Advertisement

Study on Gait Discrimination Method by Deep Learning for Biofeedback Training Optimized for Individuals

  • Yusuke OsawaEmail author
  • Keiichi Watanuki
  • Kazunori Kaede
  • Keiichi Muramatsu
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 903)

Abstract

In this research, to develop a biofeedback training system where trainees can efficiently train inadequacies that do not satisfy ideal walking using a deep learning, we examine a method that discriminates between ideal walking and nonideal walking. In the experiment, to examine the walking components used for the input data, the ground reaction force and joint angle were measured when young people walked normally and when they walked with a brace, to simulate elderly motions. Further, these data were discriminated between conditions as input data using a Convolution Neural Network (CNN). The average accuracy was 79.5% when all walking components were used as input data. In addition, it is thought that it is most suitable to discriminate walking by using all walking components, in consideration of implementation in the system.

Keywords

Walking assistance Biofeedback training Motion capture Ground reaction force Convolution neural network 

References

  1. 1.
    Brown, B.B.: Recognition of aspects of consciousness through association with EEG alpha activity represented by a light signal. Psychophysiology 6(4), 442–452 (1970)CrossRefGoogle Scholar
  2. 2.
    Stanton, R., Ada, L., Dean, C.M., Preston, E.: Biofeedback improves activities of the lower limb after stroke: a systematic review. J. Physiother. 57(3), 145–155 (2011)CrossRefGoogle Scholar
  3. 3.
    Turns, L.J., Neptune, R.R., Kautz, S.A.: Relationships between muscle activity and anteroposterior ground reaction forces in hemiparetic walking. Arch. Phys. Med. Rehabil. 88(9), 1127–1135 (2007)CrossRefGoogle Scholar
  4. 4.
    Murray, M.P., Kory, R.C., Clarkson, B.H.: Walking patterns in healthy old men. J. Gerontol. 24(2), 169–178 (1969)CrossRefGoogle Scholar
  5. 5.
    Watanabe, K., Miyakawa, T.: Gait analysis during stepping over the different height of obstacle in aged persons. Elsevier Sci., 195–198 (1994)Google Scholar
  6. 6.
    Gushiken, S., Oi, N., Tobimatsu, Y., Iwaya, T.: The relevance of standing posture and walking function in elderly people. J. Phys. Med. 14(3), 241–248 (2003). in JapaneseGoogle Scholar
  7. 7.
    Ballesteros, M.L.F., Buchthal, F., Rosenfalck, P.: The pattern of muscular activity during the arm of natural walking. Acta Physiol. 63(3), 296–310 (1965)CrossRefGoogle Scholar
  8. 8.
    Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Dhruv, D.: Grad-CAM: visual explanations from deep networks via gradient-based localization. In: ICCV 2017, pp. 618–626 (2017)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  • Yusuke Osawa
    • 1
    Email author
  • Keiichi Watanuki
    • 1
  • Kazunori Kaede
    • 1
  • Keiichi Muramatsu
    • 1
  1. 1.Graduate School of Science and EngineeringSaitama UniversitySakura-Ku, Saitama-ShiJapan

Personalised recommendations