Stress Detection using Electromyogram Signal of Erector Spinae Muscles

Document Type : Original Article (s)

Authors

1 PhD Student, Department of Biomedical Engineering, School of Biotechnology, Semnan University, Semnan, Iran

2 Assistant Professor, Department of Biomedical Engineering, School of Biotechnology, Semnan University, Semnan, Iran

Abstract

Background: Stress detection is essential and important in order to control, manage, and reduce it. On the other hand, there are many theories about the stress-related back pain. The most important point in all of these theories, is the psychological and emotional factors that cause some kinds of physiological changes, and as a result, back pain. Therefore, it seems that the electromyogram (EMG) signal of the lower back muscles can be used as a marker for stress detection.Methods: In this research, stress was detected using the electromyogram signal of erector spinae muscles. The signals of 15 persons were recorded from left and right erector spinae muscles. After extracting seven time and frequency domain features, stress was detected in two-level (stress and no stress) and four-level (no stress, low stress, moderate stress, and high stress) modes applying an efficient support vector machine (SVM) classifier. It was also attempted to improve the performance of the proposed approach by using feature selection methods.Findings: In two-level mode, stress was detected with 100% of accuracy. In the four-level mode, the efficiency of the right erector spinae muscle was higher and reached 100% of accuracy.Conclusion: The results denote that the electromyogram of the erector spinae muscles is an appropriate indicator of stress. The right erector spinae muscle is more effective than the left one. Furthermore, feature selection reduces the computation amount, and improves the efficiency of stress detection. The findings of this study can be used to detect stress for controlling and managing it.

Keywords


  1. Larsman P, Sandsjo L, Klipstein A, Vollenbroek-Hutten M, Christensen H. Perceived work demands, felt stress, and musculoskeletal neck/shoulder symptoms among elderly female computer users. The NEW study. Eur J Appl Physiol 2006; 96(2): 127-35.
  2. Kjellberg A, Wadman C. The role of the affective stress response as a mediator of the effect of psychosocial risk factors on musculoskeletal complaints; Part 1: Assembly workers. Int J Ind Ergon 2007; 37(4): 367-74.
  3. Larsman P, Thorn S, Sogaard K, Sandsjo L, Sjogaard G, Kadefors R. Work related perceived stress and muscle activity during standardized computer work among female computer users. Work 2009; 32(2): 189-99.
  4. Davoudian Talab A, Badfar G, Nikomaram M, Azari G, Mansori A. Effect of back pain on occupational stress among white-collar workers. Journal of Health Research in community 2017; 3(2): 35-43. [In Persian].
  5. Kuorinka I, Jonsson B, Kilbom A, Vinterberg H, Biering-Sorensen F, Andersson G, et al. Standardised Nordic questionnaires for the analysis of musculoskeletal symptoms. Appl Ergon 1987; 18(3): 233-7.
  6. Oberlinner C, Yong M, Nasterlack M, Pluto RP, Lang S. Combined effect of back pain and stress on work ability. Occup Med (Lond) 2015; 65(2): 147-53.
  7. Kim MG, Kim KS, Ryoo JH, Yoo SW. Relationship between occupational stress and work-related musculoskeletal disorders in Korean male firefighters. Ann Occup Environ Med 2013; 25(1): 9.
  8. Taib MF, Bahn S, Yun MH. The effect of psychosocial stress on muscle activity during computer work: Comparative study between desktop computer and mobile computing products. Work 2016; 54(3): 543-55.
  9. Pourmohammadi S, Maleki A. An automatic approach to continuous stress assessment during driving based on fuzzy c-means clustering. Modares Journal of Electrical Engineering 12013; 3(1): 9-17.
  10. Healey JA, Picard RW. Detecting stress during real-world driving tasks using physiological sensors. IEEE trans Intell Transp Syst 2005; 6(2): 156-66.
  11. Aigrain J, Spodenkiewicz M, Dubuisson S, Detyniecki M, Cohen D, Chetouani M. Multimodal stress detection from multiple assessments. IEEE Trans Affect Comput 2016; 1.
  12. SENIAM. Recommendations for sensor locations on individual muscles [Online]. [cited 2013]; Available from: http://seniam.org/sensor_location.htm
  13. Cohen S. Perceived Stress Scale. Menlo Park, CA: Mind Garden, Inc; 1994.
  14. Gjoreski M, Gjoreski H, Lustrek M, Gams M. Continuous stress detection using a wrist device: In laboratory and real life. Proceedings of 2016 ACM International Joint Conference on Pervasive and Ubiquitous Computing (UbiComp 2016); 2016 Sep 12-16; Heidelberg, Germany. New York, NY: ACM: p. 1185-93.
  15. Jozef Stefan Institute, Department of Intelligent Systems. The-S-Test [Online]. [cited 2015]; Available from: URL: https://dis.ijs.si/thestest/
  16. Wijsman JLP, Grundlehner B, Penders J, Hermens HJ. Trapezius muscle EMG as predictor of mental stress. Acm Trans Embed Comput Syst 2013; 12(4): 99.
  17. Sarafino EP, Smith TW. Health psychology: Biopsychosocial interactions. 8th ed. Hoboken, NJ: Wiley; 2013.
  18. Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Syst Appl 2012; 39(8): 7420-31.
  19. Oskoei MA, Hu H. Support vector machine-based classification scheme for myoelectric control applied to upper limb. IEEE Trans Biomed Eng 2008; 55(8): 1956-65.
  20. Schenk J, Kaiser M, Rigoll G. Selecting Features in On-Line Handwritten Whiteboard Note Recognition: SFS or SFFS? Proceedings of 10th International Conference on Document Analysis and Recognition; 2009 Jul 26-29; Barcelona, Spain. p. 1251-4.
  21. Kwak N, Choi CH. Input feature selection by mutual information based on Parzen window. IEEE Trans Pattern Anal Mach Intell 2002; 24(12): 1667-71.
  22. Sharma N, Gedeon T. Objective measures, sensors and computational techniques for stress recognition and classification: a survey. Comput Methods Programs Biomed 2012; 108(3): 1287-301.