A Machine Learning Approach to Case Adaptation

The idea of case-based reasoning (CBR) is based on experts, who prefer to rely on their experience in solving similar problems which have been solved before. Each successful experience of problem solving is stored as a case, and a case can be reused in solving a similar problem in the future. However, experience may not be exactly the same as the target problem that they are facing. To make use of experience, case adaptation is necessary. There are several issues to consider when implementing case adaptation in a CBR system, including the comprehension of each case and design of a case adaptation method. The system retrieves the most similar case depending on attributes of the target problem, and the solution part of the retrieved case will then be refined with case adaptation. The goal of this study is to design and implement case adaptation with the aide of artificial neural networks and the concept of heuristics. The experiments show that the proposed approach is efficient in adjusting the solution to fit the needs of the target problem.