Inference via fuzzy belief Petri nets

The fuzzy belief Petri net we propose in this paper propagates fuzzy beliefs from observations at nodes that represent measured parameters to fuzzy beliefs of the truths of parameters at hidden and decision nodes. The fuzzy influences spread from the observation nodes throughout our new enhanced bidirectional fuzzy belief Petri net. Compared with Bayesian belief networks, it is simpler and faster in that it needs neither the conditional probability tables that are difficult or impossible to obtain nor is it overly constrained by the mathematical axiomatic structure that makes Bayesian belief inferencing NP-hard. Compared with our previous fuzzy belief networks, it is more flexible in modeling particular situations. We develop here the concept, data structures and algorithm for this network, while future work will make comparative runs.