TY - GEN
T1 - Composition Method of Weak Decision-Making Evidence Based on Focal Element Weight
AU - Jia, Jingyuan
AU - Wang, Bo
N1 - Publisher Copyright:
© 2019 IEEE.
PY - 2019/11/1
Y1 - 2019/11/1
N2 - In order to solve the problem of one-vote veto in the combination of conflicting evidence, based on Jousselme distance mode, we apply average evidence instead of conflicting evidence. Then a threshold selection method to determine the existence of weak decision-making evidence is proposed. Because of the inability to distinguish the differences between the focal elements in the weak decision-making evidence, traditional algorithms produce non-ideal fusing results. We propose a new method of determining weights, which describes the relationship between the focus elements in a piece of evidence by means of the deviation from average and standard deviation. This method can effectively expand the difference between the most credible focal element and other focal elements. After modifying evidence body with weights, the Dempster-Shafer combination rule to combine the revised evidence body is applied. Numerical experiments demonstrate that the proposed method has a better measurement of the difference between focal elements of weak decision-making evidence. In the case where both weak decision-making evidence and one-vote veto evidence exist, the proposed method can obtain more reliable fusing results and faster convergence speed, which helps to make decisions.
AB - In order to solve the problem of one-vote veto in the combination of conflicting evidence, based on Jousselme distance mode, we apply average evidence instead of conflicting evidence. Then a threshold selection method to determine the existence of weak decision-making evidence is proposed. Because of the inability to distinguish the differences between the focal elements in the weak decision-making evidence, traditional algorithms produce non-ideal fusing results. We propose a new method of determining weights, which describes the relationship between the focus elements in a piece of evidence by means of the deviation from average and standard deviation. This method can effectively expand the difference between the most credible focal element and other focal elements. After modifying evidence body with weights, the Dempster-Shafer combination rule to combine the revised evidence body is applied. Numerical experiments demonstrate that the proposed method has a better measurement of the difference between focal elements of weak decision-making evidence. In the case where both weak decision-making evidence and one-vote veto evidence exist, the proposed method can obtain more reliable fusing results and faster convergence speed, which helps to make decisions.
KW - focal element weight
KW - information fusion
KW - weak decision-making evidence
UR - https://www.scopus.com/pages/publications/85080098373
U2 - 10.1109/CAC48633.2019.8996993
DO - 10.1109/CAC48633.2019.8996993
M3 - Conference contribution
AN - SCOPUS:85080098373
T3 - Proceedings - 2019 Chinese Automation Congress, CAC 2019
SP - 1143
EP - 1148
BT - Proceedings - 2019 Chinese Automation Congress, CAC 2019
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 2019 Chinese Automation Congress, CAC 2019
Y2 - 22 November 2019 through 24 November 2019
ER -