A Hybrid Approach to Approximate Real-time Decision Making

In this paper, we present an approach to construct a concurrent algorithm that supports real-time decision making based on the knowledge extracted from empirical data. The data is represented by a decision table in the Pawlak sense, while the concurrent algorithm is represented as a weighted priority fuzzy Petri net. This idea overcomes the difficulties that arise when field experts are entrusted with determining the values of net parameters. In the proposed approach, we assume that the decision tables contain conditional attribute values that are obtained from measurements made by sensors in real time. The Petri net built within the presented conception allows for the fastest possible identification of objects in decision tables in order to make the right decision. The sensor output values are transmitted over the net at the maximum possible speed. We achieve this effect thanks to the appropriate implementation of all true and acceptable rules generated from a given decision table.