摔倒检测简介
据报道，⼤约三分之⼀的65岁以上的⽼年⼈每年⾄少摔倒⼀次，这是导致⽼年⼈死亡和受伤的主要健康⻛险之⼀[1]。死亡率与等待帮助的时间之间的相关性呈正相关，因此，摔倒后独居⽼⼈⽐那些能在12⼩时内得到帮助的⽼⼈有更⼤的⽣命危险[2]。除了身体伤害外，摔倒还可能导致⽼⼈对摔倒产⽣恐惧，进⽽丧失⾃信⼼和⽣活⾃理能⼒[3]。及时准确地发现摔倒可以减少严重的后果，因此对于改善⽼年⼈的⽣活质量⾄关重要。
⾃1990年代以来，测摔倒检测技术的相关研究就蓬勃发展起来[4]。根据所使⽤的传感器和设备的类型，⾃动检测摔倒的技术可以⼤致分为两类：（I）基于⾮穿戴式传感器的⽅法（摄像头或其他环境传感器）[5] [6]和（II）基于可穿戴传感器的⽅法（惯性测量单元（IMU）或其他嵌⼊式传感器）[7] [8]。尽管基于⾮穿戴式摔倒检测系统可靠性已经⾜够⾼，但受到环境条件和覆盖区域的限制[9]。对于⽼年⼈⽽⾔，使⽤可穿戴设备是⼀种更实⽤且更具成本效益的解决⽅案，以在移动性和安装简便性⽅⾯⽀持其独⽴性和安全性。
腕戴式设备看起来像普通⼿表，⼏乎在所有情况下都可以接受。它既⼩巧⼜可靠，不会轻易脱落。它可以防⽔且功耗低，因此在淋浴，睡觉或换⾐服时也⽆需将其取下。因此，腕腕带式的摔倒检测器是⽼年⼈⽇常使⽤的很好选择。
近期我们发明了⼀种带有六轴惯性传感器腕戴式摔倒检测器，通过引⼊模糊逻辑算法实现了⾼精度和灵敏度的摔倒检测。该技术已在英国获得专利（GB2564167），并正在通过PCT(《专利合作条约》)（WO 2019/097248 A1）在其他国家落地。
[1] Noury N, Fleury A, Rumeau P, et al. (2007) Fall detection-principles and methods. In: 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Lyon, France, 22–26 August 2007, pp. 1663–1666. IEEE.
[2] Gurley RJ, Lum N, Sande M, et al. (1996) Persons found in their homes helpless or dead. New England Journal of Medicine 334(26): 1710–1716.
[3] Igual R, Medrano C and Plaza I (2013) Challenges, issues and trends in fall detection systems. Biomedical Engineering Online 12(1): 66.
[4] Lord CJ and Colvin DP (1991) Falls in the elderly: Detection and assessment. In: Proceedings of the Annual International Conference of the IEEE Engineering in Medicine and Biology Society Volume 13: 1991, Orlando, FL, USA, USA, 31 October-3 November 1991, pp. 1938–1939. IEEE.
[5] Er PV and Tan KK (2018) Non-intrusive fall detection monitoring for the elderly based on fuzzy logic. Measurement 124: 91–102.
[6] Yang L, Ren YY, Hu H and Tian B (2015) New fast fall detection method based on spatio-temporal context tracking of head by using depth images. Sensors 15(9): 23004–23019.
[7] Chen K-H, Hsu Y-W, Yang J-J, et al. (2017) Enhanced characteriza- tion of an accelerometer-based fall detection algorithm using a repository. Instrumentation Science & Technology 45(4): 382–391.
[8] SucerquiaA,Lo ́pezJandVargas-BonillaJ(2018)Real-life/real-time elderly fall detection with a triaxial accelerometer. Sensors (Basel) 18(4): 1101.
[9] Hijaz F, Afzal N, Ahmad T, et al. (2010) Survey of fall detection and daily activity monitoring techniques. In: 2010 International Con- ference on Information and Emerging Technologies, Karachi, Paki- stan, 14–16 June 2010, pp. 1–6. IEEE.
