Smart Media Journal (스마트미디어저널)

THE KOREAN INSTITUTE OF SMART MEDIA (한국스마트미디어학회)
권호 표지
DOI QR코드

DOI QR Code

Fall detection based on acceleration sensor attached to wrist using feature data in frequency space

주파수 공간상의 특징 데이터를 활용한 손목에 부착된 가속도 센서 기반의 낙상 감지

  • 노정현 (서경대학교 컴퓨터공학과) ;
  • 김진헌 (서경대학교 컴퓨터공학과)
  • Received : 2021.06.14
  • Accepted : 2021.10.01
  • Published : 2021.09.30
Download PDF
⟨ Previous Next ⟩

Abstract

It is hard to predict when and where a fall accident will happen. Also, if rapid follow-up measures on it are not performed, a fall accident leads to a threat of life, so studies that can automatically detect a fall accident have become necessary. Among automatic fall-accident detection techniques, a fall detection scheme using an IMU (inertial measurement unit) sensor attached to a wrist is difficult to detect a fall accident due to its movement, but it is recognized as a technique that is easy to wear and has excellent accessibility. To overcome the difficulty in obtaining fall data, this study proposes an algorithm that efficiently learns less data through machine learning such as KNN (k-nearest neighbors) and SVM (support vector machine). In addition, to improve the performance of these mathematical classifiers, this study utilized feature data aquired in the frequency space. The proposed algorithm analyzed the effect by diversifying the parameters of the model and the parameters of the frequency feature extractor through experiments using standard datasets. The proposed algorithm could adequately cope with a realistic problem that fall data are difficult to obtain. Because it is lighter than other classifiers, this algorithm was also easy to implement in small embedded systems where SIMD (single instruction multiple data) processing devices were difficult to mount.

낙상사고는 언제, 어디에서 일어날지 예측하기 어렵다. 또한 신속한 후속 조치가 수행되지 않으면 생명의 위협으로 이어지므로 낙상사고를 자동으로 감지할 수 있는 연구가 필요하게 되었다. 자동적인 낙상사고 감지기법 중 손목에 부착된 IMU 센서를 활용한 기법은 움직임이 많아 낙상사고 검출이 어렵지만, 착용의 간편함과 접근성이 뛰어난 기법으로 인식되고 있다. 낙상 데이터 확보의 어려움을 극복하기 위해 본 연구는 KNN과 SVM과 같은 머신러닝으로 적은 데이터를 효율적으로 학습하는 알고리즘을 제안한다. 또한, 이들 수학적 분류기의 성능을 높이기 위해 본 연구에서는 주파수 공간에서 취득한 특징 데이터를 활용하였다. 제안된 알고리즘은 표준 데이터세트를 활용한 실험을 통해 모델의 파라미터와 주파수 특징 추출기의 파라미터를 다각화하여 그 영향을 분석하였다. 제안된 알고리즘은 학습 데이터를 확보하기 어려운 현실적인 문제에 적절히 대처할 수 있었다. 또한 본 알고리즘이 다른 분류기보다 경량화되어 있기 때문에 SIMD(Single Instruction Multiple Data) 처리장치 탑재가 어려운 소형 임베디드시스템에도 구현이 용이했다.

Keywords

Acknowledgement

이 논문은 2019년도 문화체육관광부 및 한국콘텐츠진흥원의 연구개발사업으로 수행된 연구임 (No. R2019020008).

