综合运用粗糙集方法与D-S证据理论可有效解决身份融合中的一些复杂问题。针对多传感器身份融合中D-S理论获取基本概率赋值存在主观性的问题,提出了一种新的基于粗糙集理论的证据获取和基本概率赋值客观确定方法;利用粗糙集中属性的重要性消除冗余传感器,减少了证据组合的冲突现象。在此基础上,给出了基于粗糙D-S理论的身份融合方法,最后以具体算例验证了方法的有效性。
Integrating rough sets and D-S evidence theory can efficiently solve some complex problems in identity fusion. First, to the question of subjectivity in getting basic probability assignment of DS theory for multi-sensors identity fusion, a new method of getting evidences and objective BPA based on Rough Sets theory is proposed. Then, conflict evidences are reduced by using the attribute weightiness of Rough Sets to eliminate redundant sensors. An identity fusion method based on Rough Sets and D-S theory is exposed with the foregoing research. Finally, the validity of the developed method is verified with a particular instance.