Gomuła, J., Paja, W., Pancerz, K., Mroczek, T., Wrzesień, M.: Experiments with Hybridization and Optimization of the Rules Knowledge Base for Classification of MMPI Profiles. In: P. Perner (Eds.), Advances in Data Mining. Applications and Theoretical Aspects - Proceedings of the 11th Industrial Conference on Data Mining (ICDM'2011), New York, NY, USA, August 30 - September 3, 2011, Lecture Notes in Artificial Intelligence, Vol. 6870, Springer-Verlag, Berlin Heidelberg, 2011, pp. 121-133.

       In the paper, we investigate a problem of hybridization and optimization of the knowledge base for the Copernicus system. Copernicus is a tool for computer-aided diagnosis of mental disorders based on personality inventories. Currently, Copernicus is used to analyze and classify patients’ profiles obtained from the Minnesota Multiphasic Personality Inventory (MMPI) test. The knowledge base embodied in the Copernicus system consists of, among others, classification functions, classification rule sets as well as nosological category patterns. A special attention is focused on selection of a suitable set of rules classifying new cases. In experiments, rule sets have been generated by different data mining tools and have been optimized by generic operations implemented in the RuleSEEKER system.