CAJ | 학술논문

针对 Dempster 方法在合成高度冲突的证据时结果与直观结论相悖的问题，提出了一种基于支持度的改进证据合成方法。首先根据证据之间的相似性程度判断是否存在证据冲突，对于总数在3条以上且存在冲突的证据组合，应用各证据的支持矩阵，通过其最大特征值对应的特征向量导出各证据的支持度系数，由此对基本概率分配（basic probability assignation，BPA）函数进行转化，再采用 Dempster 方法进行合成。仿真计算结果表明，该方法能有效处理冲突证据组合，克服了一票否决问题，相对于其它几种典型改进算法具有更快的识别速度，能进一步减小识别结果的不确定性，并保留了 Dempster 方法满足交换律、结合律的良好特性。
침대 Dempster 방법재합성고도충돌적증거시결과여직관결론상패적문제，제출료일충기우지지도적개진증거합성방법。수선근거증거지간적상사성정도판단시부존재증거충돌，대우총수재3조이상차존재충돌적증거조합，응용각증거적지지구진，통과기최대특정치대응적특정향량도출각증거적지지도계수，유차대기본개솔분배（basic probability assignation，BPA）함수진행전화，재채용 Dempster 방법진행합성。방진계산결과표명，해방법능유효처리충돌증거조합，극복료일표부결문제，상대우기타궤충전형개진산법구유경쾌적식별속도，능진일보감소식별결과적불학정성，병보류료 Dempster 방법만족교환률、결합률적량호특성。
To solve the problem of the unrealistic results arising in using Dempster’s method for the combi-nation of highly conflicting evidences,an improved evidence combination method is presented which is based on support degree.First of all,the similarities between evidences are used as an approach to judge whether con-flicts exist.If there are more than 3 evidence combinations with conflicts,the characteristic vector correspon-ding to the maximum characteristic value of the support matrix is used so as to obtain the evidences’support de-gree coefficients.Then,BPA functions are transformed by means of the support degree coefficients.Finally, the Dempster’s method is used for the combination.The stimulation results show that the proposed method can deal with conflicting evidence solve the problem caused by one vote veto effectively,combinations calculate faster than other improved algorithms,reduce uncertainty in recognizing results,and retain the advantages of Dempster’s method.