Abstract: A cloud intelligent real-time fall detection system is developed to accurately judge the aged people’s fall and get timely help. This cloud intelligent system effectively integrates the new MEMS senor technology, data communication technology and control technology. Firstly, the system collects the data of aged population’s ADL（Activities of Daily Living） through the detecting device. And then the Support Vector Machine（SVM） algorithm is used to deal with the data. Finally, the characteristic data is output and uploaded to the internet of things cloud platform through GPRS, simultaneously sending the fall SMS to the guardian’s mobile phone. The experimental results show that the accuracy of fall judgment is 100 percent, and by using phone APP or the internet of things cloud platform the guardian can view the aged population’s real-time ADL and get the fall SMS. This device can break through the long-distance limit to effectively care for the aged population.

Key words: real-time fall detection, Support Vector Machine（SVM）, remote monitoring, cloud intelligence, internet of things

摘要： 为了准确判断独居老人跌倒并且及时救助，设计开发了一种云智能实时检测系统。该云智能检测系统有效地集成了新型MEMS传感器、通信以及控制等先进技术，实现准确判断、实时检测和及时救助功能。系统通过检测装置采集独居老人日常活动数据，通过支持向量机算法（SVM）对数据进行处理，输出特征数据并通过GPRS将数据上传至物联网云平台，同时将跌倒信息发送给监护人手机。并对各种跌倒状况进行各50次实验，其结果表明：跌倒判断的正确率为100%；并且通过手机APP或者物联网云平台监护人可以实时查看独居老人日常活动，同时能接收跌倒消息以便及时救助。该装置可以突破距离限制，远程实时有效监护独居老人。

关键词: 实时跌倒检测, 支持向量机算法（SVM）, 远程监护, 云智能, 物联网