An Incremental Learning Method for Data Mining from Large Databases

Abstract

Knowledge Discovery techniques seek to find new information about a domain through a combination of existing domain knowledge and data examples from the domain. These techniques can either be manually performed by an expert, or automated using software algorithms (Machine Learning). However some domains, such as the clinical field of Lung Function testing, contain volumes of data too vast and detailed for manual analysis to be effective, and existing knowledge too complex for Machine Learning algorithms to be able to adequately discover relevant knowledge. In many cases this data is also unclassified, with no previous analysis having been performed. A better approach for these domains might be to involve a human expert, taking advantage of their expertise to guide the process, and to use Machine Learning techniques to assist the expert in discovering new and meaningful relationships in the data. It is hypothesised that Knowledge Acquisition methods would provide a strong basis for such a Knowledge Discovery method, particularly methods which can provide incremental verification and validation of knowledge as it is obtained. This study examines how the MCRDR (Multiple Classification Ripple- Down Rules) Knowledge Acquisition process can be adapted to develop a new Knowledge Discovery method, Exposed MCRDR, and tests this method in the domain of Lung Function. Preliminary results suggest that the EMCRDR method can be successfully applied to discover new knowledge in a complex domain, and reveal many potential areas of study and development for the MCRDR method.