Physical Therapy Korea (한국전문물리치료학회지)

Korean Research Society of Physical Therapy (한국전문물리치료학회)
권호 표지
DOI QR코드

DOI QR Code

Feature Extraction and Evaluation for Classification Models of Injurious Falls Based on Surface Electromyography

  • Lim, Kitaek (Injury Prevention and Biomechanics Laboratory, Department of Physical Therapy, Yonsei University) ;
  • Choi, Woochol Joseph (Injury Prevention and Biomechanics Laboratory, Department of Physical Therapy, Yonsei University)
  • Received : 2021.02.15
  • Accepted : 2021.04.09
  • Published : 2021.05.20
Download PDF
⟨ Previous Next ⟩

Abstract

Background: Only 2% of falls in older adults result in serious injuries (i.e., hip fracture). Therefore, it is important to differentiate injurious versus non-injurious falls, which is critical to develop effective interventions for injury prevention. Objects: The purpose of this study was to a. extract the best features of surface electromyography (sEMG) for classification of injurious falls, and b. find a best model provided by data mining techniques using the extracted features. Methods: Twenty young adults self-initiated falls and landed sideways. Falling trials were consisted of three initial fall directions (forward, sideways, or backward) and three knee positions at the time of hip impact (the impacting-side knee contacted the other knee ("knee together") or the mat ("knee on mat"), or neither the other knee nor the mat was contacted by the impacting-side knee ("free knee"). Falls involved "backward initial fall direction" or "free knee" were defined as "injurious falls" as suggested from previous studies. Nine features were extracted from sEMG signals of four hip muscles during a fall, including integral of absolute value (IAV), Wilson amplitude (WAMP), zero crossing (ZC), number of turns (NT), mean of amplitude (MA), root mean square (RMS), average amplitude change (AAC), difference absolute standard deviation value (DASDV). The decision tree and support vector machine (SVM) were used to classify the injurious falls. Results: For the initial fall direction, accuracy of the best model (SVM with a DASDV) was 48%. For the knee position, accuracy of the best model (SVM with an AAC) was 49%. Furthermore, there was no model that has sensitivity and specificity of 80% or greater. Conclusion: Our results suggest that the classification model built upon the sEMG features of the four hip muscles are not effective to classify injurious falls. Future studies should consider other data mining techniques with different muscles.

Keywords

Acknowledgement

This study was supported by the "Brain Korea 21 FOUR Project", the Korean Research Foundation for Department of Physical Therapy in the Graduate School of Yonsei University.

