0
Research Papers

Classification of Muscle Fatigue in Dynamic Contraction Using Surface Electromyography Signals and Multifractal Singularity Spectral Analysis

[+] Author and Article Information
Kiran Marri

Non Invasive Imaging and Diagnostics Lab,
Biomedical Engineering Group,
Department of Applied Mechanics,
Indian Institute of Technology Madras,
Chennai 600 036, India
e-mail: kirankmr@gmail.com

Ramakrishnan Swaminathan

Non Invasive Imaging and Diagnostics Lab,
Biomedical Engineering Group,
Department of Applied Mechanics,
Indian Institute of Technology Madras,
Chennai 600 036, India
e-mail: sramki@iitm.ac.in

1Corresponding author.

Contributed by the Dynamic Systems Division of ASME for publication in the JOURNAL OF DYNAMIC SYSTEMS, MEASUREMENT, AND CONTROL. Manuscript received October 5, 2015; final manuscript received February 23, 2016; published online July 15, 2016. Assoc. Editor: Hashem Ashrafiuon.

J. Dyn. Sys., Meas., Control 138(11), 111008 (Jul 15, 2016) (10 pages) Paper No: DS-15-1483; doi: 10.1115/1.4033832 History: Received October 05, 2015; Revised February 23, 2016

Muscle fatigue is a neuromuscular condition experienced during daily activities. This phenomenon is generally characterized using surface electromyography (sEMG) signals and has gained a lot of interest in the fields of clinical rehabilitation, prosthetics control, and sports medicine. sEMG signals are complex, nonstationary and also exhibit self-similarity fractal characteristics. In this work, an attempt has been made to differentiate sEMG signals in nonfatigue and fatigue conditions during dynamic contraction using multifractal analysis. sEMG signals are recorded from biceps brachii muscles of 42 healthy adult volunteers while performing curl exercise. The signals are preprocessed and segmented into nonfatigue and fatigue conditions using the first and last curls, respectively. The multifractal detrended moving average algorithm (MFDMA) is applied to both segments, and multifractal singularity spectrum (SSM) function is derived. Five conventional features are extracted from the singularity spectrum. Twenty-five new features are proposed for analyzing muscle fatigue from the multifractal spectrum. These proposed features are adopted from analysis of sEMG signals and muscle fatigue studies performed in time and frequency domain. These proposed 25 feature sets are compared with conventional five features using feature selection methods such as Wilcoxon rank sum, information gain (IG) and genetic algorithm (GA) techniques. Two classification algorithms, namely, k-nearest neighbor (k-NN) and logistic regression (LR), are explored for differentiating muscle fatigue. The results show that about 60% of the proposed features are statistically highly significant and suitable for muscle fatigue analysis. The results also show that eight proposed features ranked among the top 10 features. The classification accuracy with conventional features in dynamic contraction is 75%. This accuracy improved to 88% with k-NN-GA combination with proposed new feature set. Based on the results, it appears that the multifractal spectrum analysis with new singularity features can be used for clinical evaluation in varied neuromuscular conditions, and the proposed features can also be useful in analyzing other physiological time series.

FIGURES IN THIS ARTICLE
<>
Copyright © 2016 by ASME
Your Session has timed out. Please sign back in to continue.

