Statistical Class Separation Using sEMG Features Towards Automated Muscle Fatigue Detection and Prediction

Almulla, Mohammed; Sepúlveda, Francisco; Colley, Martin; Al‐Mulla, Fahd

doi:10.1109/cisp.2009.5304091

Cited by 27 publications

(38 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reading of the goniometer was later compared with the sEMG signal to ensure that fatigue took place within the recorded sEMG. The goniometer provided a reliable indication on the development of fatigue: classical biceps muscle fatigue onset for healthy individuals usually manifests itself by small elbow angle oscillations followed by a difficulty in maintain a task [9,10,12], 90 • in our case. For each of the ten subjects three trials were carried out, providing 30 trials in total, 20 of which were used for training the GA and 10 for testing.…”

Section: Data Recording and Pre-processingmentioning

confidence: 99%

“…In that study, the GP evolved a composite feature using primitive sets (Median, Mean, Average deviation, Standard deviation, Variance, RMS, Skew, Kurtosis, Entropy) to detect fatigue, whereas in the present paper a Genetic Algorithm (GA) evolves a pseudo-wavelet that improves classification accuracy regardless of the type of classifier. Another previous study investigated the possibility of differentiating the three classes of muscle fatigue (Non-Fatigue, Transition-to-Fatigue and Fatigue) using nine different sEMG muscle fatigue related features for the separation of classes [10]. That study reached discrimination between the three classes at 81.81% true positive rate.…”

Section: Introductionmentioning

confidence: 96%

See 1 more Smart Citation

Evolved pseudo-wavelet function to optimally decompose sEMG for automated classification of localized muscle fatigue

Almulla

Sepúlveda

Colley

2011

Medical Engineering & Physics

Self Cite

View full text Add to dashboard Cite

Section: Data Recording and Pre-processingmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 96%

Evolved pseudo-wavelet function to optimally decompose sEMG for automated classification of localized muscle fatigue

Almulla

Sepúlveda

Colley

2011

Medical Engineering & Physics

Self Cite

View full text Add to dashboard Cite

“…These include genetic programming and genetic algorithms [14][15][16][17], statistical analysis [18][19][20], as well as classification methods to predict fatigue by using neural networks [21] or linear discriminant analysis (LDA) [22]. A variation of these techniques have been adapted in this research to evolve a pseudo-wavelet for classifying fatigue content in the MMG signal.…”

Section: Introductionmentioning

confidence: 99%

Optimal Elbow Angle for MMG Signal Classification of Biceps Brachii during Dynamic Fatiguing Contraction

Almulla

Sepúlveda

Suoud

2015

Bioinformatics and Biomedical Engineering

View full text Add to dashboard Cite

Abstract. Mechanomyography (MMG) activity of the biceps muscle was recorded from thirteen subjects. Data was recorded while subjects performed dynamic contraction until fatigue. The signals were segmented into two parts (Non-Fatigue and Fatigue), An evolutionary algorithm was used to determine the elbow angles that best separate (using DBi) both Non-Fatigue and Fatigue segments of the MMG signal. Establishing the optimal elbow angle for feature extraction used in the evolutionary process was based on 70% of the conducted MMG trials. After completing twenty-six independent evolution runs, the best run containing the best elbow angles for separation (fatigue and non-fatigue) was selected and then tested on the remaining 30% of the data to measure the classification performance. Testing the performance of the optimal angle was undertaken on eight features that where extracted from each of the two classes (non-fatigue and fatigue) to quantify the performance. Results show that the elbow angles produced by the Genetic algorithm can be used for classification showing 80.64% highest correct classification for one of the features and on average of all eight features including worst performing features giving 66.50%.

show abstract

“…Numerous researchers have used various muscle fatigue classification methods from sEMG signals, e.g., genetic programming and genetic algorithms [20][21][22][23], statistical analysis [24][25][26], in addition to classification techniques for fatigue detection by using neural networks [27] and linear discriminant analysis (LDA) [28]. A variation of these techniques have been tailored in this study where our GA uses a pseudo-wavelet as the feature extraction technique to determine the optimal elbow angles which best separate between fatigue and non-fatigue segments of the sEMG signal emanating from fatiguing dynamic contractions.…”

Section: Introductionmentioning

confidence: 99%

Optimal Elbow Angle for Extracting sEMG Signals During Fatiguing Dynamic Contraction

2015

View full text Add to dashboard Cite

Surface electromyographic (sEMG) activity of the biceps muscle was recorded from 13 subjects. Data was recorded while subjects performed dynamic contraction until fatigue and the signals were segmented into two parts (Non-Fatigue and Fatigue). An evolutionary algorithm was used to determine the elbow angles that best separate (using Davies-Bouldin Index, DBI) both Non-Fatigue and Fatigue segments of the sEMG signal. Establishing the optimal elbow angle for feature extraction used in the evolutionary process was based on 70% of the conducted sEMG trials. After completing 26 independent evolution runs, the best run containing the optimal elbow angles for separation (Non-Fatigue and Fatigue) was selected and then tested on the remaining 30% of the data to measure the classification performance. Testing the performance of the optimal angle was undertaken on nine features extracted from each of the two classes (Non-Fatigue and Fatigue) to quantify the performance. Results showed that the optimal elbow angles can be used for fatigue classification, showing 87.90% highest correct classification for one of the features and on average of all eight features (including worst performing features) giving 78.45%.

show abstract

Statistical Class Separation Using sEMG Features Towards Automated Muscle Fatigue Detection and Prediction

Cited by 27 publications

References 12 publications

Evolved pseudo-wavelet function to optimally decompose sEMG for automated classification of localized muscle fatigue

Evolved pseudo-wavelet function to optimally decompose sEMG for automated classification of localized muscle fatigue

Optimal Elbow Angle for MMG Signal Classification of Biceps Brachii during Dynamic Fatiguing Contraction

Optimal Elbow Angle for Extracting sEMG Signals During Fatiguing Dynamic Contraction

Contact Info

Product

Resources

About