Interactive knowledge validation and query refinement in CBR for decision support in medicine
MetadataShow full item record
In most case-based reasoning (CBR) systems there has been little research done on validating new knowledge, specifically on how previous knowledge differs from current knowledge as a result of conceptual change. This paper proposes two methods that enable the domain expert, who is non-expert in artificial intelligence (AI), to interactively supervise the knowledge validation process in a CBR system, and to enable dynamic updating of the system, to provide the best di- agnostic questions. The first method is based on formal concept analysis which involves a graphical representation and comparison of the concepts, and a summary description high- lighting the conceptual differences. We propose a dissimilarity metric for measuring the degree of variation between the previous and current concepts when a new case is added to the knowledge base. The second method involves determining unexpected classification-based association rules to form critical questions as the knowledge base gets updated.
Showing items related by title, author, creator and subject.
Zadjabbariochtapeh, Behrang (2010)Knowledge sharing is one of the most critical elements in a knowledgebased society. With huge concentration on communication facilities, there is a major shift in world-wide access to codified knowledge. Although communication ...
Geneste, Louis André (2010)This thesis examines the role that non-collaborative, weak exchange relationships might play in the acquisition of knowledge by small and medium-sized enterprises (SMEs). An important source of knowledge for a firm lies ...
Zadjabbari, Behrang; Wongthongtham, Pornpit; Hussain, Farookh Khadeer (2010)For many years, physical asset indicators were the main evidence of an organization’s successful performance. However, the situation has changed following the revolution of information technology in the knowledge-based ...