Self-Adaptive and Real-Time Pre-Fall Detection

doi:10.13438/j.cnki.jdzk.2021.03.006

Abstract

Abstract: To detect falls before falling and to provide basis for fall prevention, this study proposes a self adaptive pre-fall detection method that combines SVM and threshold method. Experiment results show that this method has a longer interval time than the artifical threshold and SVM, and has higher recall rate and specificity than SVM. The self-adaptive pre-fall detection method can detect the fall before the fall impact.

Key words: pre-fall detection, impact, self-adaptive, real-time, SVM

XIE Jing, YANG Panlong, WEI Xing. Self-Adaptive and Real-Time Pre-Fall Detection[J]. Journal of Jishou University(Natural Sciences Edition), 2021, 42(3): 34-40.

References

[1] RUBENSTEINLAURENCE Z. Falls in Older People: Epidemiology, Risk Factors and Strategies for Prevention[J]. Age and Ageing, 2006, 35(Suppl-2): 37-41.
[2] CIPPITELLI ENEA, FIORANELLI FRANCESCO, GAMBI ENNIO, et al. Radar and RGB-Depth Sensors for Fall Detection: A Review[J]. IEEE Sensors Journal, 2017, 17(12): 3585-3604.
[3] NOURY NORBERT, FLEURY ANTHONY, RUMEAU PIERRE, et al. Fall Detection—Principles and Methods[C]. 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Lyon, France: IEEE, 2007: 1663-1666.
[4] TINETTI M E, WILLIAMS C S. Falls, Injuries Due to Falls, and the Risk of Admission to a Nursing Home[J]. The New England Journal of Medicine, 1997, 337(18): 1279-1284.
[5] LU Xianling, WANG Hongbin, WANG Yingying, et al. Human Fall Detection Method Based on Acceleration Sensor[J]. Journal of Computer Applications, 2013, 30(4): 1109-1111.
[6] CHEN Long, MA Ting, LIU Songsong, et al. Posture Estimation by Bayesian Network with Belief Propagation[C]. 2013 IEEE Region 10 Conference. Xi’an, China: IEEE, 2013: 1-4.
[7] DUAN Kaibo, KEERTHI SATHIYA S. Which is the Best Multiclass SVM Method? An Empirical Study[C]∥ OZA NIKUNJ C, POLIKAR ROBI, KITTLER JOSEF, et al. Multiple Classifier Systems. 6th International Workshop, MCS 2005. Seaside, CA, USA: Springer-Verlag, 2005: 278-285.
[8] ERDOGAN SENOL ZAFER, BILGIN TURGAY TUGAY, CHO JUPHIL. Fall Detection by Using K-Nearest Neighbor Algorithm on WSN Data[C]. 2010 IEEE Globecom Workshops. Miami, FL, USA: IEEE, 2010: 2054-2058.
[9] LIM DONGHA, PARK CHULHO, KIM NAM HO, et al. Fall-Detection Algorithm Using 3-Axis Acceleration: Combination with Simple Threshold and Hidden Markov Model[J]. Journal of Applied Mathematics, 2014, 9(7): 342-351.
[10] AZIZ OMAR, MUSNGI MAGNUS, PARK EDWARD J, et al. 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 Non-Fall Trials[J]. Medical and Biological Engineering and Computing, 2017, 55(1): 45-55.
[11] NYAN M N,TAY FRANCIS E H, MURUGASU E. A Wearable System for Pre-Impact Fall Detection[J]. Journal of Biomechanics, 2008, 41(16): 3475-3481.
[12] SHI Guangyi, CHAN CHEUNG SHING, LI WEN JUNG, et al. Mobile Human Airbag System for Fall Protection Using MEMS Sensors and Embedded SVM Classifier[J]. IEEE Sensors Journal, 2009, 9(5/6): 495-503.
[13] SHAN Shaoming, YUAN Tao. A Wearable Pre-Impact Fall Detector Using Feature Selection and Support Vector Machine[C]. IEEE 10th International Conference on Signal Processing Proceedings. Beijing, China: IEEE, 2010: 1686-1689.
[14] WU Ge, XUE Shuwan. Portable Preimpact Fall Detector with Inertial Sensors[J]. IEEE Transaction on Neural Systems and Rehabilitation Engineering, 2008, 16(2): 178-183.
[15] BOURKE A K, O'DONOVAN K J, LAIGHIN G. The Identification of Vertical Velocity Profiles Using an Inertial Sensor to Investigate Pre-Impact Detection of Falls[J]. Medical Engineering and Physics, 2008, 30: 937-946.
[16] BOURKE A K, O'BRIEN J V, LYONS G M. Evaluation of a Threshold-Based Tri-Axial Accelerometer Fall Detection Algorithm[J]. Gait and Posture, 2007, 26(2): 194-199.
[17] KAU LIH-JEN, CHEN CHIH-SHENG. A Smart Phone-Based Pocket Fall Accident Detection, Positioning, and Rescue System[J]. IEEE Journal of Biomedical and Health Informatics, 2015, 19(1): 44-56.
[18] TAMURA TOSHIYO, YOSHIMURA TAKUMI, SEKINE MASAKI, et al. A Wearable Airbag to Prevent Fall Injuries[J]. IEEE Transactions on Information Technology in Biomedicine, 2009, 13(6): 910-914.
[19] 瓮恒,申圳,王振亚.一种自动保护及呼救的人体智能气囊[J].信息通信,2012(6):67-68.
[20] YAO Mian, ZHANG Qi, LI Menghua, et al．A Wearable Pre-Impact Fall Early Warning and Protection System Based on MEMS Inertial Sensor and GPRS Communication[C]∥ IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks. Cambridge: IEEE, 2015: 1-6.
[21] YAO Mian, MA Yingnan, GAO Xing, et al. Wearable Fall Warning Protection System Based on Inertial Sensing[J]. Integrated Technology, 2015, 4(5): 69-77.
[22] AZIZ OMAR, RUSSELL COLIN M, PARK EDWARD J, et al. The Effect of Window Size and Lead Time on Pre-Impact Fall Detection Accuracy Using Support Vector Machine Analysis of Waist Mounted Inertial Sensor Data[C]. 36th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Chicago: IEEE, 2014: 30-33.
[23] SU Yiwen, LIU Daliang, WU Yingfeng. A Multi-Sensor Based Pre-Impact Fall Detection System with a Hierarchical Classifier[C]. 9th International Congress on Image and Signal Processing, BioMedical Engineering and Informatics. Datong, China: IEEE, 2016: 1727-1731.
[24] RESCIO GABRIELE, LEONE ALESSANDRO, SICILIANO PIETRO. Supervised Machine Learning Scheme for Electromyography-Based Pre-Fall Detection System[J]. Expert System with Applications, 2018, 100(15): 95-105.
[25] WU Yinfeng, SU Yiwen, FENG Renjian, et al. Wearable-Sensor-Based Pre-Impact Fall Detection System with a Hierarchical Classifier[J]. Measurement, 2019, 140(7): 283-292.