Surface electromyography based muscle fatigue detection using high-resolution time-frequency methods and machine learning algorithms

BACKGROUND AND OBJECTIVE Surface electromyography (sEMG) based muscle fatigue research is widely preferred in sports science and occupational/rehabilitation studies due to its noninvasiveness. However, these signals are complex, multicomponent and highly nonstationary with large inter-subject variations, particularly during dynamic contractions. Hence, time-frequency based machine learning methodologies can improve the design of automated system for these signals. METHODS In this work, the analysis based on high-resolution time-frequency methods, namely, Stockwell transform (S-transform), B-distribution (BD) and extended modified B-distribution (EMBD) are proposed to differentiate the dynamic muscle nonfatigue and fatigue conditions. The nonfatigue and fatigue segments of sEMG signals recorded from the biceps brachii of 52 healthy volunteers are preprocessed and subjected to S-transform, BD and EMBD. Twelve features are extracted from each method and prominent features are selected using genetic algorithm (GA) and binary particle swarm optimization (BPSO). Five machine learning algorithms, namely, naïve Bayes, support vector machine (SVM) of polynomial and radial basis kernel, random forest and rotation forests are used for the classification. RESULTS The results show that all the proposed time-frequency distributions (TFDs) are able to show the nonstationary variations of sEMG signals. Most of the features exhibit statistically significant difference in the muscle fatigue and nonfatigue conditions. The maximum number of features (66%) is reduced by GA and BPSO for EMBD and BD-TFD respectively. The combination of EMBD- polynomial kernel based SVM is found to be most accurate (91% accuracy) in classifying the conditions with the features selected using GA. CONCLUSIONS The proposed methods are found to be capable of handling the nonstationary and multicomponent variations of sEMG signals recorded in dynamic fatiguing contractions. Particularly, the combination of EMBD- polynomial kernel based SVM could be used to detect the dynamic muscle fatigue conditions.

[1]  P. A. Karthick,et al.  Analysis of Muscle Fatigue Progression using Cyclostationary Property of Surface Electromyography Signals , 2015, Journal of Medical Systems.

[2]  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.

[3]  Tae-Seong Kim,et al.  An efficient word typing P300-BCI system using a modified T9 interface and random forest classifier , 2015, Comput. Biol. Medicine.

[4]  S. Ramakrishnan,et al.  Extraction and analysis of multiple time window features associated with muscle fatigue conditions using sEMG signals , 2014, Expert Syst. Appl..

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

[6]  Abdulhamit Subasi,et al.  Breast cancer diagnosis using GA feature selection and Rotation Forest , 2015, Neural Computing and Applications.

[7]  M. Zwarts,et al.  Clinical neurophysiology of fatigue , 2008, Clinical Neurophysiology.

[8]  Jasmin Kevric,et al.  Epileptic seizure detection using hybrid machine learning methods , 2017, Neural Computing and Applications.

[9]  Weidong Zhou,et al.  Automatic seizure detection using Stockwell transform and boosting algorithm for long-term EEG , 2015, Epilepsy & Behavior.

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

[11]  G V Dimitrov,et al.  Fatigue analysis of interference EMG signals obtained from biceps brachii during isometric voluntary contraction at various force levels. , 2009, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[12]  Boualem Boashash,et al.  Time-Frequency Signal Analysis and Processing: A Comprehensive Reference , 2015 .

[13]  Boualem Boashash,et al.  Passive detection of accelerometer-recorded fetal movements using a time-frequency signal processing approach , 2014, Digit. Signal Process..

[14]  B. Polus,et al.  Strategies to identify changes in SEMG due to muscle fatigue during cycling , 2005, Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference.

[15]  Boualem Boashash,et al.  Evaluation of the modified S-transform for time-frequency synchrony analysis and source localisation , 2012, EURASIP J. Adv. Signal Process..

[16]  A Malanda,et al.  EMG spectral indices and muscle power fatigue during dynamic contractions. , 2010, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

[17]  Jian Zhang,et al.  Classifying Lower Extremity Muscle Fatigue During Walking Using Machine Learning and Inertial Sensors , 2013, Annals of Biomedical Engineering.

[18]  Boualem Boashash,et al.  Principles of time-frequency feature extraction for change detection in non-stationary signals: Applications to newborn EEG abnormality detection , 2015, Pattern Recognit..

[19]  Mario Cifrek,et al.  Surface EMG based muscle fatigue evaluation in biomechanics. , 2009, Clinical biomechanics.

[20]  A. Galbis,et al.  Phase information of time-frequency transforms as a key feature for classification of atrial fibrillation episodes. , 2015, Physiological measurement.

[21]  M. Knaflitz,et al.  Assessment of muscle fatigue during biking , 2003, IEEE Transactions on Neural Systems and Rehabilitation Engineering.

[22]  Lalu Mansinha,et al.  Localization of the complex spectrum: the S transform , 1996, IEEE Trans. Signal Process..

[23]  Oguz Findik,et al.  A comparison of feature selection models utilizing binary particle swarm optimization and genetic algorithm in determining coronary artery disease using support vector machine , 2010, Expert Syst. Appl..

[24]  John M. O'Toole,et al.  Time-Frequency Processing of Nonstationary Signals: Advanced TFD Design to Aid Diagnosis with Highlights from Medical Applications , 2013, IEEE Signal Processing Magazine.

[25]  Braham Barkat,et al.  A high-resolution quadratic time-frequency distribution for multicomponent signals analysis , 2001, IEEE Trans. Signal Process..

[26]  Boualem Boashash,et al.  Automatic signal abnormality detection using time-frequency features and machine learning: A newborn EEG seizure case study , 2016, Knowl. Based Syst..

[27]  Kiran Marri,et al.  Classification of Muscle Fatigue in Dynamic Contraction Using Surface Electromyography Signals and Multifractal Singularity Spectral Analysis , 2016 .

[28]  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.

[29]  Swaminathan Ramakrishnan,et al.  A Binary Bat Approach for Identification of Fatigue Condition from sEMG Signals , 2014, SEMCCO.

[30]  Boualem Boashash,et al.  Design of a high-resolution separable-kernel quadratic TFD for improving newborn health outcomes using fetal movement detection , 2012, 2012 11th International Conference on Information Science, Signal Processing and their Applications (ISSPA).

[31]  U. Rajendra Acharya,et al.  Classification of Epilepsy Using High-Order Spectra Features and Principle Component Analysis , 2012, Journal of Medical Systems.

[32]  Muscle fatigue analysis using surface EMG signals and time–frequency based medium-to-low band power ratio , 2016 .

[33]  Francisco Sepulveda,et al.  A Review of Non-Invasive Techniques to Detect and Predict Localised Muscle Fatigue , 2011, Sensors.

[34]  P. A. Karthick,et al.  Surface electromyography based muscle fatigue progression analysis using modified B distribution time-frequency features , 2016, Biomed. Signal Process. Control..

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

[36]  Kiran Marri,et al.  Classification of muscle fatigue using surface electromyography signals and multifractals , 2015, 2015 12th International Conference on Fuzzy Systems and Knowledge Discovery (FSKD).

[37]  Engin Avci,et al.  A new intelligent diagnosis system for the heart valve diseases by using genetic-SVM classifier , 2009, Expert Syst. Appl..

[38]  Daniel R. Rogers,et al.  EMG-based muscle fatigue assessment during dynamic contractions using principal component analysis. , 2011, Journal of electromyography and kinesiology : official journal of the International Society of Electrophysiological Kinesiology.

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

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