多传感器数据融合的多准则决策模型

在多准则下考察传感器的融合权重, 提出一种新的多传感器数据融合方法. 通过多个性能指标折中估计传感器权重, 以降低决策的主观性和偶然性; 提出从不同融合级别来定义多个准则, 定性地提高了多准则的信息量; 在没有决策者对各准则偏好信息的情况下, 以最小化准则冗余度和最大化评价差异度为原则建立多目标优化模型对准则权重向量优化求解. 仿真实验结果表明, 相比于单准则和单层次的融合方法, 所提出方法具有更低的决策风险和更高的稳定性.

Multi-criteria decision model of multi-sensor data fusion

A new multi-sensor data fusion method using multi-criteria decision aid is proposed,which considers several indicators to reduce the decision subjectivity and contingency. Different fusion levels in the multi-sensor target recognition system is proposed to define multiple criteria, hence to gain more information of multi-criteria qualitatively. With no information about the preference of the decision maker for each criteria, the criteria weights vector can be obtained by solving a multi-objective optimization which intends to minimize the criteria redundancy and maximize the diversity factor of every criteria. The simulation results show that the proposed method performs better in anti-risk capability and stability than the mono-criteria and decision-making level method.