Enhancing case-based reasoning retrieval using classification based on associations

The aim of this paper was to perform an extension of (CBRAR) strategy, Case-Based Reasoning using Association Rules to enhance the performance of the Similarity Base Retrieval SBR. FP-CAR classed frequent pattern tree algorithms are used in order to select correctly retrieved cases in Case-Based Reasoning (CBR). Class Association Rules (CARs) are utilized to generate an optimum FP-tree which holds a value of each node. The potential benefit offered is that more efficient results can be obtained when the retrieval phase returns uncertain answers. A comparison of CBR Query with FP-CAR is performed as patterns in order to identify the longest length nodes of the voted class. If the patterns are matched, the proposed CBRAR can choose the most similar and correct case. The experimental evaluation on a real dataset shows that the proposed CBRAR is a superior approach when likened to the accuracy of the CBR systems used in this investigation.