欢迎您！东篱公司
退出
-
申报数据库
-
立项数据库
-
成果数据库
-
项目获奖数据库
中文摘要：
针对基于传感器的行为识别系统中通道数据缺失问题,采用耦合隐马尔可夫模型提出了一个多传感器数据融合的自适应行为识别方法,该方法充分挖掘了不同传感器之间数据的关联性和人体行为中身体不同部位之间的协作性。实验分析了站立、行走、坐、躺四种行为,结果表明该方法的识别率在84%以上,并且与其他相关方法相比,具有较高的识别率和自适应能力。
英文摘要：
Aiming at the problem that activity recognition system based on sensor missed channel data, this paper proposed a self-adaptive activity recognition method of multi-sensor data fusion which used the coupled hidden Markov models. This meth- od fully mined the correlation among different sensor data and human activity in the collaboration among the different parts of the body. Experimental analysis of the four kinds of activity included standing, walking, sitting, lying, the results show that the recognition rate of this method is more than 84%. And compared with other related methods, the proposed method has high recognition rate and self-adaptive ability.
同期刊论文项目
同项目期刊论文
Integration technology of collaborative computing system over multiple virtual machines oriented for
期刊信息
位置：