摘要
基于无线体域网的人体日常行为检测是老年人健康监护中的一个重要内容,为了提高系统检测结果的准确性,提出一种基于信号融合的日常行为检测方法:首先将电极片放置于受试者下肢特定的4块肌肉处,右脚穿戴特制的压力鞋,同时采集受试者6种日常动作时的表面肌电信号和足底压力信号,然后分别提取两种信号有效段的特征,最后将两类特征组合成混合向量,输入支持向量机。实验结果显示,采用该方法对6种动作的平均识别率为91.7%,大大高于采用一种源信号的识别方法。
In order to improve the performance of the monitoring system,this paper proposes a human body motion pattern recognition method.The method based on signal fusion:firstly,the study collect the surface electromyography(sEMG)from lower limbs of the human.At the same time,collect the pressure signal of the sole.Then extract the characteristics of the two signals separately.The characteristics of the two types of signals are combined and input into the SVM for classification.The experimental results show that the average recognition rate of the six motion modes y is 91.7%,which is better than the single source recognition results.
出处
《工业控制计算机》
2019年第1期56-57,共2页
Industrial Control Computer
基金
石河子大学应用基础研究青年项目(2015ZRKXYQ05)
关键词
表面肌电信号
足底压力信号
支持向量机
人体动作识别
surface electromyography
plantar pressure
support vector machine
human action recognition
