DOI QR코드

DOI QR Code

Berg Balance Scale Score Classification Study Using Inertial Sensor

관성센서를 이용한 버그균형검사 점수 분류 연구

  • 홍상표 (인하대학교 전자공학과) ;
  • 김연욱 (인하대학교 전자공학과) ;
  • 조우형 (인하대학교 전자공학과) ;
  • 좌경림 (인하대병원 재활의학과) ;
  • 정한영 (인하대병원 재활의학과) ;
  • 김규성 (인하대병원 이비인후과) ;
  • 이상민 (한국대학교 전자공학과)
  • Received : 2017.01.10
  • Accepted : 2017.02.26
  • Published : 2017.02.28

Abstract

In this paper, we present the score classification accuracy of BBS(Berg Balance Scale) which is the most commonly used balance evaluation tool using machine learning. Data acquisition was performed using the Noraxon system and an inertial sensor of Noraxon system was attached to the body in 8 locations (left and right ankle, left and right upper buttocks, left and right wrists, back, forehead). Based on the 3-axis accelerometer of the inertial sensor, the feature vector STFT(Short Time Fourier Transform) and SAM(Signal Area Magnitude) were extracted. Then, the items of the BBS were divided into static movement and dynamic movement depending on the operation characteristics, and the feature vectors were selected according to the sensor attachment positions which affect the score for each item of the BBS. Feature vectors selected for each item of BBS were classified using GMM(Gaussian Mixture Model). As a result of the accuracy calculation for 40 subjects, 55.5%, 72.2%, 87.5%, 50%, 35.1%, 62.5%, 43.3%, 58.6%, 60.7%, 33.3%, 44.8%, 89.2%, 51.8%, 85.1%, respectively.

본 논문에서는 균형평가도구 중 임상에서 가장 많이 사용되는 BBS(Berg Balance Scale)를 머신러닝 기법을 이용하여 점수 분류 정확도를 제시한다. 데이터취득은 Noraxon 시스템을 이용하여, 신체 8군데(왼쪽 오른쪽 발목, 왼쪽 오른쪽 엉덩이 위, 왼쪽 오른쪽 손목, 등(Back), 이마)에 관성센서를 부착하였다. 관성센서의 3축 가속도데이터를 기반으로 특징벡터 STFT(Short Time Fourier Transform), SAM(Signal Area Magnitude)를 추출하였다. 그 다음, BBS의 항목을 동작특성에 따라 정적인 동작(static movement)과 동적인 동작(dynamic movement)으로 나누었고, BBS의 각 항목에 대하여 점수에 영향이 있는 센서부착위치에 따라 특징벡터를 선별하였다. BBS의 항목마다 선별된 특징벡터는 GMM(Gaussian Mixture Model)을 이용하여 분류하였다. 실험대상자 40명에 대한 정확도 산출결과, 1번순으로 차례대로 55.5%, 72.2%, 87.5%, 50%, 35.1%, 62.5%, 43.3%, 58.6%, 60.7%, 33.3%, 44.8%, 89.2%, 51.8%, 85.1%의 분류 정확도를 확인하였다.

Keywords

References

  1. Dae-Hee Lee, Hyo-Lyun Roh, "The Effects of Increase in Balance Ability to One Leg Support Exercises for Adults Using Empty bottle", The Journal of Korean Society for Neurotherapy, vol. 17, no. 1, pp.1-5, 2013.
  2. Jeong-Tak Ryu, "The development of fall detection system using 3-axis acceleration sensor and tilt sensor", Journal of the Korea Industrial Information Systems Research, vol. 18, no. 4, pp. 19-24, 2013. https://doi.org/10.9723/jksiis.2013.18.4.019
  3. Jong-im Won, Ki-song Kim, "Concurrent Validity of the Functional Gait Assessment, Berg Balance Scale, and Timed Up and Go Test in Patients With Stroke", Physical Therapy Korea, vol. 18, no. 2, pp. 43-51, 2011.
  4. Su-Young Lee, Su-Jin Hwang, Journal of Special Education & Rehabilitation Science, vol. 50, no. 4, pp. 171-182, 2011.