Maintaining Case Based Reasoning Systems Based on Soft Competence Model

Abstract

Case-based Reasoning (CBR) is a well known computer reasoning technique. Its deficiency depends on the mass of the case data and the rapidity of the retrieval process that can be wasteful in time. This is due to the number of cases that gets large and the store of cases besieges with ineffective cases, as the noises. This may badly affect the performance of the system in terms of its efficiency, competence and solution quality. Resultantly, maintaining CBR system becomes mandatory. In this paper, we offer a novel case base maintenance (CBM) policy based on well-organized machine learning techniques, using a soft competence model, in the process of improving the competence of our reduced case base. The intention of our CBM strategy is to shrink the volume of a case base while preserving as much as possible the performance and the competence of the CBR system. We support our approach with empirical evaluation using different benchmark data sets to show the effectiveness of our method in terms of shrinking the size of the case base and the research time, getting satisfying classification accuracy and improving the competence of the system.