A Retrieval Strategy Using the Integrated Knowledge of Similarity and Associations

摘要: Retrieval is often considered the most important task in Case-Based Reasoning (CBR), since it lays foundation for overall performance of CBR systems. In CBR, a typical retrieval strategy realized through similarity knowledge encoded measures. This called similarity-based (SBR). paper proposes and validates that association analysis techniques can be used to improve SBR. We propose USIMSCAR performs by integrating knowledge.We show its reliability, comparison with several methods implementing SBR, using datasets from UCI ML Repository