References

Dutta, S. , Ghosh, D. , Samanta, S. , and Dey, S. , 2014, “ Multifractal Parameters as an Indication of Different Physiological and Pathological States of the Human Brain,” Physica A, 396, pp. 155–163. [CrossRef]
Merletti, R. , and Farina, D. , 2009, “ Analysis of Intramuscular Electromyogram Signals,” Philos. Trans. A, 367(1887), pp. 357–368. [CrossRef]
Merletti, R. , and Parker, P. A. , 2004, Electromyography: Physiology, Engineering, and Non-Invasive Applications, Wiley, Hoboken, NJ.
Phinyomark, A. , Phukpattaranont, P. , and Limsakul, C. , 2012, “ Feature Reduction and Selection for EMG Signal Classification,” Expert Syst. Appl., 39(8), pp. 7420–7431. [CrossRef]
Barry, B. K. , and Enoka, R. M. , 2007, “ The Neurobiology of Muscle Fatigue: 15 Years Later,” Integr. Comput. Biol., 47(4), pp. 465–473. [CrossRef]
Hug, F. , 2011, “ Can Muscle Coordination be Precisely Studied by Surface Electromyography?,” J. Electromyogr. Kinesiol., 21(1), pp. 1–12. [CrossRef] [PubMed]
Merletti, R. , and Farina, D. , 2008, “ Surface EMG Processing: Introduction to the Special Issue,” Biomed. Signal Process. Control, 3(2), pp. 115–117. [CrossRef]
Kumar, D. K. , Arjunan, S. P. , and Naik, G. R. , 2011, “ Measuring Increase in Synchronization to Identify Muscle Endurance Limit,” IEEE Trans. Neural Syst. Rehabil. Eng., 19(5), pp. 578–587. [CrossRef] [PubMed]
Pereira, G. R. , de Oliveira, L. F. , and Nadal, J. , 2013, “ Reducing Cross Terms Effects in the Choi–Williams Transform of Mioelectric Signals,” Comput. Methods Programs Biomed., 111(3), pp. 685–692. [CrossRef] [PubMed]
Venugopal, G. , and Ramakrishnan, S. , 2014, “ Analysis of Progressive Changes Associated With Muscle Fatigue in Dynamic Contraction of Biceps Brachii Muscle Using Surface EMG Signals and Bispectrum Features,” Biomed. Eng. Lett., 4(3), pp. 269–276. [CrossRef]
González-Izal, M. , Malanda, A. , Gorostiaga, E. , and Izquierdo, M. , 2012, “ Electromyographic Models to Assess Muscle Fatigue,” J. Electromyogr. Kinesiol., 22(4), pp. 501–512. [CrossRef] [PubMed]
Kantelhardt, J. W. , Zschiegner, S. A. , Koscielny-bunde, E. , Havlin, S. , Bunde, A. , and Stanley, H. E. , 2002, “ Multifractal Detrended Fluctuation Analysis of Nonstationary Time Series,” Phys. A Stat. Mech. Appl., 316, pp. 87–114. [CrossRef]
Alessio, E. , Carbone, A. , Castelli, G. , and Frappietro, V. , 2002, “ Second-Order Moving Average and Scaling of Stochastic Time,” Eur. Phys. J. B, 27(2), pp. 197–200.
Gu, G.-F. , and Zhou, W.-X. , 2010, “ Detrending Moving Average Algorithm for Multifractals,” Phys. Rev. E, 82(1), p. 11136. [CrossRef]
Ghosh, D. , Dutta, S. , and Chakraborty, S. , 2014, “ Multifractal Detrended Cross-Correlation Analysis for Epileptic Patient in Seizure and Seizure Free Status,” Chaos Solitons Fractals, 67, pp. 1–10. [CrossRef]
Ghosh, D. , Dutta, S. , and Samanta, S. , 2012, “ Fluctuation of Gold Price: A Multifractal Approach,” Acta Phys. Pol. B, 43(6), pp. 1261–1274. [CrossRef]
Dutta, S. , Ghosh, D. , and Chatterjee, S. , 2013, “ Multifractal Detrended Fluctuation Analysis of Human Gait Diseases,” Front. Physiol., 4, p. 274. [CrossRef] [PubMed]
Ihlen, E. A. , 2012, “ Introduction to Multifractal Detrended Fluctuation Analysis in matlab,” Front. Physiol., 3, pp. 1–18. [CrossRef] [PubMed]
West, B. J. , 2012, Fractal Physiology and Chaos in Medicine, World Scientific, Singapore.
Marri, K. , and Swaminathan, R. , 2016, “ Analysis of Biceps Brachii Muscles in Dynamic Contraction Using sEMG Signals and Multifractal DMA Algorithm,” Int. J. Signal Process. Syst., 4(1), pp. 79–85.
Venugopal, G. , Navaneethakrishna, M. , and Ramakrishnan, S. , 2014, “ Extraction and Analysis of Multiple Time Window Features Associated With Muscle Fatigue Conditions Using sEMG Signals,” Expert Syst. Appl., 41(6), pp. 2652–2659. [CrossRef]
Marri, K. , and Swaminathan, R. , 2015, “ Identification of Onset of Fatigue in Biceps Brachii Muscles Using Surface EMG and Multifractal DMA Algorithm,” Biomed. Sci. Instrum., 51, pp. 107–114 http://www.ncbi.nlm.nih.gov/pubmed/25996706. [PubMed]
Hermens, H. J. , Freriks, B. , Disselhorst-Klug, C. , and Rau, G. , 2000, “ Development of Recommendations for SEMG Sensors and Sensor Placement Procedures,” J. Electromyogr. Kinesiol., 10(5), pp. 361–374. [CrossRef] [PubMed]
Zhou, W. , Dang, Y. , and Gu, R. , 2013, “ Efficiency and Multifractality Analysis of CSI 300 Based on Multifractal Detrending Moving Average Algorithm,” Physica A, 392(6), pp. 1429–1438. [CrossRef]
Xiong, G. , Zhang, S. , and Zhao, H. , 2014, “ Multifractal Spectrum Distribution Based on Detrending Moving Average,” Chaos Solitons Fractals, 65, pp. 97–110. [CrossRef]
Lin, J. , and Chen, Q. , 2013, “ Fault Diagnosis of Rolling Bearings Using Multifractal Detrended Fluctuation Analysis and Mahalanobis Distance Criterion,” Mech. Syst. Signal Process., 38(2), pp. 515–533. [CrossRef]
Huang, H.-P. , and Chen, C.-Y. , 1999, “ Development of a Myoelectric Discrimination System for a Multi-Degree Prosthetic Hand,” IEEE International Conference on Robotics and Automation, Vol. 3, pp. 2392–2397.
Du, S. , and Vuskovic, M. , 2004, “ Temporal vs. Spectral Approach to Feature Extraction From Prehensile EMG Signals,” IEEE International Conference on Information Reuse and Integration (IRI), pp. 344–350.
Oskoei, M. A. , Member, S. , Hu, H. , and Member, S. , 2008, “ Support Vector Machine-Based Classification Scheme for Myoelectric Control Applied to Upper Limb,” IEEE Trans. Biomed. Eng., 55(8), pp. 1956–1965. [CrossRef] [PubMed]
Guyon, I. , and Elisseeff, A. , 2003, “ An Introduction to Variable and Feature Selection,” J. Mach. Learn. Res., 3, pp. 1157–1182 http://www.jmlr.org/papers/volume3/guyon03a/guyon03a.pdf.
Deng, L. , Pei, J. , Ma, J. , and Lee, D. L. , 2004, “ A Rank Sum Test Method for Informative Gene Discovery,” Proceedings of the Tenth ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, ACM, New York, pp. 410–419.
Pereira, A. , Vega, J. , Moreno, R. , Dormido-Canto, S. , Rattá, G. A. , and Pavón, F. , 2015, “ Feature Selection for Disruption Prediction From Scratch in JET by Using Genetic Algorithms and Probabilistic Predictors,” Fusion Eng. Des., 96–97, pp. 907–911. [CrossRef]
Hall, M. , Frank, E. , Holmes, G. , Pfahringer, B. , Reutemann, P. , and Witten, I. H. , 2009, “ The WEKA Data Mining Software: An Update,” ACM SIGKDD Explor. Newsl., 11(1), pp. 10–18. [CrossRef]
Konar, P. , Sil, J. , and Chattopadhyay, P. , 2015, “ Knowledge Extraction Using Data Mining for Multi-Class Fault Diagnosis of Induction Motor,” Neurocomputing, 166, pp. 14–25. [CrossRef]
Cai, H. , Ruan, P. , Ng, M. , and Akutsu, T. , 2014, “ Feature Weight Estimation for Gene Selection: A Local Hyperlinear Learning Approach,” BMC Bioinform., 15(1), p. 70. [CrossRef]
Wood, T. M. , Maddalozzo, G. F. , and Harter, R. A. , 2002, “ Accuracy of Seven Equations for Predicting 1-RM Performance of Apparently Healthy, Sedentary Older Adults,” Meas. Phys. Educ. Exercise Sci., 6(2), pp. 67–94. [CrossRef]
Clarkson, K. L. , 2006, “ Nearest-Neighbor Searching and Metric Space Dimensions,” Nearest-Neighbor Methods for Learning and Vision: Theory and Practice, Shakhnarovich, G., Darrell, T., Indyk, P., eds., MIT Press, Cambridge, MA.
Maalouf, M. , and Siddiqi, M. , 2014, “ Weighted Logistic Regression for Large-Scale Imbalanced and Rare Events Data,” Knowl. Based Syst., 59, pp. 142–148. [CrossRef]
Canu, S. , and Alex, S. , 2006, “ Kernel Methods and the Exponential Family,” Neurocomputing, 69(7), pp. 714–720. [CrossRef]
Cifrek, M. , Medved, V. , Tonković, S. , and Ostojić, S. , 2009, “ Surface EMG Based Muscle Fatigue Evaluation in Biomechanics.,” Clin. Biomech. (Bristol, Avon), 24(4), pp. 327–340. [CrossRef] [PubMed]

