Modelling contextual meta-knowledge in temporal model based diagnosis
José T. Palma, R. Marı́n · 2002
Abstract. Applying Model Based Diagnosis (MBD) techniques in medical domains reveals the need to use deep causal knowledge mod-elling frameworks as well as temporal management techniques to capture the dynamic component of disease evolution (with the lat-ter being very important in other domains). Despite the intense re-search activity in the field of Temporal MBD, there are three issues that have not been analysed in depth: (a) modelling complex inter-action of contextual information, (b) evaluation of hypotheses pos-sibility degrees and (c) the structure of explanations. Our aim is to present a general framework for Temporal MBD which approaches these problems and to demonstrate the suitability of the Fuzzy Tem-poral Constraints Networks formalism (FTCN) for representing the domain temporal dimension. 1