A Gait Phase Classifier using a Recurrent Neural Network

순환 신경망을 이용한 보행단계 분류기

  • Heo, Won ho (Electrical & Electronic Engineering, Yonsei University) ;
  • Kim, Euntai (Electrical & Electronic Engineering, Yonsei University) ;
  • Park, Hyun Sub (Human-Assistive Robot Research Center, Korea Institute of Industrial Technology) ;
  • Jung, Jun-Young (Human-Assistive Robot Research Center, Korea Institute of Industrial Technology)
  • 허원호 (연세대학교 전기전자공학부, 한국생산기술연구원 인간지원로봇연구단) ;
  • 김은태 (연세대학교 전기전자공학부) ;
  • 박현섭 (한국 산업기술평가관리원 로봇PD실) ;
  • 정준영 (한국생산기술연구원 인간지원로봇연구단)
  • Received : 2015.02.15
  • Accepted : 2015.03.15
  • Published : 2015.06.01


This paper proposes a gait phase classifier using a Recurrent Neural Network (RNN). Walking is a type of dynamic system, and as such it seems that the classifier made by using a general feed forward neural network structure is not appropriate. It is known that an RNN is suitable to model a dynamic system. Because the proposed RNN is simple, we use a back propagation algorithm to train the weights of the network. The input data of the RNN is the lower body's joint angles and angular velocities which are acquired by using the lower limb exoskeleton robot, ROBIN-H1. The classifier categorizes a gait cycle as two phases, swing and stance. In the experiment for performance verification, we compared the proposed method and general feed forward neural network based method and showed that the proposed method is superior.


Supported by : 산업통상자원부


  1. H.-D. Lee and C.-S. Han, "Technical trend of the lower limb exoskeleton system for the performance enhancement," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 20, no. 3, pp. 364-371, Oct. 2014.
  2. M. Sekine, Y. Abe, M. Sekimoto, Y. Higashi, T. Fujimoto, T. Tamura, and Y. Fukui, "Assessment of gait parameter in hemiplegic patients by accelerometry," Proc. of the 22nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Chicago, IL, pp. 1879-1882, May 2000.
  3. M. Vukobratovic, D. Hristic, and Z. Stojiljkovic, "Development of active anthropomorphic exoskeletons," Medical and Biological Engineering, vol. 12, no. 1, pp. 66-80, Jan. 1974.
  4. F. Alonge, E. Cucco, F. D'Ippolito, and A. Pulizzotto, "The use of accelerometers and gyroscopes to estimate hip and knee angles on gait analysis," Sensors, vol. 14, no. 5, pp. 8430-8446, May 2014.
  5. H. Kim, "Human gait-phase classification to control a lower extremity exoskeleton robot," Korea Information and Communications Society, vol. 39B, no. 7, pp. 479-490, Jul. 2014.
  6. K. Kong and M. Tomizuka, "Smooth and continuous human gait phase detectionbased on foot pressure patterns," 2008 IEEE International Conference on Robotics and Automation, Pasadena, CA, pp. 3678-3683, May 2008.
  7. J. Jung, I. Jang, R. Riener, and H. Park "Walking intent detection algorithm for paraplegic patients using a robotic exoskeleton walking assistant with crutches," International Journal of Control, Automation and Systems, vol. 10, no. 5, pp. 954-962, Oct. 2012.
  8. J. Taborri, S. Rossi, E. Palermo, F. Patane, and P. Cappa, "A novel HMM distributed classifier for the detection of gait phases by means of a wearable inertial sensor network," Sensors, vol. 14, no. 9, pp. 16212-16234, Sep. 2014.
  9. M. Chae, J. Jung, C. Park, I. Jang, and H. Park, "Gait phases classification using joint angle and ground reaction force: application of backpropagation neural networks," Journal of Institute of Control, Robotics and Systems (in Korean), vol. 18, no. 7, pp. 644-649, Jul. 2012.
  10. S. Lee and Y. Sankai, "Power assist control for walking aid with HAL-3 based on EMG and impedance adjustment around knee joint," IEEE/RSJ International Conference on Intelligent Robots and Systems, Lausanne, Switzerland, pp. 1499-1504, Oct. 2002.
  11. J. Perry, Gait Analysis, 1st Ed, SLACK INC., New Jersey, 2006.
  12. D. Pena, G. C. Tiao, and R. S. Tasy, A Course in Time Serise Analysis, 1st Ed, John Wiley & Sons, New York, 2001.
  13. B. Pearlmutter, "Dynamic recurrent neural networks," Carnegie Mellon University Technical Report, Pennsylvania, 1990.
  14. S. Cho and J. Kim, "Acceleration techniques of backpropagation learning algorithm: classification and comparision," Journal of KIISE, vol. 18, no. 6, pp. 649-660, Dec. 1991.