References

  1. Grisso JA, Schwarz DF, Wishner AR, Weene B, Holmes JH, Sutton RL. Injuries in an elderly inner-city population. J Am Geriatr Soc 1990;38(12):1326-31. https://doi.org/10.1111/j.1532-5415.1990.tb03456.x
  2. Empana JP, Dargent-Molina P, Breart G; EPIDOS Group. Effect of hip fracture on mortality in elderly women: the EPIDOS prospective study. J Am Geriatr Soc 2004;52(5):685-90. https://doi.org/10.1111/j.1532-5415.2004.52203.x
  3. Wolinsky FD, Fitzgerald JF, Stump TE. The effect of hip fracture on mortality, hospitalization, and functional status: a prospective study. Am J Public Health 1997;87(3):398-403. https://doi.org/10.2105/AJPH.87.3.398
  4. Sattin RW. Falls among older persons: a public health perspective. Annu Rev Public Health 1992;13:489-508.
  5. Choi WJ, Cripton PA, Robinovitch SN. Effects of hip abductor muscle forces and knee boundary conditions on femoral neck stresses during simulated falls. Osteoporos Int 2015; 26(1):291-301. https://doi.org/10.1007/s00198-014-2812-4
  6. Lim KT, Choi WJ. Effect of fall characteristics on the severity of hip impact during a fall on the ground from standing height. Osteoporos Int 2020;31(9):1713-9.
  7. Yang Y, Komisar V, Shishov N, Lo B, Korall AM, Feldman F, et al. The effect of fall biomechanics on risk for hip fracture in older adults: a cohort study of video-captured falls in long-term care. J Bone Miner Res 2020;35(10):1914-22.
  8. Aziz O, Musngi M, Park EJ, Mori G, Robinovitch SN. A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and non-fall trials. Med Biol Eng Comput 2017;55(1):45-55.
  9. Juan C, Xiang C, Minfen S. A framework for daily activity monitoring and fall detection based on surface electromyography and accelerometer signals. IEEE J Biomed Health Inform 2013;17(1):38-45. https://doi.org/10.1109/TITB.2012.2226905
  10. Ren L, Peng Y. Research of fall detection and fall prevention technologies: a systematic review. IEEE Access 2019;7: 77702-22.
  11. Cheng WC, Jhan DM. Triaxial accelerometer-based fall detection method using a self-constructing cascade-AdaBoost-SVM classifier. IEEE J Biomed Health Inform 2013;17(2):411-9. https://doi.org/10.1109/JBHI.2012.2237034
  12. Santos GL, Endo PT, Monteiro KHC, Rocha EDS, Silva I, Lynn T. Accelerometer-based human fall detection using convolutional neural networks. Sensors (Basel) 2019;19(7):1644. https://doi.org/10.3390/s19071644
  13. Roy SH, Cheng MS, Chang SS, Moore J, De Luca G, Nawab SH, et al. A combined sEMG and accelerometer system for monitoring functional activity in stroke. IEEE Trans Neural Syst Rehabil Eng 2009;17(6):585-94. https://doi.org/10.1109/TNSRE.2009.2036615
  14. Adewuyi AA, Hargrove LJ, Kuiken TA. An analysis of intrinsic and extrinsic hand muscle EMG for improved pattern recognition control. IEEE Trans Neural Syst Rehabil Eng 2016; 24(4):485-94. https://doi.org/10.1109/TNSRE.2015.2424371
  15. Phinyomark A, Phukpattaranont P, Limsakul C. Feature reduction and selection for EMG signal classification. Expert Systems with Applications 2012;39(8):7420-31. https://doi.org/10.1016/j.eswa.2012.01.102
  16. Sutherland DH. The evolution of clinical gait analysis part l: kinesiological EMG. Gait Posture 2001;14(1):61-70. https://doi.org/10.1016/S0966-6362(01)00100-X
  17. Xi X, Tang M, Miran SM, Luo Z. Evaluation of feature extraction and recognition for activity monitoring and fall detection based on wearable sEMG sensors. Sensors (Basel) 2017;17(6): 1229. https://doi.org/10.3390/s17061229
  18. Criswell E, Cram JR. Cram's introduction to surface electromyography. 2nd ed. Sudbury: Jones and Bartlett; 2011;xxi, 412.
  19. Nazmi N, Abdul Rahman MA, Yamamoto S, Ahmad SA, Zamzuri H, Mazlan SA. A review of classification techniques of EMG signals during isotonic and isometric contractions. Sensors (Basel) 2016;16(8):1304. https://doi.org/10.3390/s16081304
  20. Englehart K, Hudgins B, Parker PA, Stevenson M. Classification of the myoelectric signal using time-frequency based representations. Med Eng Phys 1999;21(6-7):431-8. https://doi.org/10.1016/S1350-4533(99)00066-1
  21. Kim KS, Choi HH, Moon CS, Mun CW. Comparison of k-nearest neighbor, quadratic discriminant and linear discriminant analysis in classification of electromyogram signals based on the wrist-motion directions. Curr Appl Phys 2011;11(3):740-5. https://doi.org/10.1016/j.cap.2010.11.051
  22. Zardoshti-Kermani M, Wheeler BC, Badie K, Hashemi RM. EMG feature evaluation for movement control of upper extremity prostheses. IEEE Trans Rehabil Eng 1995;3(4):324-33.
  23. Hudgins B, Parker P, Scott RN. A new strategy for multifunction myoelectric control. IEEE Trans Biomed Eng 1993;40(1): 82-94. https://doi.org/10.1109/10.204774
  24. Boostani R, Moradi MH. Evaluation of the forearm EMG signal features for the control of a prosthetic hand. Physiol Meas 2003;24(2):309-19. https://doi.org/10.1088/0967-3334/24/2/307
  25. Park SH, Lee SP. EMG pattern recognition based on artificial intelligence techniques. IEEE Trans Rehabil Eng 1998;6(4): 400-5.
  26. Chang GC, Kang WJ, Luh JJ, Cheng CK, Lai JS, Chen JJ, et al. Real-time implementation of electromyogram pattern recognition as a control command of man-machine interface. Med Eng Phys 1996;18(7):529-37. https://doi.org/10.1016/1350-4533(96)00006-9
  27. Keles S, Subasi A. Classification of EMG signals using decision tree methods. Paper presented at: 3rd International Symposium on Sustainable Development (ISSD); 2012 May 31-Jun 1; Sarajevo, Bosnia and Herzegovina. Sarajevo: International Burch University, 2012. p. 354-66.
  28. Lee KJ, Lim K, Choi WJ. The effect on the hip muscle activation of the fall direction and knee position during a fall. Phys Ther Korea 2021;28(1):84-91.
  29. Wei W, Jia Q. Weighted feature Gaussian kernel SVM for emotion recognition. Comput Intell Neurosci 2016;2016: 7696035. https://doi.org/10.1155/2016/7696035
  30. Song W, Han Q, Lin Z, Yan N, Luo D, Liao Y, et al. Design of a flexible wearable smart sEMG recorder integrated gradient boosting decision tree based hand gesture recognition. IEEE Trans Biomed Circuits Syst 2019;13(6):1563-74. https://doi.org/10.1109/tbcas.2019.2953998
  31. Trevisan C, Di Gregorio P, Debiasi E, Pedrotti M, La Guardia M, Manzato E, et al. Decision tree for ward admissions of older patients at the emergency department after a fall. Geriatr Gerontol Int 2018;18(9):1388-92. https://doi.org/10.1111/ggi.13497
  32. Cai WY, Guo JH, Zhang MY, Ruan ZX, Zheng XC, Lv SS. GBDT-based fall detection with comprehensive data from posture sensor and human skeleton extraction. J Healthc Eng 2020; 2020:8887340.
  33. Waris A, Niazi IK, Jamil M, Englehart K, Jensen W, Kamavuako EN. Multiday evaluation of techniques for EMG-based classification of hand motions. IEEE J Biomed Health Inform 2019; 23(4):1526-34. https://doi.org/10.1109/jbhi.2018.2864335