可穿戴式跌倒检测智能系统设计

摘要

为提高对老年人跌倒检测的正确率,设计一种可穿戴式跌倒检测系统.研制基于三轴加速度计的跌倒检测设备,给出系统硬件和软件的实现方案;提出基于反向传播(BP)神经网络的跌倒检测算法,将训练好的网络参数植入研制的可穿戴式跌倒检测设备,实现对跌倒的实时检测.实验结果表明:所研制的跌倒检测智能系统能够有效地区分跌倒与非跌倒,正确率达97.37％.%In order to improve the detection correct rate of falls in elderly people,a wearable fall detection intelligent system is designed.Fall detection device based on three axis accelerometer is developed,and hardware and software design schemes are presented;fall detection algorithm based on back propagation (BP)neural network is proposed,parameters of network after training are implanted into wearable fall detection equipment to realize real-time fall detection.Experimental results show that the developed fall detection intelligent system can effectively distinguish between fall and non-fall,and the correct rate is 97.37 ％.