共查询到15条相似文献,搜索用时 187 毫秒
1.
2.
针对常见证据冲突度量方法适应性差、准确性低的问题,提出了一种基于Pignistic概率转换和奇异值分解的证据冲突度量方法。首先通过Pignistic概率转换将证据焦元差异映射到信度差异上,构建证据复合信任函数矩阵。然后采用奇异值分解的方法提取矩阵特征,根据奇异值特性将矩阵特征空间划分为相似子空间和冲突子空间,综合考虑证据矩阵相似特性和冲突特性,将冲突子空间奇异值与相似子空间奇异值之比作为新的冲突度量因子。最后在全冲突场景、变信度场景、变焦元场景、焦元嵌套场景等多种证据冲突场景下将所提方法与常见方法进行了对比分析,结果表明所提方法具有适应性广、准确性高、稳定性好的特点。 相似文献
3.
4.
现有的冲突证据组合修正方法仅从证据距离、模糊度等描述信息不确定性的一个或几个方面对证据体的基本概率分配函数进行修正,对证据的关联性考虑不够充分。该文提出基于信息总不确定度的冲突证据组合修正新方法。该文在笛卡尔乘积的基础上定义提出组合总不确定度的概念,并给出根据融合前各证据体总不确定度预测融合后证据体组合总不确定度值域的方法。对冲突证据,利用各证据体总不确定度与组合总不确定度的比值,求出对证据基本概率分配函数的修正权重,再根据Dempster规则进行加权平均组合。信息融合的算例分析结果表明,与现有方法相比,该方法融合结果的总不确定度更小,更有利于融合结果的后续决策分析与数据应用。 相似文献
5.
基于信任度和虚假度的证据组合方法 总被引:1,自引:0,他引:1
D-S证据理论在信息融合领域有着广泛的应用,但使用Dempster组合规则对高冲突证据进行合成时可能会得到反直观的结果,在应用中也存在“一票否决”的问题,为解决这些问题,提出一种改进的基于证据信任度和虚假度的证据加权组合方法。首先在证据相关系数的基础上定义了证据信任度,再结合证据虚假度的概念来确定各原始证据的权重,依此权重系数对各证据进行加权平均后利用Dempster组合规则对加权平均证据进行组合。数值算例表明,该组合方法可实现冲突证据的有效融合,与其他方法相比该方法具有更好的收敛性。 相似文献
6.
7.
一种有效处理冲突证据的组合方法 总被引:78,自引:0,他引:78
为了有效融合高度冲突的证据,提出一种新的基于证据距离的组合方法,首先引入了一个证据体距离函数,之后求出系统中各证据被其它证据所支持的程度,对支持度归一化后获得各个证据的可信度,并将可信度作为证据的权重,对系统中的证据加权平均后再利用Dempster组合规则实现信息融合,与其它方法比较,该方法在系统存在伪证据(干扰)时仍然能够有效快速地识别出目标。 相似文献
8.
提出了一种基于D-S证据理论的空中目标识别方法.该方法首先对目标特征进行提取,然后根据提取的特征利用模糊C均值聚类的方法进行基本概率分配,最后利用D-S组合公式进行融合识别.实例验证了算法的有效性. 相似文献
9.
针对证据理论应用过程中,冲突证据的组合问题和基本概率赋值函数难以确定的问题,提出了一种新的冲突证据的组合方法。该方法以修改模型为基础,而不改变Dempster组合规则的结构。首先,在充分考虑焦元属性之间及证据之间的相互关联性基础上,引入证据体距离函数,然后,求出系统中各证据被其他证据所支持的程度,对支持度归一化后获得各个证据的可信度,并将可信度作为证据的权重,再将平均证据代替冲突证据,最后利用Dempster组合规则实现信息融合。通过仿真实验,将该方法与现有方法进行了分析比较,结果表明应用该方法是一种有效可行的证据组合方法。 相似文献
10.
11.
The situation of high conflict between evidences and one ballot veto cannot be solved by classical D-S rule,and the results obtained from classical D-S rule are contrary to the facts.To solve this problem,a new standard to measure conflicts between evidences was proposed based on the combination of Pignistic function transformation and correlation coefficient,and also a novel kind of weighted combination method which was applied to measure conflicts between evidences was put forward according to the standard.After that,a support matrix was constructed based from which the credibility of evidence was obtained,and the weighted average method was used to revise the evidence.Finally,the combination was accomplished by using Dempster’s rule.The result of numerical examples shows that it’s effective to solve the combination of conflicting evidence.Compared with other methods,the proposed method has good astringency. 相似文献
12.
13.
To overcome the invalidation problem of Dempster rule with high conflict,a weighted combination method based on degree of credibility and certainty was proposed.Firstly,the cosine similarity was modified to hold the ability to measure the evidence conflict when multi-subset focal elements were included,followed by the building of evidence credibility model.Secondly,the evidence certainty model based on precision and entropy was presented,which can both reflect the evidence’s degree of multi-subset focal elements and the dispersion degree of probability assignment.Then the weighted coefficient was determined by credibility and certainty.Finally,the normalized weighted coefficient was used to average the basic probability assignment,and the final combination result can be obtained according to Dempster rule.Numerical examples show that,compared with other traditional weighted combination methods,the proposed approach has made better performance in reducing conflict and accelerating convergence. 相似文献
14.
To deal with the shortcomings encountered when using the existing similarity/dissimilarity measures to quantify evidence conflict,a new dissimilarity measure called power-Pignistic probability distance was defined.Furthermore,a weighted evidence combination method was proposed based on power-Pignistic probability distance.The conflict degree between two pieces of evidence was quantified by the power-Pignistic probability distance.After that,a similarity measure matrix was constructed,based on which the credibility of evidence was obtained.Then the weighted average method was used to revise the evidence.Finally,the fusion was accomplished by using Dempster’s rule.The results of the numerical examples show the efficiency and rationality of the proposed method. 相似文献