References

  1. 질병관리청 국가건강정보포털 낙상(2020), https://health.kdca.go.kr/healthinfo/biz/health/gnrlzHealthInfo/gnrlzHealthInfo/gnrlzHealthInfoView.do?cntnts_sn=1743 (accessed May, 12, 2021)
  2. World Health Organization. Falls.(2021), https://www.who.int/en/news-room/fact-sheets/detail/falls (accessed May 12, 2021)
  3. Koldo de Miguel, et al., "Home Camera-Based Fall Detection System for the Elderly," Sensors, vol. 17, no. 12, article no.:2864, Dec., 2017.
  4. R. Igual, C, Medrano, and I Plaza, "Challenges, issues and trends in fall detection systems," BioMed Eng OnLine, vol. 12, article no.:66, Jul., 2013.
  5. P. Jantaraprim, P. Phukpattaranont, C. Limsakul and B. Wongkittisuksa, "Evaluation of fall detection for the elderly on a variety of subject groups," i-CREATe'09:Proceedings of the 3rd International Convention on Rehabilitation Engineering & Assistive Technology, No. 11, pp. 1-4, Apr., 2009.
  6. C. Lai, Y. Huang, J. H. Park and H. Chao, "Adaptive Body Posture Analysis for Elderly-Falling Detection with Multisensors," IEEE Intelligent Systems, vol. 25, no. 2, pp. 20-30, Mar.-Apr., 2010. https://doi.org/10.1109/MIS.2010.39
  7. T. Zhang, J. Wang, L. Xu and P. Liu, "Fall Detection by Wearable Sensor and One-Class SVM Algorithm," Intelligent Computing in Signal Processing and Pattern Recognitio, vol. 345, pp. 858-863, 2006. https://doi.org/10.1007/978-3-540-37258-5_104
  8. S. Shan, and T. Yuan, "A Wearable Pre-Impact Fall Detector Using Feature Selection and Support Vector Machine," IEEE 10th INTERNATIONAL CONFERENCE ON SIGNAL PROCESSING PROCEEDINGS, pp. 1686-1689, Beijing, China, Oct., 2010.
  9. Samad Barri Khojasteh, et al., "Improving Fall Detection Using an On-Wrist Wearable Accelerometer," Sensors, vol. 18, no. 5, article no.:1350, Apr. 2018.
  10. S. J. Preece, J. Y Goulermas, L. P J Kenney, D. Howard, K. Meijer and R. Crompton, "Activity identification using body-mounted sensors--a review of classification techniques," Physiol Meas., vol. 30, no. 4, Apr., 2009.
  11. U. Maurer, A. Rowe, A. Smailagic and D. Siewiorek, "Location and activity recognition using eWatch: A wearable sensor platform," Ambient Intell. Everday Life, pp. 86-102, 2006.
  12. L. Bao and S. S. Intille, "Activity recognition from user-annotated acceleration data," Pers Comput, pp. 1-17, 2004.
  13. N. Wang, E. Ambikairajah, N. H. Lovell and B. G. Celler, "Accelerometry based classification of walking patterns using time-frequency analysis," 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 4899-4902, Lyon, France, Aug. 2007.
  14. Nicolas Zurbuchen, et al., "A Machine Learning Multi-Class Approach for Fall Detection Systems Based on Wearable Sensors with a Study on Sampling Rates Selection," Sensors, vol. 21, no. 3, article no.:938, Jan., 2021.
  15. A. Ejupi, C. Galang, O. Aziz, EJ. Park and S. Robinovitch, "Accuracy of a wavelet-based fall detection approach using an accelerometer and a barometric pressure sensor," 39th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), pp. 2150-2153, Jeju, Korea (South), Jul., 2017.
  16. Turke Althobaiti, et al., "Triaxial Accelerometer-Based Falls and Activities of Daily Life Detection Using Machine Learning," Sensors, vol. 20, no. 13, article no.:3777, Jul., 2020.
  17. Francisco Luna-Perejon, et al., "Wearable Fall Detector Using Recurrent Neural Networks," Sensors, vol. 19, no. 22, article no.:4885, Nov., 2019.
  18. D. Kraft, S. Karthik and B. Gerald, "Deep Learning Based Fall Detection Algorithms for Embedded Systems, Smartwatches, and IoT Devices Using Accelerometers," Technologies, vol. 8, no. 4, Nov., 2020.
  19. Eduardo Casilari, Jose A. Santoyo-Ramon and Jose M. Cano-Garcia, "UMAFall: A Multisensor Dataset for the Research on Automatic Fall Detection," Procedia Computer Science, vol. 110, Pages 32-39, 2017. https://doi.org/10.1016/j.procs.2017.06.110
  20. Jose A. Santoyo-Ramon, Eduardo Casilari and Jose M. Cano-Garcia, "Analysis of a Smartphone-Based Architecture with Multiple Mobility Sensors for Fall Detection with Supervised Learning," Sensors, vol. 18, no. 4, Apr., 2018.
  21. Lourdes Martinez-Villasenor, et al., "UP-Fall Detection Dataset: A Multimodal Approach," Sensors, vol. 19, no. 9, Apr., 2019.
  22. S. J. Preece, J. Y. Goulermas, L. P. J. Kenney and D. Howard, "A Comparison of Feature Extraction Methods for the Classification of Dynamic Activities From Accelerometer Data," IEEE Transactions on Biomedical Engineering, vol. 56, no. 3, pp. 871-879, Mar., 2009. https://doi.org/10.1109/TBME.2008.2006190