DOI QR코드

DOI QR Code

Accident detection algorithm using features associated with risk factors and acceleration data from stunt performers

  • Jeong, Mingi (Industrial & Personal Safety Intelligence Research Section, Electronics and Telecommunications Research Institute) ;
  • Lee, Sangyeoun (Industrial & Personal Safety Intelligence Research Section, Electronics and Telecommunications Research Institute) ;
  • Lee, Kang Bok (Industrial & Personal Safety Intelligence Research Section, Electronics and Telecommunications Research Institute)
  • Received : 2021.06.08
  • Accepted : 2022.01.16
  • Published : 2022.08.10

Abstract

Accidental falls frequently occur during activities of daily living. Although many studies have proposed various accident detection methods, no high-performance accident detection system is available. In this study, we propose a method for integrating data and accident detection algorithms presented in existing studies, collect new data (from two stunt performers and 15 people over age 60) using a developed wearable device, demonstrate new features and related accident detection algorithms, and analyze the performance of the proposed method against existing methods. Comparative analysis results show that the newly defined features extracted reflect more important risk factors than those used in existing studies. Further, although the traditional algorithms applied to integrated data achieved an accuracy (AC) of 79.5% and a false positive rate (FPR) of 19.4%, the proposed accident detection algorithms achieved 97.8% AC and 2.9% FPR. The high AC and low FPR for accidental falls indicate that the proposed method exhibits a considerable advancement toward developing a commercial accident detection system.

Keywords

Acknowledgement

This work was supported by the Electronics and Telecommunications Research Institute (ETRI) grant funded by the Korean government (22ZR1100, A Study of Hyper-Connected Thinking Internet Technology by autonomous connecting, controlling, and evolving ways).

