An integrated feature selection and cluster analysis techniques for case-based reasoning

Feature selection and case organization are crucial steps in case-based reasoning (CBR), since the retrieval efficiency and accuracy even the success of the CBR system are heavily dependent on their quality. However, inappropriate feature selection and case selection together with ill-structured case organization may not only present a dilemma in case retrieval, but also greatly increase the case base. To obtain an efficient CBR system, selection of proper features and suitable cases with appropriate case organization are very important. This paper proposes a hybrid CBR system by introducing reduction technique in feature selection and cluster analysis in case organization. In this study, a minimal set of features is selected from the problem domain while redundant ones are reduced through neighborhood rough set algorithm. Once feature selection is finished, the growing hierarchical self-organizing map (GHSOM) is taken as a cluster tool to organize those cases so that the initial case base can be divided into some small subsets with hierarchical structure. New case is led into corresponding subset for case retrieval. Experiments on UCI datasets and a practical case in electromotor product design show the effectiveness of the proposed approach. The results indicate that the research techniques can effectively enhance the performance of the CBR system.