Admire framework: Distributed data mining on data grid platforms

摘要

In this paper, we present the ADMIRE architecture; a new framework fordeveloping novel and innovative data mining techniques to deal with very largeand distributed heterogeneous datasets in both commercial and academicapplications. The main ADMIRE components are detailed as well as its interfacesallowing the user to efficiently develop and implement their data miningapplications techniques on a Grid platform such as Globus ToolKit, DGET, etc.