Super Wavelet for sEMG Signal Extraction During Dynamic Fatiguing Contractions

In this research an algorithm was developed to classify muscle fatigue content from dynamic contractions, by using a genetic algorithm (GA) and a pseudo-wavelet function. Fatiguing dynamic contractions of the biceps brachii were recorded using Surface Electromyography (sEMG) from thirteen subjects. Labelling the signal into two classes (Fatigue and Non-Fatigue) aided in the training and testing phase. The genetic algorithm was used to develop a pseudo-wavelet function that can optimally decompose the sEMG signal and classify the fatigue content of the signal. The evolved pseudo wavelet was tuned using the decomposition of 70 % of the sEMG trials. 28 independent pseudo-wavelet evolution were run, after which the best run was selected and then tested on the remaining 30 % of the trials to measure the classification performance. Results show that the evolved pseudo-wavelet improved the classification rate of muscle fatigue by 4.45 percentage points to 14.95 percentage points when compared to other standard wavelet functions (p<0.05), giving an average correct classification of 87.90 %.

[1]  M. R. Al-Mulla,et al.  Classification of localized muscle fatigue with genetic programming on sEMG during isometric contraction , 2009, 2009 Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[2]  Carlo J. De Luca,et al.  Muscle Fatigue Monitor: A Noninvasive Device for Observing Localized Muscular Fatigue , 1982, IEEE Transactions on Biomedical Engineering.

[3]  M.R. Al-Mulla,et al.  Evolutionary computation extracts a super sEMG feature to classify localized muscle fatigue during dynamic contractions , 2012, 2012 4th Computer Science and Electronic Engineering Conference (CEEC).

[4]  Dinesh Kant Kumar,et al.  Wavelet analysis of surface electromyography , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[5]  M. R. Al-Mulla,et al.  Statistical Class Separation Using sEMG Features Towards Automated Muscle Fatigue Detection and Prediction , 2009, 2009 2nd International Congress on Image and Signal Processing.

[6]  Paolo Bonato,et al.  Time-frequency parameters of the surface myoelectric signal for assessing muscle fatigue during cyclic dynamic contractions , 2001, IEEE Transactions on Biomedical Engineering.

[7]  I. Cosic,et al.  Strategies to identify changes in SEMG due to muscle fatigue during cycling , 2005, 2005 IEEE Engineering in Medicine and Biology 27th Annual Conference.

[8]  Huosheng Hu,et al.  Manifestation of fatigue in myoelectric signals of dynamic contractions produced during playing PC games , 2008, 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.

[9]  Abdulhamit Subasi,et al.  Muscle Fatigue Detection in EMG Using Time–Frequency Methods, ICA and Neural Networks , 2009, Journal of Medical Systems.

[10]  Sabri Koçer,et al.  Classification of EMG Signals Using PCA and FFT , 2005, Journal of Medical Systems.

[11]  Francisco Sepulveda,et al.  Predicting the time to localized muscle fatigue using ANN and evolved sEMG feature , 2010, 2010 International Conference on Autonomous and Intelligent Systems, AIS 2010.

[12]  T. Masuda,et al.  Changes in surface EMG parameters during static and dynamic fatiguing contractions. , 1999, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[13]  M Hagberg,et al.  Work load and fatigue in repetitive arm elevations. , 1981, Ergonomics.

[14]  F. Sepulveda,et al.  A Novel Feature Assisting in the Prediction of sEMG muscle fatigue towards a wearable autonomous system , 2010, 2010 IEEE 16th International Mixed-Signals, Sensors and Systems Test Workshop (IMS3TW).

[15]  Zhizhong Wang,et al.  Classification of surface EMG signals using harmonic wavelet packet transform , 2006, Physiological measurement.

[16]  Francisco Sepulveda,et al.  An Autonomous Wearable System for Predicting and Detecting Localised Muscle Fatigue , 2011, Sensors.

[17]  Francisco Sepulveda,et al.  Novel Feature Modelling the Prediction and Detection of sEMG Muscle Fatigue towards an Automated Wearable System , 2010, Sensors.

[18]  Zbigniew Michalewicz,et al.  Genetic Algorithms + Data Structures = Evolution Programs , 1996, Springer Berlin Heidelberg.

[19]  F. Sepulveda,et al.  Cluster separation index suggests usefulness of non-motor EEG channels in detecting wrist movement direction intention , 2004, IEEE Conference on Cybernetics and Intelligent Systems, 2004..

[20]  Mehran Jahed,et al.  Real-time intelligent pattern recognition algorithm for surface EMG signals , 2007, Biomedical engineering online.

[21]  D. Farina,et al.  Geometrical factors in surface EMG of the vastus medialis and lateralis muscles. , 2000, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[22]  Mohammed R. Al-Mulla,et al.  Novel Pseudo-Wavelet Function for MMG Signal Extraction during Dynamic Fatiguing Contractions , 2014, Sensors.

[23]  Riccardo Poli,et al.  Detecting Localised Muscle Fatigue during Isometric Contraction using Genetic Programming , 2009, IJCCI.

[24]  N. Dimitrova,et al.  Muscle fatigue during dynamic contractions assessed by new spectral indices. , 2006, Medicine and science in sports and exercise.

[25]  Francisco Sepulveda,et al.  Evolved pseudo-wavelet function to optimally decompose sEMG for automated classification of localized muscle fatigue. , 2011, Medical engineering & physics.

[26]  Kurt Jørgensen,et al.  Electromyography and fatigue during prolonged, low-level static contractions , 2004, European Journal of Applied Physiology and Occupational Physiology.

[27]  M. Akay,et al.  Enhancement of spectral analysis of myoelectric signals during static contractions using wavelet methods , 1999, IEEE Transactions on Biomedical Engineering.

[28]  Guruprasad Madhavan,et al.  Electromyography: Physiology, Engineering and Non-Invasive Applications , 2005, Annals of Biomedical Engineering.

[29]  P J Sparto,et al.  Wavelet analysis of electromyography for back muscle fatigue detection during isokinetic constant-torque exertions. , 1999, Spine.

[30]  Roberto Merletti,et al.  Electromyography. Physiology, engineering and non invasive applications , 2005 .

[31]  Roberto Merletti,et al.  The extraction of neural strategies from the surface EMG. , 2004, Journal of applied physiology.

[32]  Min Chen,et al.  Enabling Fast Brain-Computer Interaction by Single-Trial Extraction of Visual Evoked Potentials , 2011, Journal of Medical Systems.

[33]  Dario Farina,et al.  Interpretation of the Surface Electromyogram in Dynamic Contractions , 2006, Exercise and sport sciences reviews.

[34]  James S. Walker,et al.  A Primer on Wavelets and Their Scientific Applications , 1999 .