跌倒检测在远程健康监管系统中的应用研究  

Application research of fall detection in remote health care and supervisory system

作　　者：宁鸿成[1] 滕桂法[1] 赵洋[1] 董素芬[1] 

机构地区：[1]河北农业大学信息科学与技术学院,河北保定071001

出　　处：《微型机与应用》2011年第6期76-78,81,共4页Microcomputer & Its Applications

摘　　要：利用三轴加速度传感器对人体活动产生的加速度信号进行采集,提出了将数据分析分割成用户终端信号的预处理和在后台处理两部分。在用户终端采取基于1-class SVM分类算法对疑似数据进行提取,在后台通过分析不同动作事件下其能量损耗的阈值范围的不同进行跌倒判断,并分析了人体在特定时域的速度、位移以及倾角作为判断跌倒的辅助判据。实验表明,该应用能够为老年人的健康提供一种新的保障。It acquired acceleration signal by tri-axial accelerometer and advanced the data processing was divided into parts that is pre-processing at client terminal and background processing. At the client terminal, it makes a pre-processing method that suspected data is acquired based on one-class SVM classification algorithm. At the background, it analyzed different action which expended different threshold ranges of energy to judgment, and then analyzed the special temporal speed, displacement and angle as an auxiliary criterion for judgment. The experiments show that the application can offer a new guarantee for the elderly health.

关 键 词：跌倒检测 三轴加速度传感器 1-class SVM 

分 类 号：TP212.9[自动化与计算机技术—检测技术与自动化装置]