KIPS Transactions on Computer and Communication Systems (정보처리학회논문지:컴퓨터 및 통신 시스템)

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

A Study on the Method of Differentiating Between Elderly Walking and Non-Senior Walking Using Machine Learning Models

기계학습 모델을 이용한 노인보행과 비노인보행의 구별 방법에 관한 연구

  • 김가영 (강릉원주대학교 컴퓨터공학과) ;
  • 정수환 (강릉원주대학교 컴퓨터공학과) ;
  • 엄수현 (강릉원주대학교 컴퓨터공학과) ;
  • 장성원 (강릉원주대학교 컴퓨터공학과) ;
  • 이소연 (강릉원주대학교 컴퓨터공학과) ;
  • 최상일 (강릉원주대학교 컴퓨터공학과)
  • Received : 2021.06.04
  • Accepted : 2021.07.24
  • Published : 2021.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

Gait analysis is one of the research fields for obtaining various information related to gait by analyzing human ambulation. It has been studied for a long time not only in the medical field but also in various academic areas such as mechanical engineering, electronic engineering, and computer engineering. Efforts have been made to determine whether there is a problem with gait through gait analysis. In this paper, as a pre-step to find out gait abnormalities, it is investigated whether it is possible to differentiate whether experiment participants wear elderly simulation suit or not by applying gait data to machine learning models for the same person. For a total of 45 participants, each gait data was collected before and after wearing the simulation suit, and a total of six machine learning models were used to learn the collected data. As a result of using an artificial neural network model to distinguish whether or not the participants wear the suit, it showed 99% accuracy. What this study suggests is that we explored the possibility of judging the presence or absence of abnormality in gait by using machine learning.

보행 분석은 인간의 걸음걸이를 분석하여 보행과 관련된 여러 다양한 정보를 얻기 위한 연구 분야 중 하나로써 의료 분야뿐만 아니라 기계공학, 전자공학 및 컴퓨터공학 등 다양한 학문 분야에서 오랫동안 연구되고 있다. 보행 분석을 통해 걸음걸이에 문제가 있는지를 파악하려는 노력이 꾸준히 이어져 왔다. 본 논문에서는 이러한 보행 이상을 알아보기 위한 전 단계로써 보행 데이터를 활용하여 동일 실험 참가자에 대해 노인 체험복착용 전후의 걸음걸이를 기계학습 모델에 적용하여 학습시킴으로써 노인 체험복 착용 여부를 구별할 수 있는지를 연구하였다. 총 45명의 실험 참가들을 대상으로 노인 체험복 착용 전과 후 각각의 보행 데이터를 수집하였고, 총 6개의 기계학습 모델을 이용하여 보행 데이터를 학습시켰다. 신경망 모델을 활용하여 노인 체험복 착용 여부를 판별한 결과 약 99%의 높은 정확도를 보였다. 본 연구에서 시사하는 것은 기계학습을 활용하여 보행의 이상 유무를 판단할 수 있는 가능성을 모색했다는 데 있다.

Keywords

Acknowledgement

이 논문은 2019년도 강릉원주대학교 신임교원 연구비 지원에 의하여 연구되었음. 이 논문은 2020년도 정부(과학기술정보통신부)의 재원으로 한국연구재단 생애첫연구사업의 지원을 받아 수행된 연구임(No.2020R1G1A1013937).

