Traffic-Related Knowledge Acquired by Interaction with Experts

We present our research on acquiring domain knowledge related to urban vehicular tra c by means of interaction with experts. Such knowledge is needed in knowledge discovery and data mining for approximation of complex vague concepts from the road tra c. According to perception based computing paradigm, this can be done by construction of hierarchical classi ers supported with expert knowledge. We treat tra c, especially urban tra c, as a complex process having hierarchical structure. Complexity of this process makes tra c data massive and complex, what makes domain oriented hierarchical classi ers indispensable here. We propose a method of tra c domain knowledge acquisition by interaction with experts aimed at construction of such classi ers.