一种新的基于信任区间的信任熵  

A novel belief entropy based on belief interval

作　　者：彭泽辉 杨建平 李海滨[2] 聂晓波 高云峰 PENG Zehui;YANG Jianping;LI Haibin;NIE Xiaobo;GAO Yunfeng(School of Mechanical Engineering,Inner Mongolia University of Technology,Hohhot 010051,China;School of Science,Inner Mongolia University of Technology,Hohhot 010051,China)

机构地区：[1]内蒙古工业大学机械工程学院,呼和浩特010051 [2]内蒙古工业大学理学院,呼和浩特010051

出　　处：《内蒙古工业大学学报（自然科学版）》2023年第6期488-492,共5页Journal of Inner Mongolia University of Technology：Natural Science Edition

基　　金：内蒙古自治区自然科学基金项目(2022MS05021);内蒙古自治区直属高校基本科研业务费项目(JY20220276);内蒙古工业大学科学研究项目(ZZ202002)。

摘　　要：由于D-S(Dempster-Shafer)证据理论在处理信息不确定性方面具有巨大的优势,得到了广泛应用。在证据理论应用中,需要测量基于信任分配的不确定性。针对如何测量证据理论中的不确定性的问题,提出了一种新的信任熵,并且对新信任熵的属性进行了分析。新信任熵是基于香农熵的扩展,利用了信任区间来衡量证据理论的不确定性。最后通过几个经典数值算例对新信任熵的有效性进行了验证。结果表明,新的信任熵能够准确地测量D-S证据理论中的不确定性和不确定性的变化趋势,并且包含更多的不确定信息。D-S(Dempster-Shafer)evidence theory is widely used due to its significant advantages in handling information uncertainty.In the application of evidence theory,it is necessary to measure the uncertainty based on belief assignment.To address the issue of measuring uncertainty in the evidence theory,a new belief entropy was proposed and its properties were analyzed.The new belief entropy is an extension of Shannon entropy and utilizes belief intervals to measure the uncertainty of D-S evidence theory.Finally,the validity of the new belief entropy was verified through several classical values calculations.The results show that the new belief entropy can accurately measure the uncertainty and its variation trend in the D-S evidence theory,while encompassing more uncertain information.

关 键 词：D-S(Dempster-Shafer)证据理论 不确定性 香农熵 信任熵 

分 类 号：O213[理学—概率论与数理统计] TP391[理学—数学]