Study of Stability of Time-domain Features for Electromyographic Pattern Recognition

Overview

Journal J Neuroeng Rehabil

Publisher Biomed Central

Specialties Biomedical Engineering
Neurology
Rehabilitation Medicine

Date 2010 May 25

PMID 20492713

Citations 96

Authors

Dennis Tkach

He Huang

Todd A Kuiken

Affiliations

Soon will be listed here.

Abstract

Background: Significant progress has been made towards the clinical application of human-machine interfaces (HMIs) based on electromyographic (EMG) pattern recognition for various rehabilitation purposes. Making this technology practical and available to patients with motor deficits requires overcoming real-world challenges, such as physical and physiological changes, that result in variations in EMG signals and systems that are unreliable for long-term use. In this study, we aimed to address these challenges by (1) investigating the stability of time-domain EMG features during changes in the EMG signals and (2) identifying the feature sets that would provide the most robust EMG pattern recognition.

Methods: Variations in EMG signals were introduced during physical experiments. We identified three disturbances that commonly affect EMG signals: EMG electrode location shift, variation in muscle contraction effort, and muscle fatigue. The impact of these disturbances on individual features and combined feature sets was quantified by changes in classification performance. The robustness of feature sets was evaluated by a stability index developed in this study.

Results: Muscle fatigue had the smallest effect on the studied EMG features, while electrode location shift and varying effort level significantly reduced the classification accuracy for most of the features. Under these disturbances, the most stable EMG feature set with combination of four features produced at least 16.0% higher classification accuracy than the least stable set. EMG autoregression coefficients and cepstrum coefficients showed the most robust classification performance of all studied time-domain features.

Conclusions: Selecting appropriate EMG feature combinations can overcome the impact of the studied disturbances on EMG pattern classification to a certain extent; however, this simple solution is still inadequate. Stabilizing electrode contact locations and developing effective classifier training strategies are suggested to further improve the robustness of HMIs based on EMG pattern recognition.

Citing Articles

Machine Learning- and Deep Learning-Based Myoelectric Control System for Upper Limb Rehabilitation Utilizing EEG and EMG Signals: A Systematic Review.

Zaim T, Abdel-Hadi S, Mahmoud R, Khandakar A, Rakhtala S, Chowdhury M Bioengineering (Basel). 2025; 12(2).

PMID: 40001664 PMC: 11851773. DOI: 10.3390/bioengineering12020144.

The Investigation of the Relationship Between Individual Pain Perception, Brain Electrical Activity, and Facial Expression Based on Combined EEG and Facial EMG Analysis.

Ma C, Wang C, Zhu D, Chen M, Zhang M, He J J Pain Res. 2025; 18():21-32.

PMID: 39776765 PMC: 11705972. DOI: 10.2147/JPR.S477658.

Surface electromyography evaluation for decoding hand motor intent in children with congenital upper limb deficiency.

Battraw M, Fitzgerald J, Winslow E, James M, Bagley A, Joiner W Sci Rep. 2024; 14(1):31741.

PMID: 39738577 PMC: 11685410. DOI: 10.1038/s41598-024-82519-z.

MS-CLSTM: Myoelectric Manipulator Gesture Recognition Based on Multi-Scale Feature Fusion CNN-LSTM Network.

Wang Z, Huang W, Qi Z, Yin S Biomimetics (Basel). 2024; 9(12.

PMID: 39727788 PMC: 11727569. DOI: 10.3390/biomimetics9120784.

Application of a sEMG hand motion recognition method based on variational mode decomposition and ReliefF algorithm in rehabilitation medicine.

Yuan Y PLoS One. 2024; 19(11):e0314611.

PMID: 39602453 PMC: 11602058. DOI: 10.1371/journal.pone.0314611.

References

Sahlin K, Ren J . Relationship of contraction capacity to metabolic changes during recovery from a fatiguing contraction. J Appl Physiol (1985). 1989; 67(2):648-54. DOI: 10.1152/jappl.1989.67.2.648. View

Micera S, Sabatini A, Dario P . On automatic identification of upper-limb movements using small-sized training sets of EMG signals. Med Eng Phys. 2001; 22(8):527-33. DOI: 10.1016/s1350-4533(00)00069-2. View

Yoon T, Schlinder Delap B, Griffith E, Hunter S . Mechanisms of fatigue differ after low- and high-force fatiguing contractions in men and women. Muscle Nerve. 2007; 36(4):515-24. DOI: 10.1002/mus.20844. View

