TY - JOUR
T1 - Gaussian Successive Fuzzy Integral for Sequential Multi-decision Making
AU - Luo, An Chun
AU - Chen, Sei Wang
AU - Fang, Chiung Yao
N1 - Publisher Copyright:
© 2015 Taiwan Fuzzy Systems Association and Springer-Verlag.
PY - 2015/6/29
Y1 - 2015/6/29
N2 - Fuzzy integral provides a powerful tool for fusing multiple sources of information or evidence to give an evaluation that expresses the level of confidence (or preference) in a particular hypothesis (or decision). However, the computational framework of the fuzzy integral is not suitable for sequential decision making tasks, since it assumes that the sources of information have been readily available prior to information fusion. In a sequential decision making task, information is progressively accumulated, while decisions are made at various time instants. In this paper, we reformulate the computational framework of the fuzzy integral in order to translate its framework into a successive one. To this end, three issues have been encountered: (i) how to collect the richest information for sequential decision making, (ii) how to efficiently preserve the constantly increasing amount of incoming information, and (iii) how to build up an effective computational scheme in order to gratify the requirement of real-time decision making. The derived scheme, called the Gaussian successive fuzzy integral scheme, was closely examined to validate its feasibility in real-time sequential multi-decision making on the basis of incremental information gathering.
AB - Fuzzy integral provides a powerful tool for fusing multiple sources of information or evidence to give an evaluation that expresses the level of confidence (or preference) in a particular hypothesis (or decision). However, the computational framework of the fuzzy integral is not suitable for sequential decision making tasks, since it assumes that the sources of information have been readily available prior to information fusion. In a sequential decision making task, information is progressively accumulated, while decisions are made at various time instants. In this paper, we reformulate the computational framework of the fuzzy integral in order to translate its framework into a successive one. To this end, three issues have been encountered: (i) how to collect the richest information for sequential decision making, (ii) how to efficiently preserve the constantly increasing amount of incoming information, and (iii) how to build up an effective computational scheme in order to gratify the requirement of real-time decision making. The derived scheme, called the Gaussian successive fuzzy integral scheme, was closely examined to validate its feasibility in real-time sequential multi-decision making on the basis of incremental information gathering.
KW - Gaussian successive fuzzy integral
KW - Incremental information gathering
KW - Real-time sequential multi-decision making
UR - http://www.scopus.com/inward/record.url?scp=84930505107&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84930505107&partnerID=8YFLogxK
U2 - 10.1007/s40815-015-0028-1
DO - 10.1007/s40815-015-0028-1
M3 - Article
AN - SCOPUS:84930505107
VL - 17
SP - 321
EP - 336
JO - International Journal of Fuzzy Systems
JF - International Journal of Fuzzy Systems
SN - 1562-2479
IS - 2
ER -