Combining Different Domain Models into a Contextual Similarity Function

Abraham Rodriguez Rodriguez
Department of Computer Sciences
University of Las Palmas de Gran Canaria
Canary Islands
Spain
email: arodriguez@dis.ulpgc.es or abraham@iiia.csic.es


Abstract The similarity assessment is a fundamental issue in the Case-based Reasoning field. It seems obvious that flexibility must be a determining factor when assessing the importance of one specific characteristic. This purpose can only be achieved through the development of a context dependent similarity measure. This paper presents a novel approach for determining the importance of the case characteristics which combines a memory of solved episodes with general domain knowledge into a number of fixed dimensions.