Knowledge discovery in databases in an intelligent decision support context a meteorological forecasting case study

The Knowledge Discovery in Databases (KDD) is concerned with exploiting massive data sets. Potentially, large data sets contain some useful knowledge that can be used for intelligent decision support. Soft Computing technologies such as fuzzy logic and artificial neural networks are being used for KDD purposes in developing intelligent systems for decision-making, systems that can deal with complex and ill-structured situations. This paper describes an ongoing research project, which is concerned with the integration of an Intelligent Decision Support System (IDSS) within the KDD process. The paper discusses the basic components of the hybrid computational architecture we propose for such integration. It comprises databases, mining data sets, knowledge bases powered by data mining technology and artificial neural network technology. The paper explores the computational technologies that are involved in this integration and the application domain it is being applied. The architecture is being implemented in the context of aviation weather forecasting. This allowed testing the benefits of such an approach for decision-makers dealing with complex and ill-structured tasks where historical data is available. The proposed architecture aims to serve as a model for a KDD-based intelligent decision support that could be used more widely in complex decision problems.<div><br></div><div>Presented at: 4th International ICSC Symposia on Soft Computing and Intelligent Systems for Industry; 2001 Jun 26-29; Paisley, Scotland. 7 leaves.