Vigreux B, Cnockaert J, PERTUZON E . Factors influencing quantified surface EMGs. Eur J Appl Physiol Occup Physiol. 1979; 41(2):119-29. DOI: 10.1007/BF00421659. View

Kiguchi K, Imada Y, Liyanage M . EMG-based neuro-fuzzy control of a 4DOF upper-limb power-assist exoskeleton. Annu Int Conf IEEE Eng Med Biol Soc. 2007; 2007:3040-3. DOI: 10.1109/IEMBS.2007.4352969. View

Stein J, Narendran K, McBean J, Krebs K, Hughes R . Electromyography-controlled exoskeletal upper-limb-powered orthosis for exercise training after stroke. Am J Phys Med Rehabil. 2007; 86(4):255-61. DOI: 10.1097/PHM.0b013e3180383cc5. View

Dipietro L, Ferraro M, Palazzolo J, Igo Krebs H, Volpe B, Hogan N . Customized interactive robotic treatment for stroke: EMG-triggered therapy. IEEE Trans Neural Syst Rehabil Eng. 2005; 13(3):325-34. PMC: 2752646. DOI: 10.1109/TNSRE.2005.850423. View

Smith I, Newham D . Fatigue and functional performance of human biceps muscle following concentric or eccentric contractions. J Appl Physiol (1985). 2006; 102(1):207-13. DOI: 10.1152/japplphysiol.00571.2006. View

Broman H, Bilotto G, De Luca C . Myoelectric signal conduction velocity and spectral parameters: influence of force and time. J Appl Physiol (1985). 1985; 58(5):1428-37. DOI: 10.1152/jappl.1985.58.5.1428. View

10.

Englehart K, Hudgins B . A robust, real-time control scheme for multifunction myoelectric control. IEEE Trans Biomed Eng. 2003; 50(7):848-54. DOI: 10.1109/TBME.2003.813539. View

11.

Hargrove L, Englehart K, Hudgins B . A comparison of surface and intramuscular myoelectric signal classification. IEEE Trans Biomed Eng. 2007; 54(5):847-53. DOI: 10.1109/TBME.2006.889192. View

12.

Williams 3rd T . Practical methods for controlling powered upper-extremity prostheses. Assist Technol. 1989; 2(1):3-18. DOI: 10.1080/10400435.1990.10132142. View

13.

Ferreira A, Celeste W, Cheein F, Bastos-Filho T, Sarcinelli-Filho M, Carelli R . Human-machine interfaces based on EMG and EEG applied to robotic systems. J Neuroeng Rehabil. 2008; 5:10. PMC: 2292737. DOI: 10.1186/1743-0003-5-10. View

14.

Sahlin K, Tonkonogi M, Soderlund K . Energy supply and muscle fatigue in humans. Acta Physiol Scand. 1998; 162(3):261-6. DOI: 10.1046/j.1365-201X.1998.0298f.x. View

15.

Sensinger J, Lock B, Kuiken T . Adaptive pattern recognition of myoelectric signals: exploration of conceptual framework and practical algorithms. IEEE Trans Neural Syst Rehabil Eng. 2009; 17(3):270-8. PMC: 3025709. DOI: 10.1109/TNSRE.2009.2023282. View

16.

Choi C, Micera S, Carpaneto J, Kim J . Development and quantitative performance evaluation of a noninvasive EMG computer interface. IEEE Trans Biomed Eng. 2009; 56(1):188-91. DOI: 10.1109/TBME.2008.2005950. View

17.

Hargrove L, Englehart K, Hudgins B . The effect of electrode displacements on pattern recognition based myoelectric control. Conf Proc IEEE Eng Med Biol Soc. 2007; 2006:2203-6. DOI: 10.1109/IEMBS.2006.260681. View

18.

Khezri M, Jahed M . Real-time intelligent pattern recognition algorithm for surface EMG signals. Biomed Eng Online. 2007; 6:45. PMC: 2222669. DOI: 10.1186/1475-925X-6-45. View

19.

Zecca M, Micera S, Carrozza M, Dario P . Control of multifunctional prosthetic hands by processing the electromyographic signal. Crit Rev Biomed Eng. 2003; 30(4-6):459-85. DOI: 10.1615/critrevbiomedeng.v30.i456.80. View

20.

Graupe D, Salahi J, Kohn K . Multifunctional prosthesis and orthosis control via microcomputer identification of temporal pattern differences in single-site myoelectric signals. J Biomed Eng. 1982; 4(1):17-22. DOI: 10.1016/0141-5425(82)90021-8. View