Informed case base maintenance: a complexity profiling approach
Susan M Craw, Stewart Massie, Nirmalie Wiratunga · 2007
Knowledge maintenance for Case-Based Reasoning systems is an important knowledge engineering task despite the avail-ability of initial case knowledge and new cases to extend it. For classification systems it is essential that different sce-narios for the various classes are well represented and de-cision boundaries are well defined in the case knowledge. A complexity-based competence metric is proposed that iden-tifies redundant and error-causing cases to be deleted. The metric informs amaintenance tool that enables the engineer to experiment and balance conflicting objectives. Complexity-informed maintenance outperforms benchmark algorithms for redundancy and error reduction tasks.