Attributed concept maps: fuzzy integration and fuzzy matching

摘要

A concept map, typically depicted as a connected graph, isncomposed of a collection of propositions. Each proposition forming ansemantic unit consists of a small set of concept nodes interconnected tonone another with relation links. Concept maps possess a number ofnappealing features which make them a promising tool for teaching,nlearning, evaluation, and curriculum planning. We extend concept maps bynassociating their concept nodes and relation links with attribute valuesnwhich indicate the relative significance of concepts and relationshipsnin knowledge representation. The resulting maps are called attributednconcept maps (ACM). Assessing students will be conducted by matchingntheir ACMs with those prebuilt by experts. The associated techniques arenreferred to as map matching techniques. The building of an expert ACMnhas in the past been done by only one specialist. We integrate a numbernof maps developed by separate experts into a single map, called thenmaster map (MM), which will serve as a prototypical map in map matching.nBoth map integration and map matching are conceptualized in terms ofnfuzzy set discipline. Experimental results have shown that the proposednideas of ACM, MM, fuzzy map integration, and fuzzy map matching are wellnsuited for students with high performances and difficult subjectnmaterials