References

  1. J.-H. Park, "Characteristics of gait in the elderly: Normal vs. abnormal," Journal of the Korean Neurological Association, Vol.35, No.4, pp.1-4, 2017. https://doi.org/10.17340/jkna.2017.4.23
  2. D. K. Lee, "Gait Disorders," Korean Journal of Clinical Geriatrics, Vol.12, No.4, pp.141-148, 2011.
  3. G. S. Heo, S. H. Yang, S. R. Lee, J. G. Lee, and C.-Y. Lee, "A study on particular abnormal gait using accelerometer and gyro sensor," Journal of the Korean Society for Precision Engineering, Vol.29 No.11, pp.1199-1206, 2012. https://doi.org/10.7736/KSPE.2012.29.11.1199
  4. R. M. Ardle, S. D. Din, B. Galna, A. Thomas, and L. Rochester, "Differentiating dementia disease subtypes with gait analysis: Feasibility of wearable sensors?," Gait & Posture, Vol.76, pp.372-376, 2020. https://doi.org/10.1016/j.gaitpost.2019.12.028
  5. L. G. M. Ader, B. R. Greene, K. McManus, and B. Caulfield, "Reliability of inertial sensor based spatiotemporal gait parameters for short walking bouts in community dwelling older adults," Gait & Posture, Vol.85, pp.1-6, 2021. https://doi.org/10.1016/j.gaitpost.2021.01.010
  6. T. Steinmetzer, S. Wilberg, I. Bonninger, and C. M. Travieso, "Analyzing gait symmetry with automatically synchronized wearable sensors in daily life," Microprocessors and Microsystems, Vol.77, pp.1-10, 2020.
  7. S. Clemens, K. J. Kim, R. Gailey, N. Kirk-Sanchez, A. Kristal, and I. Gaunaurd, "Inertial sensor-based measures of gait symmetry and repeatability in people with unilateral lower limb amputation," Clinical Biomechanics, Vol.72, pp.102-107, 2020. https://doi.org/10.1016/j.clinbiomech.2019.12.007
  8. S. Mekruksavanich and A. Jitpattanakul, "Classification of gait pattern with wearable sensing data," in Proceedings of the 4th International Conference on Digital Arts, Media and Technology, Nan, Thailand, pp.137-141, 2019.
  9. A. Tanigawa, S. Morino, T. Aoyama, and M. Takahashi, "Gait analysis of pregnant patients with lumbopelvic pain using inertial sensor," Gait & Posture, Vol.65, pp.176-181, 2018.
  10. J. Li, Z. Wang, X. Shi, S. Qiu, H. Zhao, and M. Guo, "Quantitative analysis of abnormal and normal gait based on inertial sensors," in Proceedings of the 22nd IEEE International Conference on Computer Supported Cooperative Work in Design, Nanjing, China, 2018.
  11. S. S. Fathima and W. Banu, "Abnormal walk identification for systems using gait patterns," Biomedical Research, pp.112-117, 2016.
  12. K.-W. Park, "Gait Disturbances in Elderly Life," Journal of the Korean Neurological Association, Vol.35, No.4, pp.10-15, 2017. https://doi.org/10.17340/jkna.2017.4.25
  13. X. Wang, D. Ristic-Durrant, M. Spranger, and A. Graser, "Gait assessment system based on novel gait variability measures," in Proceedings of the 15th IEEE International Conference on Rehabilitation Robotics (ICORR), London, UK, pp.467-472, 2017.
  14. C. P. Burgos, L. Gartner, M. A. G. Ballester, J. Noailly, F. Stocker, M. Schonfelder, T. Adams, and S. Tassani, "In-ear accelerometer-based sensor for gait classification," IEEE Sensors Journal, Vol.20, No.21 pp.12895-12902, 2020. https://doi.org/10.1109/jsen.2020.3002589
  15. R. LeMoyne and T. Mastroianni, "Network centric therapy for machine learning classification of hemiplegic gait through conformal wearable and wireless inertial sensors," in Proceedings of the 8th IEEE International Conference on E-Health and Bioengineering (EHB), 2020.
  16. R. LeMoyne and T. Mastroianni, "Conformal wearable and wireless inertial sensor system for machine learning classification of hemiplegic reduced arm swing," in Proceedings of the 8th IEEE International Conference on E-Health and Bioengineering (EHB), 2020.
  17. H. Zhang, Y. Guo, and D. Zanotto, "Accurate ambulatory gait analysis in walking and running using machine learning models," IEEE Transaction on Neural Systems and Rehabilitation Engineering, Vol.28, No.1, pp.191-202, 2020. https://doi.org/10.1109/tnsre.2019.2958679
  18. J. C. Perez-Ibarra, A. A. G. Siqueira, and H. I. Krebs, "Identification of gait events in healthy and parkinson's disease subjects using inertial sensors: A supervised learning approach," IEEE Sensors Journal, Vol.20, No.24, pp.14984-14993, 2020. https://doi.org/10.1109/jsen.2020.3011627
  19. B. Shi, S. C. Yen, A. Tay, D. M.L. Tan, N. S. Y. Chia, and W. L. Au, "Convolutional neural network for freezing of gait detection leveraging the continuous wavelet transform on lower extremities wearable sensors data," in Proceedings of the 42nd IEEE Conference of Engineering in Medicine and Biology Society (EMBC), pp.5410-5415, 2020.
  20. S. Strada, J. Paris, F. Piccoli, D. P. Tucci, P. Casali, and S. Savaresi, "Machine learning recognition of gait identity via shoe embedded accelerometer," in Proceedings of the International Conference on Internet of Things (iThings), pp.852-857, 2020.
  21. M. Nagashima, S. G. Cho, M. Ding, G. A. G. Ricardez, J. Takamatsu, and T. Ogasawara, "Prediction of plantar forces during gait using wearable sensors and deep neural networks," in Proceedings of the 41st IEEE Conference of the Engineering in Medicine and Biology Society (EMBC), pp.3629-3632, Berlin, Germany, 2019.
  22. A. Rubio-Solis, G. Panoutsos, C. Beltran-Perez, and U. Martinez-Hernandez, "A multilayer interval type-2 fuzzy extreme learning machine for the recognition of walking activities and gait events using wearable sensors," Neurocomputing, Vol.389, pp.42-55, 2019. https://doi.org/10.1016/j.neucom.2019.11.105
  23. S. Majumder, T. Mondal, and M. J. Deen, "A simple, low-cost and efficient gait analyzer for wearable healthcare applications," IEEE Sensors Journal, Vol.19, No.6, pp.2320-2329, 2019. https://doi.org/10.1109/jsen.2018.2885207
  24. U. Martinez-Hernandez and A. A. Dehghani-Sanij, "Adaptive bayesian inference system for recognition of walking activities and prediction of gait events using wearable sensors," Neural Networks, Vol.102, pp.107-119, 2018. https://doi.org/10.1016/j.neunet.2018.02.017
  25. J. Hannink, T. Kautz, C. F. Pasluosta, J. Barth, S. Schulein, K-G. Gssbmann, J. Klucken, and B. M. Eskofier, "Mobile stride length estimation with deep convolutional neural networks," IEEE Journal of Biomedical and Health Informatics, Vol.22, No.2, pp.354-362, 2018. https://doi.org/10.1109/jbhi.2017.2679486
  26. B. Shi, X. Bai, and C. Yao, "An end-to-end trainable neural network for image-based sequence recognition and its application to scene text recognition," IEEE Transactions on Pattern Analysis and Machine Intelligence, Vol.39, No.11, pp.2298-2304, 2017. https://doi.org/10.1109/TPAMI.2016.2646371