Figures

Grahic Jump Location
Fig. 1

Overall methodology for nonfatigue and fatigue studies

Grahic Jump Location
Fig. 2

Representative sEMG signals recorded from biceps brachii muscles of (a) subject A and (b) subject B

Grahic Jump Location
Fig. 3

Multifractal spectrum of sEMG signals in nonfatigue and fatigue conditions for (a) subject A and (b) subject B

Grahic Jump Location
Fig. 4

Mean percentage differences of features in nonfatigue and fatigue conditions

Grahic Jump Location
Fig. 5

Box plot of (a) SOM, (b) TSE-5, (c) WSE, and (d) DVS in nonfatigue and fatigue conditions. Central bar indicates median amplitude, central dot indicates mean, bottom and top of box indicate 25th and 75th percentiles, respectively, and extended lines indicate range (outliers are shown with cross).

Grahic Jump Location
Fig. 6

Multifractal spectral features ranked using Wilcoxon rank test

Grahic Jump Location
Fig. 7

Top 20 multifractal spectrum features using IG (light gray), GA (black), and Wilcoxon rank test (dark gray)

Grahic Jump Location
Fig. 8

Performance of k-NN classifier with different distance methods

Grahic Jump Location
Fig. 9

Three types of multifractal spectrum scenarios that the classifier did not predict accurately: (a) similar SOM, (b) similar maximum exponent, and (c) similar PEV and exponent

Tables

Errata

Discussions

Some tools below are only available to our subscribers or users with an online account.

Related Content

Customize your page view by dragging and repositioning the boxes below.

Related Journal Articles
Related eBook Content
Topic Collections

Sorry! You do not have access to this content. For assistance or to subscribe, please contact us:

  • TELEPHONE: 1-800-843-2763 (Toll-free in the USA)
  • EMAIL: asmedigitalcollection@asme.org
Sign In