Case-Based Reasoning: As an Expert System

To improve the software quality the number of errors from the software must be removed. The research paper presents a study towards case-based reasoning as an expert system. The purpose of this paper is to apply the machine learning approaches, such as case-based reasoning, to calculate the error with respect to LOC. The novel idea behind this system is that knowledge base (KBS) building is an important task in CBR and the knowledge base can be built based on world new problems along with world new solutions. Second, reducing the maintenance cost by removing the duplicate record set from the KBS. Third, predict the error in software module correctly and use the results in future estimation. In this paper five distance functions the Euclidean, Canberra, Exponential, Clark and Manhattan method were taken into consideration in terms of percentage of errors generated during execution of programs. We feel that case-based models are particularly useful when it is difficult to define actual rules about a problem domain. In order to obtain a result we have used indigenous tool.