CAESAR: a system for case based software reuse

TitleCAESAR: a system for case based software reuse
Publication TypeConference Proceedings
Year of Conference1992
AuthorsFouque G., Matwin S.
Conference NameSeventh Knowledge-Based Software Engineering Conference
Conference LocationMclean, VA, USA, USA
KeywordsComputer aided software engineering, Computer science, Humans, Indexing, Knowledge representation, Machine learning, Software engineering, Software libraries, Software systems, Software tools

The authors show how the compositional software reuse approach can be fruitfully cast in the case-based reasoning (CBR) paradigm. Any CBR system in which the cases are software artifacts must rely on software-specific concepts to provide adequate knowledge representation. However, the fact that these software artifacts can be executed on a computer should yield stronger results than could be expected from generic CBR. The CAESAR system relies on advanced data flow analysis concepts for its representation of knowledge about software modules. Cases and their fragments are retrieved and adapted to solve new problems. The new cases which result are executed on system-generated test sets to evaluate the results of CBR.<>