A fuzzy management scheme is proposed to cope with the evaluation of multisensor tasks priority in defence surveillance applications. Based on all fused track and sector data, a reasoning system determines the priority of each surveillance task to perform during the decision cycle, by means of a symbolic inference process inspired in the behaviour of human operators. This approach allows to integrate high-level information (possibly subjective concepts, considering also their uncertainty) with conventional numeric representations in the decision process. The elected formal method to represent the variables involved in this decision process is the theory of possibility and fuzzy sets, since it offers a unified framework to represent uncertainty knowledge. In this sense, to obtain the priority for each task, the reasoning process relies on a decision tree whose nodes are linguistic variables representing intermediate concepts used by a human operator to determine the tasks priorities. The validity of the fuzzy reasoning approach is supported by the fact that it has been able to manage environmental situations in a similar way as experienced human operators do. Included results illustrate how the importance of the tasks, measured through their time-varying priorities, allows the manager to timely adapt sensor operation to changing situations.
Surveillance multisensor management with fuzzy evaluation of sensor task priorities
Engineering Applications of Artificial Intelligence ; 15 , 6 ; 511-527
2002
17 Seiten, 15 Quellen
Article (Journal)
English
MATSurv: multisensor air traffic surveillance system
SPIE | 1995
|Fuzzy multisensor tracking system
British Library Conference Proceedings | 1999
|