Implementation of Cushion Type Posture Discrimination System Using FSR Sensor Array

FSR 센서 어레이를 이용한 방석형 자세 판별시스템의 구현

  • Kim, Mi-Seong (Division of Computer Engineering, Dongseo University) ;
  • Seo, Ji-Yun (Division of Computer Engineering, Dongseo University) ;
  • Noh, Yun-Hong (Department of Computer engineering, Busan Digital University) ;
  • Jeong, Do-Un (Division of Computer Engineering, Dongseo University)
  • 김미성 (동서대학교 컴퓨터공학부) ;
  • 서지윤 (동서대학교 컴퓨터공학부) ;
  • 노윤홍 (부산디지털대학교 컴퓨터공학과) ;
  • 정도운 (동서대학교 컴퓨터공학부)
  • Received : 2019.03.12
  • Accepted : 2019.06.20
  • Published : 2019.06.30

Abstract

Recently, modern people are increasing the incidence of various musculoskeletal diseases due to wrong posture. Prevention is possible through proper posture habit, but it is not easy to recognize posture by oneself. Various studies have been conducted to monitor persistent posture in daily life, but most studies using constrained measurement methods and high-cost measurement equipment are not suitable for daily life. In this paper, we implemented a posture discrimination system using a FSR sensor array that can induce posture correction spontaneously through sitting posture monitoring in daily life. The implemented system is designed as a cushion type so it is easy to apply to existing chair. In addition, it can identify five most common postures in everyday life, and can monitor real-time through Android-based smart-phone monitoring application. For the performance evaluation of the implemented system, each posture was measured 50 times repeatedly. As a result, 97.6% accuracy was confirmed.

최근 현대인들은 잘못된 자세로 인해 다양한 근골격계 질환의 발병률이 높아지고 있다. 근골격계 질환의 근본적인 원인은 잘못된 자세 습관으로 발병한 경우가 많다. 근골격계 질환은 바른 자세 습관을 통해 예방이 가능하지만, 자세를 스스로 인식하여 교정하기는 쉽지 않다. 지속적인 자세 모니터링을 위하여 다양한 연구들이 수행되었으나, 기존 계측 시스템은 구속성 및 고비용으로 인해 일상생활에 적용하기가 적합하지 않다. 본 논문은 일상생활에서 착석 자세 모니터링을 통해 자발적으로 자세 교정을 유도할 수 있는 FSR 센서 어레이를 이용한 자세 판별 시스템을 구현하였다. 구현된 시스템은 방석 형태로 설계되어 기존에 보유하고 있는 의자에 적용이 용이하다. 또한, 일상생활에서 가장 대표적인 5가지 자세를 판별할 수 있으며, 안드로이드 기반의 스마트폰 모니터링 애플리케이션을 통해 실시간으로 모니터링이 가능하다. 시스템의 성능 평가를 위하여 각각의 자세를 50회씩 반복하여 측정하였으며, 98.88%의 높은 자세 판별 정확도를 확인하였다.

Keywords

References

  1. Kim JS, Hans Shin B, Kim SJ, Park HJ, "Work Posture Analysis for Preventing Musculoskeletal Disorders Using Kinect", 2016.
  2. Mun-Ky Song, Ji-Young Kong, "Effects of Sitting Habits and Physical Activity Levels on Spine and Pelvis Deformations in School Children", 2017.
  3. Health News, "Musculoskeletal Checkup Required to Improve Quality of Life", 2018.
  4. Sanyona Ma, Sangpyo Hong, Hyeon-min Shim, Jang-Woo Kwon, Sangmin Lee, "A study on Sitting Posture Recognition using Machine Learning", The Transactions of the Korean Institute of Electrical Engineers, 65(9), 1557-1563, 2016. https://doi.org/10.5370/KIEE.2016.65.9.1557
  5. Seung-Jin Moon, Yoon-Sung Park, "The Design and Implementation of the Position Calibration System Using Sensor on u-WBAN", Journal of Korean Institute of The Intelligent System, 20(2), 304-310, 2010. https://doi.org/10.5391/JKIIS.2010.20.2.304
  6. Yongjoo Cho, Kyoung Shin Park, "Design and Development of the Multiple Kinect Sensor-basd Exercise Pose Estimation System", Journal of The Korea Institute of Information and Communication Engineering, 21(3), 558- 567, 2017. https://doi.org/10.6109/jkiice.2017.21.3.558
  7. Ho-jin Ha, Chang-dong Lee, "Design of Algorithm for Guidance of Sitting Posture Correction Using Pressure Sensor and Image Processing Interpolation Technique", 2016.
  8. Yun-Hong Noh, Do-Un Jeong, "Implementation and Evaluation of Chair-type ECG Monitoring System using Unconstraint Electrode", The Korea Institute of Convergence Signal Processing, 2015.
  9. An YS, Kim KS, Song CG. "Posture guidance system using 3-axis accelerometer for scoliosis patient", ICS 2009 Information and Control Symposium, 2009.
  10. Jun JI, Park JI, "Posture-Correction-Guidance System Using Monocular Camera", Korean Broadcasting Engineering Conference, 2011.