\r何 坚^{1, 2}，张子浩¹，王伟东\r^{1, 2}\r
\r
AuthorsHTML:\r何 坚^{1, 2}，张子浩¹，王伟东\r^{1, 2}\r
\r
AuthorsListE:\rHe Jian^{1, 2}，Zhang Zihao¹，Wang Weidong\r^{1, 2}\r
\r
AuthorsHTMLE:\rHe Jian^{1, 2}，Zhang Zihao¹，Wang Weidong\r^{1, 2}\r
\r
Unit:\r\r1. 北京工业大学信息学部，北京 100124；\r
\r\r2. 北京市物联网软件与系统工程技术研究中心，北京 100124\r
\r
\r
Unit_EngLish:\r1. Faculty of Information Technology，Beijing University of Technology，Beijing 100124，China；
2. Beijing Engineering Research Center for IOT Software and Systems，Beijing 100124，China\r
\r
Abstract_Chinese:\r针对社区老年人跌倒检测的低功耗、高准确率要求，本文在建立基于三轴加速度、角速度的人体活动模型基础上，采用低功耗ZigBee 和可在休眠状态采集并缓存数据的MPU6050 动作传感器设计构造人体活动感知模块，并设计了中断驱动的低功耗人体活动数据采集传输算法，实现老年人活动数据的低功耗采集与远距离传输；其次，在数据接收端应用滑动窗口技术实时接收和缓存人体活动的三轴加速度、角速度数据，将这些数据进行量程规范并映射成对应的RGB 3通道像素数据；最后，在分析人体日常活动与跌倒数据及其对应像素图差异的基础上，设计了面向跌倒检测的卷积神经网络(FD-CNN)，并结合互联网上公开的日常活动和跌倒数据进行网络训练和测试．实验结果证明FD-CNN 跌倒检测的准确率达到98.6%，系统的敏感度和特异性分别达到98.6%和99.8%，FD-CNN 相比已有的跌倒检测算法在系统准确率、敏感度和特异性等方面都有显著提高；相比已有基于蓝牙的跌倒检测系统，本系统的传输距离远、易组网，同时系统功耗更低，适合于社区老年人的跌倒检测与报警．\r
\r
Abstract_English:\rto the requirement of low power consumption and high accuracy of fall detection systems for the elderly in a community，a human body activity model based on tri-axial acceleration and angular velocity is first established. A sensor board integrated with low-power ZigBee and the MPU6050 sensor，which can sample and cache data in sleep mode，is developed. An interrupt-driven algorithm，which can collect and transmit the tri-axial acceleration and the angular velocity data of human activities through ZigBee technology under low power，is designed. Second，the data with regard to the tri-axial acceleration and angular velocity of human activities are received in real time by a server via the sliding window，and the range specification of the data is correspondingly mapped into three channel red-green-blue(RGB)pixels to realize the image representation of the data. Finally，on the basis of analyzing and comparing the differences between activities of daily living(ADLs)and fall images，a fall detection convolutional neural network(FD-CNN)algorithm is designed；the network is trained using ADLs and fall data published on the Internet. The experimental results show that the accuracy of the FD-CNN algorithm is 98.6%，and its sensitivity and
specificity are 98.6% and 99.8%，respectively. Compared with the existing fall detection algorithms，the FD-CNN algorithm has significantly superior accuracy，sensitivity，and specificity in terms of fall detection. Meanwhile，the system presented in this study has significant features，such as long transmission distance，easy networking，and lower power consumption，in comparison to the Bluetooth-based fall detection system. Hence，the proposed system is very suitable for fall detection and alarm applications for the elderly in a community.\r
\r
Keyword_Chinese:跌倒检测；ZigBee；低功耗；卷积神经网络\r

Keywords_English:fall detection；ZigBee；low power；convolutional neural network\r


PDF全文下载地址:http://xbzrb.tju.edu.cn/#/digest?ArticleID=6324