confidence: 99%

“…In this scenario, the EMG signal can be modelled as a Gaussian random process with a band-limited power spectral density [23]. However, there is evidence that the EMG signal is not a Gaussian random process when the level of contraction is low [9], [11], [18], [19], [20], [21] and few MUs have been recruited [24], that is, before the interference pattern is completely formed [15]. To our knowledge, there is no published derivation of the complete EMG PDF from minimum to maximum contraction or description of why, in terms of EMG signal generation, the distribution changes its characteristics as force increases.…”

Section: Emg Probability Density Function: a New Way To Look At Emg S...mentioning

confidence: 99%

“…While this model provides a simple and accurate description of the EMG signal in the time domain [23], [34], it does not help us to understand the characteristics of EMG PDF. In some approximations [23], the EMG signal has been modelled as a Gaussian noise process subject to the application of the central limit theorem when the number of active MUs is large enough; while this approach may reflect reality for high-contraction recordings, it does not explain the EMG PDF under low and moderate levels of muscle contraction [7], [9], [11], [22].…”

Section: A Emg Convolutional Modelmentioning

confidence: 99%

“…Another important observation about the iterated convolution terms in (11) is that, while it is correct to assert that the support of the PDF after the convolution is the summation of the supports of the convolved PDFs, the more terms that are included in the convolution, the more the resulting distribution tends to get smoothed out and tends to concentrate around its central values (the distribution tends to acquire a Gaussianlike shape).This effect is commonly known as EMG amplitude cancellation.…”

Section: B Derivation Of the Emg Probability Density Functionmentioning

confidence: 99%

“…Calculation of the moments of the folded distribution of the EMG stem from (11), after folding each of the linearly combined distributions. To be precise,…”

Section: Emg Filling Factormentioning

confidence: 99%

See 4 more Smart Citations

EMG Probability Density Function: A New Way to Look at EMG Signal Filling From Single Motor Unit Potential to Full Interference Pattern

Navallas

Eciolaza

Mariscal

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

An analytical derivation of the EMG signal's amplitude probability density function (EMG PDF) is presented and used to study how an EMG signal buildsup, or fills, as the degree of muscle contraction increases. The EMG PDF is found to change from a semi-degenerate distribution to a Laplacian-like distribution and finally to a Gaussian-like distribution. We present a measure, the EMG filling factor, to quantify the degree to which an EMG signal has been built-up. This factor is calculated from the ratio of two non-central moments of the rectified EMG signal. The curve of the EMG filling factor as a function of the mean rectified amplitude shows a progressive and mostly linear increase during early recruitment, and saturation is observed when the EMG signal distribution becomes approximately Gaussian. Having presented the analytical tools used to derive the EMG PDF, we demonstrate the usefulness of the EMG filling factor and curve in studies with both simulated signals and real signals obtained from the tibialis anterior muscle of 10 subjects. Both simulated and real EMG filling curves start within the 0.2 to 0.35 range and rapidly rise towards 0.5 (Laplacian) before stabilizing at around 0.637 (Gaussian). Filling curves for the real signals consistently followed this pattern (100% repeatability within trials in 100% of the subjects). The theory of EMG signal filling derived in this work provides (a) an analytically consistent derivation of the EMG PDF as a function of motor unit potentials and motor unit firing patterns; (b) an explanation of the change in the EMG PDF according to degree of muscle contraction; and (c) a way (the EMG filling factor) to quantify the degree to which an EMG signal has been built-up.

show abstract

Section: Emg Probability Density Function: a New Way To Look At Emg S...mentioning

confidence: 99%

Section: Emg Probability Density Function: a New Way To Look At Emg S...mentioning

confidence: 99%

Section: A Emg Convolutional Modelmentioning

confidence: 99%

Section: B Derivation Of the Emg Probability Density Functionmentioning

confidence: 99%

“…Calculation of the moments of the folded distribution of the EMG stem from (11), after folding each of the linearly combined distributions. To be precise,…”

Section: Emg Filling Factormentioning

confidence: 99%

See 3 more Smart Citations

EMG Probability Density Function: A New Way to Look at EMG Signal Filling From Single Motor Unit Potential to Full Interference Pattern

Navallas

Eciolaza

Mariscal

et al. 2023

IEEE Trans. Neural Syst. Rehabil. Eng.

View full text Add to dashboard Cite

show abstract

Unveiling EMG semantics: a prototype-learning approach to generalizable gesture classification

Lee,

Jiang,

Yang

et al. 2024

J. Neural Eng.

View full text Add to dashboard Cite

Upper limb loss can profoundly impact an individual's quality of life, posing challenges to both physical capabilities and emotional well-being. To restore limb function by decoding electromyography (EMG) signals, in this paper, we present a novel deep prototype learning method for accurate and generalizable EMG-based gesture classification. Existing methods suffer from limitations in generalization across subjects due to the diverse nature of individual muscle responses, impeding seamless applicability in broader populations. By leveraging deep prototype learning, we introduce a method that goes beyond direct output prediction. Instead, it matches new EMG inputs to a set of learned prototypes and predicts the corresponding labels. This novel methodology significantly enhances the model's classification performance and generalizability by discriminating subtle differences between gestures, making it more reliable and precise in real-world applications. Our experiments on four Ninapro datasets suggest that our deep prototype learning classifier outperforms state-of-the-art methods in terms of intra-subject and inter-subject classification accuracy in gesture prediction. The results from our experiments validate the effectiveness of the proposed method and pave the way for future advancements in the field of EMG gesture classification for upper limb prosthetics.

show abstract

A Laplacian-Gaussian Mixture Model for Surface EMG Signals from Upper Limbs

Cited by 2 publications

References 8 publications

EMG Probability Density Function: A New Way to Look at EMG Signal Filling From Single Motor Unit Potential to Full Interference Pattern

EMG Probability Density Function: A New Way to Look at EMG Signal Filling From Single Motor Unit Potential to Full Interference Pattern

Unveiling EMG semantics: a prototype-learning approach to generalizable gesture classification

Contact Info

Product

Resources

About