摘要
为了既能提高系统人体行为的识别率,又能降低系统能耗,提出了基于多传感器的人体行为识别系统。通过对滑动时间窗内传感器数据信息进行数学统计,提取数据特征;并通过用weka软件对数据的这些特征进行分析,设计出基于决策树的两层分类识别算法,来对8种常见人体行为进行识别。实验结果表明:该系统在降低了系统能耗同时系统识别率较高,平均识别率达到93.12%,系统便于携带且具有很强的实用性。
The multi-sensor-based human behavior recognition system is proposed to improve recognition rate of system on human behavior, and can reduce system energy consumption. Data features are extracted from sensor data information by mathematical statistics means within sliding time window;by using weka software, analyze data festures,a two-layer classification recognition algorithm based on decision tree is designed to recognize eight common human behaviors. Experimental result demonstrates that this system achieves high recognition rate of 93.12 %, and reduces system energy consumption, and it is portable and has strong practical applicability.
出处
《传感器与微系统》
CSCD
2016年第3期89-91,95,共4页
Transducer and Microsystem Technologies
基金
国家自然科学基金资助项目(61171190)
关键词
识别率
系统能耗
数据特征
决策树
recognition rate
system energy consumption
data features
decision tree
