IEEE J Biomed Health Inform. 2018 Nov;22(6):1929-1937. doi: 10.1109/JBHI.2017.2778271. Epub 2017 Nov 29.
Falls in older people are a major challenge to public health. A wearable fall detector can detect falls automatically based on kinematic information of the human body, allowing help to arrive sooner. To date, most studies have focused on the accuracy of an offline algorithm to distinguish real-world or simulated falls from activities of daily living, while neglecting the false alarm rate and battery life of a real device. To address these two important metrics, which significantly influence user compliance, this paper proposes a low-power fall detector using triaxial accelerometry and barometric pressure sensing. This fall detector minimizes power consumption using both hardware- and firmware-based techniques. Additionally, the fall detection algorithm used in this device is optimized to achieve a balance between sensitivity and false alarm rate, while minimizing the power consumption due to algorithm execution. The fall detector achieved a high sensitivity (91%) with a low false alarm rate (0.1149 alarms per hour), and a commercially-viable battery life (1125 days).
老年人跌倒对公共健康构成重大挑战。可穿戴跌倒探测器可根据人体运动信息自动检测跌倒，从而更快地提供帮助。迄今为止，大多数研究都集中在离线算法的准确性上，以区分真实世界或模拟的跌倒与日常生活活动，而忽略了真实设备的误报率和电池寿命。为了解决这两个重要的指标，这极大地影响了用户的依从性，本文提出了一种使用三轴加速度计和气压感测的低功耗跌倒探测器。该跌倒探测器使用硬件和固件技术来最小化功耗。此外，该设备中使用的跌倒检测算法经过优化，在灵敏度和误报率之间取得平衡，同时最小化由于算法执行而导致的功耗。该跌倒探测器的灵敏度高达 91%，误报率低至 0.1149 次/小时，电池寿命长（1125 天）。
