针对D-S证据理论的冲突证据融合问题进行了研究,通过对证据进行冲突检验及修正弥补了D-S证据理论在处理冲突证据时的不足。采用了加性策略对事件进行排序的方法,找出证据支持最大的q个事件,就是最有可能是识别结论的q个事件,对其进行冲突检验及修正。解决了D-S证据合成方法组合冲突证据时出现的问题,保证了非冲突证据的有效合成。通过仿真试验表明该算法能有效地排除干扰,得出了符合实际的组合结果。
D-S evidence combination can not proceed if the evidence totally collides with each other highly, and the combination result can not keep accord with the real condition when the evidence seriously conflicts. To solve this problem, this paper presents a new method to verify and modify the conflicting evidences. In this method, additive strategy is adopted to make events to be descending sort firstly, then the q events which are most likely to be recognition results are sought out. Next, these events are verified and modified by using the method proposed in this paper. Finally, simulation experiments are conducted to demonstrate the rationality of this new improved algorithm when dealing with conflicting evidences. Although evidences conflict one another highly, the combination result still satisfies the practical situation.