DOI QR코드

DOI QR Code

Extraction of Motion Parameters using Acceleration Sensors

  • Lee, Yong-Hee (Dept. of Computer Engineering, Halla University) ;
  • Lee, Kang-Woo (Dept. of Computer Engineering, Halla University)
  • Received : 2019.09.16
  • Accepted : 2019.10.23
  • Published : 2019.10.31

Abstract

In this paper, we propose a parametric model for analyzing the motion information obtained from the acceleration sensors to measure the activity of the human body. The motion of the upper body and the lower body does not occur at the same time, and the motion analysis method using a single motion sensor involves a lot of errors. In this study, the 3-axis accelerometer is attached to the arms and legs, the body's activity data are measured, the momentum of the arms and legs are calculated for each channel, and the linear predictive coefficient is obtained for each channel. The periodicity of the upper body and the lower body is determined by analyzing the correlation between the channels. The linear predictive coefficient and the periodic value are used as data to measure the type of exercise and the amount of exercise. In the proposed method, we measured four types of movements such as walking, stair climbing, slow hill climbing, and fast hill descending. In order to verify the usefulness of the parameters, the recognition results are presented using the linear predictive coefficient and the periodic value for each motion as the neural network input.

본 논문에서는 인체의 활동량을 측정하기 위해 가속도 센서로 부터 얻은 운동신호를 파라미터로 모델링 하는 방법을 제안한다. 상체와 하체의 움직임이 동시에 일어나지 않는 경우, 현재의 단체널 방식의 운동량 분석방법은 많은 오차를 수반하게 된다. 본 연구에서는 3축 가속도 센서를 팔과 다리에 부착하고 인체의 활동을 측정한 후, 각 채널 별로 팔과 다리의 운동량을 계산하고, 채널별로 선형예측계수를 얻는다. 또한, 상체와 하체운동간의 교차상관도를 측정함으로써 상체와 하체의 주기성을 판단하게 된다. 선형예측계수와 주기 값은 운동의 종류와 이에 따른 운동량을 측정하는 자료로 이용하게 된다. 결과에서 제안한 방법의 유효성을 확인하기 위해 계단내려가기, 계단오르기, 언덕오르기, 언덕내려가기 등의 4가지 운동을 측정하여, 제시한 파라미터 모델의 유용성을 확인한다.

Keywords

References

  1. Mi Zhang and Alexander A Sawchuk, "Usc-had: a daily activity dataset for ubiquitous activity recognition using wearable sensors," in ACM Conference on Ubiquitous Computing, 2012.
  2. Muhammad Shoaib, et al., "Fusion of smartphone motion sensors for physical activity recognition," Sensors, 2014.
  3. Lho, Hyung-Suk ,Kim, Yun-Kyung ,Cho, We-Duke,"Real-Time Activity Monitoring Algorithm Using A Tri-axial", The KIPS Transactions : Part D, Vol.18 No.2, pp. 143-148, 2011.
  4. Yun Kyung Kim, Hyung-Suk Lho, We-Duke Cho, "Step Count Detection Algorithm and Activity Monitoring System Using a Accelerometer", Journal of the Institute of Electronics Engineers of Korea, Vol.48 No.2, pp.127-137, 2011.
  5. Megan P.Rothney, "Validity of Physical Activity Intensity Predictions by ActiGraph, Actical, and RT3 Accelerometers" Obesity, pp. 1946-1952, 2008.
  6. Maurice R. Puyau, "Prediction of Activity Energy Expenditure Using Accelerometers in Children" pp. 1625-1631, 2004.
  7. Choi, Hyun-Min, Kim, Jong-Kyung, Chun,Jong-Mok, Yang, Seung-Won, Nho, Ho-Sung," Validation of Activity Tracker for Assessing Energy Expenditure", The Korea Journal of Sports Science, Vol.20, No.6, pp. 1251-1260, 2011.
  8. HALL, CAMERON; FIGUEROA, ARTURO; FERNHALL, BO; KANALEY, JILL A,"Energy Expenditure of Walking and Running: Comparison with Prediction Equations", Medicine & Science in Sports & Exercise, Vol. 36, No. 12, pp 2128-2134, December 2004, 2011. https://doi.org/10.1097/00005768-200412000-00018
  9. Muni sekhar.K, Arpana bhide, Hemalatha, Shiva Krishna G, "Comparisin of Energy Expenditure During Walking and Running on Track before and after Traning in Young Health Adult Women", International Journal of Physiotherapy and Research, Vol. 1, No.4, pp.143-47. 2013.
  10. David Jacobi, "Physical Activity-Related Energy Expenditure With the RT3 and TriTrac Accelerometers in Overweight Adults" Obesity,pp. 950-956, 2007.
  11. Scott E. Crouter, "Estimating energy expenditure using accelerometers", Springer-Verlag,pp. 601-612, 2006.
  12. Shigeo Abe, "Support vector machines for pattern classication, vol. 53, Springer, 2005.
  13. Pierluigi Casale, et al., "Human activity recognition from accelerometer data using a wearable device," in Pattern Recognition and Image Analysis, 2011.the 2nd International Conference on Industrial Mechatronics and Automation, pp. 436-439, 2010.