References

  1. C. H. Orces and H. Alamgir, Trends in Fall-related injuries Among Older Adults Treated in Emergency Departments in the USA, Inj. Prev. 20 (2014), 421-423. https://doi.org/10.1136/injuryprev-2014-041268
  2. World Health Organization (WHO), WHO global report on falls prevention in older age, WHO, Geneva, Switzerland, 2018 Available from: https://extranet.who.int/agefriendlyworld/wp-content/uploads/2014/06/WHO-Global-report-on-falls-prevention-inolder-age.pdf [last accessed May 2021].
  3. Centers for Disease Control and Prevention (CDC), WISQARS™, Web-based injury statistics query and reporting system, Available from: http://www.cdc.gov/injury/wisqars [last accessed July 2020].
  4. Consumer Injury Surveillance System (CISS), Analysis of risk cases for falling accident in older adults, Oct. 2016, Available from: https://www.kca.go.kr/smartconsumer/board/download.do?menukey=7301&fno=10014532&bid=00000146&did=1001991589 [in Korean], [last accessed May 2021].
  5. Y. Yang, V. Komisar, N. Shishov, B. Lo, A. M. B. Korall, F. Feldman, and S. N. Robinovitch, The effect of fall biomechanics on risk for hip fracture in older adults: A cohort study of video-captured falls in long-term care, J. Bone Miner. Res. 35 (2020), 1914-1922. https://doi.org/10.1002/jbmr.4048
  6. S. N. Robinovitch, F. Feldman, Y. Yang, R. Schonnop, P. M. Leung, T. Sarraf, J. Sims-Gould, and M. Loughin, Video capture of the circumstances of falls in elderly people residing in long-term care: An observational study, Lancet 381 (2013), no. 9860, 37-54.
  7. M. D. Neuman, J. H. Silber, J. S. Magaziner, M. A. Passarella, S. Mehta, and R. M. Werner, Survival and functional outcomes after hip fracture among nursing home residents, JAMA Intern. Med. 174 (2014), 1273-1280. https://doi.org/10.1001/jamainternmed.2014.2362
  8. Y. Kim, S. M. Baek, and B. C. Bae, Motion capture of the human body using multiple depth sensors, ETRI J. 39 (2017), no. 2, 181-190. https://doi.org/10.4218/etrij.17.2816.0045
  9. E. Casilari, R. Luque, and M. J. Moron, Analysis of android device-based solutions for fall detection, Sensors 15 (2015), no. 2, 17827-17894. https://doi.org/10.3390/s150817827
  10. D. Micucci, M. Marco, and N. Paolo, UniMiB SHAR: A dataset for human activity recognition using acceleration data from smartphones, Appl. Sci. 7 (2017), no. 10. https://doi.org/10.3390/app7101101
  11. E. Casilari, S. A. Jose, and M. C. Jose, UMAFall: A Multisensor dataset for the research on automatic fall detection, Procedia. Comput. Sci. 110 (2017), 32-39. https://doi.org/10.1016/j.procs.2017.06.110
  12. A. Sucerquia, D. L. Jose, and F. V. Jesus Francisco, SisFall: A fall and movement dataset, Sensors 17 (2017), no. 1, 198. https://doi.org/10.3390/s17010198
  13. O. Aziz, M. Musngi, E. J. Park, G. Mori, and S. N. Robinovitch, A comparison of accuracy of fall detection algorithms (threshold-based vs. machine learning) using waist-mounted tri-axial accelerometer signals from a comprehensive set of falls and nonfall trials, Med. Biol. Eng. Comput. 55 (2017), no. 1, 45-55. https://doi.org/10.1007/s11517-016-1504-y
  14. F. Gottwalt, C. Elizabeth, and D. Tharam, CorrCorr: A feature selection method for multivariate correlation network anomaly detection techniques, Comput. Secur. 83 (2019), 234-245. https://doi.org/10.1016/j.cose.2019.02.008
  15. D. H. Mazumder and R. Veilumuthu, An enhanced feature selection filter for classification of microarray cancer data, ETRI J. 41 (2019), no. 3, 358-370. https://doi.org/10.4218/etrij.2018-0522
  16. J. Oxley, S. O'Hern, D. Burtt, and B. Rossiter, Fall-related injuries while walking in victoria, Feb. 2016, Available from: https://www.victoriawalks.org.au/Assets/Files/Fall-Related-Injuries-While-Walking-Report.pdf [last accessed May 2021].
  17. K. M. DeGoede, J. A. Ashton-Miller, and A. B. Schultz, Fall-related upper body injuries in the older adult: A review of the biomechanical issues, J. Biomech. 36 (2003), no. 7, 1043-1053. https://doi.org/10.1016/S0021-9290(03)00034-4
  18. A. B. Peterson and R. K. Scott, Deaths from fall-related traumatic brain injury-United States, 2008-2017, MMWR Morb. Mortal. Wkly Rep. 69 (2020), no. 9, 225-230.
  19. L. Hazelhoff and H. Jungong, Video-based fall detection in the home using principal component analysis, (ACIVS 2008: Advanced Concepts for Intelligent Vision Systems, Juan-Les-Pins, France), Oct. 2008, pp. 298-309.
  20. A. Stinchcombe, N. Kuran, and S. Powell, Seniors' Falls in Canada: Second report: Key highlights, Chronic Dis. Inj. Canada 34 (2014), no. 2-3, 171-174. https://doi.org/10.24095/hpcdp.34.2/3.13
  21. R. T. Janice, Slip, trip, stumble, fall: An overview of falls in the elderly and how to prevent them, Aug. 2018, Available from: https://lermagazine.com/cover_story/slip-trip-stumble-fall-an-overview-of-falls-in-the-elderly-and-how-to-prevent-them [last accessed May 2021].
  22. G. Kowshik, J. Anudeep, P. V. Krishna, S. K. Vasudevan, and I. Shah, An inventive and innovative system to detect fall of old aged persons - a novel attempt with IoT, sensors and data analytics to prevent the post fall effects, Intern. J. Med. Eng. Inf. 12 (2020), no. 1, 1-18. https://doi.org/10.1504/ijmei.2020.10027423
  23. F. M. da Silva, M. da Silva Reis, M. H. de Matos, D. N. Barbosa, D. R. Soares, E. T. de Aquino Oliveira, A. M. dos Santos, and J. A. Rodrigues, Golden time: Analysis of the response time of the Mobile Urgency Care Service (Samu), Revista de Epidemiologia e Controle de Infeccao 10 (2020), no. 3, 270-275.
  24. C. Buse and T. Julia, Materialising memories: Exploring the stories of people with dementia through dress, Ageing Soc. 36 (2016), no. 6, 1115-1135. https://doi.org/10.1017/S0144686X15000185
  25. N. A. Neubauer and L. Liu, The significance of losing things: Evaluation of antecedent behaviors of dementia-related wandering in community and facility settings, June 17, 2020. Available from: https://www.futuremedicine.com/doi/full/10.2217/nmt-2019-0030 [last accessed May 2021].
  26. D. Anguita, A. Ghio, L. Oneto, X. Parra, and J. L. Reyes-Ortiz, Human activity recognition on smartphones using a multiclass hardware-friendly support vector machine, Intern. workshop on ambient assisted living, Berlin, Heidelberg, 2012.
  27. F. Karim, S. Majumdar, H. Darabi, and S. Harford, Multivariate LSTM-FCNs for time series classification, Neural Netw. 116 (2019), 237-245. https://doi.org/10.1016/j.neunet.2019.04.014
  28. A. D. Ahlam, S. Rubita, and H. M. Nasrul, Transfer Deep Learning Along with Binary Support Vector Machine for Abnormal Behavior Detection, IEEE Access 8 (2020), 61085-61095. https://doi.org/10.1109/access.2020.2982906
  29. Z. Xia, P. Li, K. Xiao, X. Meng, L. Han, and C. Yu, Sensor drift compensation based on the improved LSTM and SVM multi-class ensemble learning models, Sensors 19 (2019), no. 18. https://doi.org/10.3390/s19183844
  30. S. Rajesh and A. Sungheetha, An efficient dimension reduction based fusion of CNN and SVM model for detection of abnormal incident in video surveillance, J. Soft Comp. Paradigm 3 (2021), no. 2, 55-69. https://doi.org/10.36548/jscp.2021.2.001
  31. S. A. Taghanaki, M. R. Ansari, B. Z. Dehkordi, and S. A. Mousavi, Nonlinear feature transformation and genetic feature selection: improving system security and decreasing computational cost, ETRI J. 34 (2012), no. 6, 847-857. https://doi.org/10.4218/etrij.12.1812.0032