Journal of Internet Computing and Services (인터넷정보학회논문지)

Korean Society for Internet Information (한국인터넷정보학회)
권호 표지

Selecting Minimized Input Features for Detecting Automatic Fall Detection Based on NEWFM

낙상 검출을 위한 NEWFM 기반의 최소의 특징입력 선택

  • 신동근 (삼육대학교 컴퓨터학부) ;
  • 이상홍 (경원대학교 전자계산학과) ;
  • 임준식 (경원대학교 컴퓨터소프트웨어학)
  • Published : 2009.06.30
Download PDF
⟨ Previous Next ⟩

Abstract

This paper presents a methodology for a fall detection using the feature extraction method based on the neural network with weighted fuzzy membership functions (NEWFM). The distributed non-overlap area measurement method selects the minimized number of input features by removing the worst input features one by one. Nineteen number of wavelet transformed coefficients captured by a triaxial accelerometer are selected as minimized features using the non-overlap area distribution measurement method. The proposed methodology shows that sensitivity, specificity, and accuracy are 95%, 97.25%, and 96.125%, respectively.

본 논문은 가중 퍼지소속함수 기반 신경망(Neural Network with Weighted Fuzzy Membership Functions, NEWFM)기반의 특징추출기법을 사용하여 낙상을 검출하는 방안을 제안하고 있다. 비중복면적 분산 측정법에 의해 중요도가 가장 낮은 특징입력을 하나씩 제거하면서 최소의 특징입력을 선택하였다. 특징입력으로써 가속도 센서를 통해 입력된 가속도 변화랑을 웨이블릿 변환한 33개의 계수들 중 비중복면적 분산측정법에 의해서 추출된 19개의 계수가 사용되었다. 제안된 방법으로 민감도가 95%, 특이도가 97.25%, 정확도가 96.125%를 나타내었다.

Keywords

References

  1. M.J.Mathie, B.G.Celler, N.H.Lovell, A.C.F.Coster, "Classification of basic daily movements using a triaxial accelerometer" Medical &Biological Engineering &Computing 2004, Vol. 42. 679~687 https://doi.org/10.1007/BF02347551
  2. Dean M. Karantonis, Nigel H. Lovell, "Implementation of a Real-Time Human Movement Classifier Using a Triaxial Accelerometer for Ambulatory Monitoring" IEEE Transactions on information technology in biomedicine, vol. 10, no. 1, jan 2006
  3. Amit Purwar, Do Un Jeong, Wan Young Chung, "Activity Monitoring from Real-Time Triaxial Accelerometer data using Sensor network" International Conference on Control, Automation and Systems 2007. Oct. 17-20 in COEX, Seoul, Korea
  4. L. Jatoba, U.Grobamann, "Development of a Self-Constructing Neuro-Fuzzy Inference System for Online Classification of Physical Movements" 2007. IEEE
  5. J. S. Lim and S. Gupta, "Feature Selection Using Weighted Neuro-Fuzzy Membership Functions," The 2004 International Conference on Artificial Intelligence(IC-AI'04), VOL. 1, pp. 1301-1315, Las Vegas, Nevada, USA. June 21-24, 2004.
  6. J. S. Lim, "Finding Fuzzy Rules by Neural Network with Weighted Fuzzy Membership Function," International Journal of Fuzzy Logic and Intelligent Systems, Vol. 4, No.2, pp.211-216, September, 2004. https://doi.org/10.5391/IJFIS.2004.4.2.211
  7. Carlijn V.C. Bouten, Karel T. M. Koekkoek, Maarten Verduin, Rens Kodde, Jan D. Janssen, "A treaxial accelerometer and portable data processing unit for the assessment of daily physical activity", IEEE Transactions on Biomedical Engineering, Vol.44, pp.136-147, 1997. https://doi.org/10.1109/10.554760
  8. 이승형, "가속도 센서를 이용한 행태 분석 모니터링 시스템 개발". 연세대학교 대학원, 2003.
  9. S-M Zhou and J. Q. Gan, "Constructing L2-SVM-Based Fuzzy Classifiers in High-Dimensional Space with Automatic Model Selection and Fuzzy Rule Ranking," IEEE Trans. on Fuzzy Systems, Vol. 15, No. 3, pp. 398-409, 2007 https://doi.org/10.1109/TFUZZ.2006.882464
  10. S. Mallat, "Zero Crossings of a Wavelet Transform," IEEE Trans. on Information Theory, Vol. 37, pp. 1019-1033, 1991. https://doi.org/10.1109/18.86995
  11. Joon S. Lim, "Finding Features for Real-Time Premature Ventricular Contraction Detection Using a Fuzzy Neural Network System", IEEE Trans. on Neural Networks, VOL. 20, No. 3, pp. 522-527, MARCH 2009. https://doi.org/10.1109/TNN.2008.2012031