Multifractal analysis of sEMG signals for fatigue assessment in dynamic contractions using Hurst exponents

Marri, Kiran; Swaminathan, Ramakrishnan

doi:10.1109/nebec.2015.7117117

Cited by 6 publications

(3 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The sEMG signals can be normalized using several methods such as amplitude, maximum voluntary contraction and time scale methods. In this study, the sEMG signals are normalized by dividing the time scale into six equal zones [22]. The first zone (Z1) and sixth zone (Z6) are considered as nonfatigue and fatigue condition respectively.…”

Section: Resultsmentioning

confidence: 99%

Fatigue Analysis of Triceps Brachii Muscle using sEMG Signals and Recurrence Quantification Technique

Marri¹,

Swaminathan²

2016

JOLST

Self Cite

View full text Add to dashboard Cite

Analysis of surface electromyography (sEMG) signals under fatigue conditions in dynamic contraction is gaining clinical relevance in the field of rehabilitation, ergonomics and sports performance. In this work, an attempt is made to analyze the sEMG signals recorded from triceps brachii muscles using Recurrence Quantification Analysis (RQA). The signals are recorded from 21 healthy adults during dynamic contraction involving dumbbell curl exercise. The sEMG signals are pre-processed and segmented into six equal zones along the time scale. The first zone and sixth zone are considered as nonfatigue and fatigue condition respectively. The signals are then subjected to RQA for further analysis. Two standard RQA features namely determinism (DET) and maximum length of the vertical line (V MAX) are computed for analyzing nonfatigue and fatigue conditions. A new RQA feature known as complexity (CPX) is also introduced for sEMG signal analysis that is derived from determinism. The results of RQA features are statistically verified using ANOVA. All the three RQA features namely, DET, complexity and V MAX are found to be statistically highly significant. In the case of fatigue condition, DET and V MAX increased by 17% and 30% respectively. It appears that RQA method may be a useful technique in differentiating fatigue and nonfatigue conditions under varied dynamic muscle contractions. 

show abstract

Section: Resultsmentioning

confidence: 99%

Fatigue Analysis of Triceps Brachii Muscle using sEMG Signals and Recurrence Quantification Technique

Marri¹,

Swaminathan²

2016

JOLST

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this classification pipeline, we first compute the mean absolute value, root mean square, maximum absolute amplitude, waveform length, zerocrossings, slope sign changes, and maximum fractal length, as these features were some of the most reported time domain features in the literature (Oskoei and Hu, 2008;Tkach et al, 2010;Ahsan et al, 2011;Phinyomark et al, 2012;Balbinot and Favieiro, 2013;Daud et al, 2013;Al-Angari et al, 2016). Additionally, we compute the Kurtosis (Nazarpour et al, 2013) as a robust measure of signal non-Gaussianity, the Hurst exponent (Marri and Swaminathan, 2015) as a measure of chaos, or unpredictability, in the EMG signal, and Sample Entropy (Zhang and Zhou, 2012;Gao et al, 2015) as a measure of the complexity of a physiological time series (Richman and Moorman, 2000).…”

Section: Pipeline Based On Standard Signal Processing Featuresmentioning

confidence: 99%

Machine learning for hand pose classification from phasic and tonic EMG signals during bimanual activities in virtual reality

Simar,

Colot,

Cebolla

et al. 2024

Front. Neurosci.

View full text Add to dashboard Cite

Myoelectric prostheses have recently shown significant promise for restoring hand function in individuals with upper limb loss or deficiencies, driven by advances in machine learning and increasingly accessible bioelectrical signal acquisition devices. Here, we first introduce and validate a novel experimental paradigm using a virtual reality headset equipped with hand-tracking capabilities to facilitate the recordings of synchronized EMG signals and hand pose estimation. Using both the phasic and tonic EMG components of data acquired through the proposed paradigm, we compare hand gesture classification pipelines based on standard signal processing features, convolutional neural networks, and covariance matrices with Riemannian geometry computed from raw or xDAWN-filtered EMG signals. We demonstrate the performance of the latter for gesture classification using EMG signals. We further hypothesize that introducing physiological knowledge in machine learning models will enhance their performances, leading to better myoelectric prosthesis control. We demonstrate the potential of this approach by using the neurophysiological integration of the “move command" to better separate the phasic and tonic components of the EMG signals, significantly improving the performance of sustained posture recognition. These results pave the way for the development of new cutting-edge machine learning techniques, likely refined by neurophysiology, that will further improve the decoding of real-time natural gestures and, ultimately, the control of myoelectric prostheses.

show abstract

“…In practice such multifractal analysis is extended as well on non-integer 2q, negative q and zero q. For such multi-fractal scaling in financial data see [7], in computer network traffic data see [91,92], in image analysis see [93] while in biomedical data see [94]. Remark 2.1.3.…”

Section: Scaling Approachmentioning

confidence: 99%

Selected Methods for non-Gaussian Data Analysis

Domino

2018

Preprint

View full text Add to dashboard Cite

Multifractal analysis of sEMG signals for fatigue assessment in dynamic contractions using Hurst exponents

Cited by 6 publications

References 11 publications

Fatigue Analysis of Triceps Brachii Muscle using sEMG Signals and Recurrence Quantification Technique

Fatigue Analysis of Triceps Brachii Muscle using sEMG Signals and Recurrence Quantification Technique

Machine learning for hand pose classification from phasic and tonic EMG signals during bimanual activities in virtual reality

Selected Methods for non-Gaussian Data Analysis

Contact Info

Product

Resources

About