Multimodal Reasoning with Rule Induction and Case-Based Reasoning

The integration of problem-solving methods have attracted increasing research interest. We present a hybrid system, ELEM2-CBR, that integrates rule induction and case-based reasoning. ELEM2-CBR has the following characteristics. First, it applies a novel feature weighting function for assessing similarities between cases. By using this weighting function, optimal case retrieval is achieved in that the most relevant cases can be retrieved from the case base. Second, the method handles both classification and numeric prediction tasks under a mixed paradigm of rule-based and ease-based reasoning. Before problem solving, rule induction is performed to induce a set of decision rules from a set of training data. The rules are then employed to determine some parameters in the new weighting function. For classification tasks, rules are applied to make decisions; if there is a conflict between matched rules, case-based reasoning is performed. In this paper, the new weighting function is presented. ELEM2-CBR’s multimodal reasoning strategies are described. We demonstrate the performance of ELEM2-CBR by comparing its experimental results with the ones from other methods on a number of designed and real-world problems.