Muscular fatigue detection using sEMG in dynamic contractions

Bueno, Diana R.; Lizano, J.M.; Montano, Luis

doi:10.1109/embc.2015.7318407

Cited by 7 publications

(3 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Compared to studies that just compared the difference in the development of muscle fatigue between relatively high intensity and low intensity muscle contraction (Kuorinka, 1988), this finding gives an insight into the importance of continuous changes of muscle fatigue values following changes of muscle load intensity. In the previous study, repetitive elbow flexion/extension motion using a 1kg dumbbell was reported to occur fatigue on the biceps brachii muscle (Bueno, Lizano, & Montano, 2015). However, in the current study, it was found that biceps brachii muscle recovers from fatigue while conducting elbow flexion and extension using a 1kg load lowered from 2kg.…”

Section: Detection Of Development and Recovery Of Muscle Fatiguecontrasting

confidence: 75%

Monitoring muscle fatigue following continuous load changes

Yoon

Shin

2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

Human-Robot collaboration (HRC) have been actively applied in industry in a form of interactacting with workers by detecting their muscle fatigue. During repetitive movements such as dynamic muscle contractions, the information of decrement of electromyography (EMG) center frequency can suggest muscle fatigue occurred. However, the method was not evaluated both for development and recovery of muscle fatigue during such dynamic situations. If the decrement can be detected during the work without interruptions, the method can be highly useful in the industry. This study aims to confirm validity of the dynamic fatigue evaluation method using the wavelet transform in both direction of fatigue (development and recovery) by varying load intensity. Seventeen healthy males conducted four sets of repetitive elbow flexion-extension exertions work with one set of 2-minute work with a 2 kg weight (‘heavy work’) and then another with an 1 kg weight (‘light work’). Muscle fatigue was quantified by calculating the EMG center frequency from dynamic evaluation and static evaluation for each set of exertion work task. In the result, the EMG center frequency was significantly decreased during every ‘heavy work’ and increased during every ‘light work’, which was consistent with the result from dynamic fatigue evaluation based on the wavelet transform. The result suggests the possibility of monitoring muscle fatigue in real-time in industry and providing a guideline in designing a human-robot interaction system.

show abstract

Section: Detection Of Development and Recovery Of Muscle Fatiguecontrasting

confidence: 75%

Monitoring muscle fatigue following continuous load changes

Yoon

Shin

2020

Proceedings of the Human Factors and Ergonomics Society Annual

View full text Add to dashboard Cite

show abstract

“…Also, they compared the classification and prediction results of drivers' driving state by means of linear discriminant analysis, KNN, support vector machine and other algorithms. Dr. Bueno [16] et al studied the EMG signal indexes related to fatigue, including the average rating rate (MNF), median frequency, Dimitrov spectrum index, root mean square, and zero crossing detection. The model is established on the basis of Gaussian mixture model technology.…”

Section: Drowsiness Detection Methods Based On Physiological Signalmentioning

confidence: 99%

Two-Stream Spatial–Temporal Transformer Networks For Driver Drowsiness Detection

Qianyi Jiang,

Huahu Xu

2023

Journal of Computers

View full text Add to dashboard Cite

<p>For driver drowsiness detection in the real world, the existing methods have good performance in general. However, when the face is blocked, the light is dim, and the driver’s head posture changes, the performance will deteriorate significantly. In this paper, a two-stream Spatial-Temporal transformer network intended to perform diver drowsiness detection task is proposed to solve the above problems. The spatial-temporal graph is extracted from the video and then the results are obtained from 2s-STTN. The model is a two-stream transformer network model. In our model, the Spatial Self-Attention module is used to learn the embedding of different facial landmarks, and the Temporal Self-Attention module is used to learn the correlation between the frames of facial feature points. Different activated facial landmarks are separated and recognized by class activation mapping technology. Each flow recognizes different activated facial features, extracts spatial or temporal features, and integrates the information about facial features, so as to improve the performance of the system. 2s-STTN can not only mine the long-term dependence of driver behavior from video, but also mine the driver drowsiness information provided by the unobstructed facial signs when the face is blocked. By conducting experiments and comparing our model with other models, it is demonstrated that the proposed model has good performance in driver drowsiness detection.</p> <p> </p>

show abstract

“…Currently, it is understood that muscle fatigue can be measured in several ways. An increase in the Root Mean Square (RMS) of the EMG during a fatiguing task is directly related to the recruitment of additional motor units while performing the task ( 29 ). Similarly, the time-domain increase in EMG peak amplitude during submaximal fatiguing contractions has similar increasing trends during additional motor unit recruitment up to a maximal fatiguing state ( 30 ).…”

Section: Introductionmentioning

confidence: 99%

Rate of change in longitudinal EMG indicates time course of an individual's neuromuscular adaptation in resistance-based muscle training

Stefanovic

Ramanarayanan²,

Karkera³

et al. 2022

Front. Rehabilit. Sci.

View full text Add to dashboard Cite

An individual's long-term neuromuscular adaptation can be measured through time-domain analyses of surface electromyograms (EMG) in regular resistance-based training. The perceived changes in recruitment, such as those measured during muscle fatigue, can subsequently prolong the recovery time in rehabilitation applications. Thus, by developing quantifiable methods for measuring neuromuscular adaptation, adjuvant treatments applied during neurorehabilitation can be improved to reduce recovery times and to increase patient quality of care. This study demonstrates a novel time-domain analysis of long-term changes in EMG captured neuromuscular activity that we aim to use to develop a quantified performance metric for muscle-based intervention training and optimization of an individual. We measure EMG of endurance and hypertrophy-based resistance exercises of healthy participants over 100 days to identify trends in long-term neuromuscular adaptation. Particularly, we show that the rate of EMG amplitude increase (motor recruitment) is dependent on the training modality of an individual. Particularly, EMG decreases over time with repetitive training – but the rate of decrease is different in hypertrophy, endurance, and control exercises. We found that the EMG peak contraction decreases across all subjects, on average, by 8.23 dB during hypertrophy exercise and 10.09 dB for endurance exercises over 100 days of training, while control participants showed negligible change. This represents approximately 2 dB difference EMG activity when comparing endurance and hypertrophy exercises, and >8 dB change when comparing to our control cases. As such, we show that the slope of the long-term EMG activity is related to the resistance-based exercise. We believe this can be used to identify person-specific performance metrics, and to create optimized interventions using a measured performance baseline of an individual.

show abstract

Muscular fatigue detection using sEMG in dynamic contractions

Cited by 7 publications

References 7 publications

Monitoring muscle fatigue following continuous load changes

Monitoring muscle fatigue following continuous load changes

Two-Stream Spatial–Temporal Transformer Networks For Driver Drowsiness Detection

Rate of change in longitudinal EMG indicates time course of an individual's neuromuscular adaptation in resistance-based muscle training

Contact Info

Product

Resources

About