基于传感器节点可靠性模型的协同决策算法  

Collaborative decision algorithm using the reliability model of sensor motes

作　　者：邓遂[1] 曹红兵 沈杰 刘海涛[1,2] 

机构地区：[1]中国科学院上海微系统与信息技术研究所无线传感网络与通信重点实验室,上海200050 [2]无锡物联网产业研究院,江苏无锡214315

出　　处：《华中科技大学学报（自然科学版）》2012年第4期63-66,共4页Journal of Huazhong University of Science and Technology(Natural Science Edition)

基　　金：国家科技重大专项基金资助项目(2009ZX03006-001-02);国家重点基础研究发展计划资助项目(2011CB302901)

摘　　要：针对多传感器系统中的协同决策问题,先对传感器节点的可靠性进行了分析和建模,从不同传感器节点的信息处理结果之间相互支持和节点自身历史表现2个方面,得到影响传感器节点可信度的2组参数;然后在D-S证据理论相关研究的基础上提出一种协同决策算法,并采用蒙特卡罗方法对协同决策算法进行了仿真验证.仿真结果表明:协同决策算法的平均决策正确率比现有算法提高了2.0%～10.8%,并且在证据严重冲突的情况下能获得比其他方法更好的决策效果.To solve the collaborative decision problem in multi-sensor system,the reliability of sensor motes from the relationship between the information processing results and the historical performance of different motes,which generates two groups of parameters related with the reliability of sensor motes,was analyzed.Then a collaborative decision algorithm based on the evidence theory was proposed with a collaborative decision model and its performance was evaluated by using the Monte Carlo simulation method.The simulation results show that the collaborative decision algorithm achieves 2.0~10.8 % higher accuracy rate than that of other methods and has better performance when evidences seriously conflict.

关 键 词：多传感器系统 信息融合 可靠性 决策 蒙特卡罗方法 证据理论 贝叶斯公式 

分 类 号：TN915[电子电信—通信与信息系统]