Features

http://www.datamininggrid.org/index.htm

Up to now Datamining tools have mainly been developed for largely homogeneous and localized computing environments. These assumptions are increasingly not met in modern scientific and industrial complex-problem solving environments, which are more an more relying on the sharing of geographically dispersed computing resources. Next-generation grid technologies are promising to provide the necessary infrastructure facilitating a seamless sharing of computing resources in complex problem-solving environments. This shift to large-scale distributed computing has profound implications for the way data are analysed. Grid computing promises to be capable of addressing the changing computing requirements of future distributed data-mining environments.

Currently there exists no coherent framework for developing and deploying data-mining applications on the grid. The DataMiningGrid project will address this gap by developing generic and sector-independent data mining tools and services for the grid. Grid interfaces will be developed allowing data mining tools to operate in a distributed grid computing environment. Therefore a major innovation in the project comes from distributing knowledge acquisition. Both for technical reasons � e.g. bandwidth � and for organizational reasons � privacy and security � it is impossible to bring all data to a centralized place. Therefore the aim of the project is to upgrade data mining technologies in such a way that makes traditional knowledge discovery approaches distributed. Data mining is upgraded to the working and organizational habit of the new knowledge workers.

A test bed consisting of several real-world applications from a diverse set of sectors will serve as a platform for demonstrating and promoting the technology developed by the DataMiningGrid. The following main objectives of the DataMiningGrid project were identified:

• To develop grid interfaces that allow datamining tools and data sources to interoperate within distributed grid computing environments,
• To develop grid-based text mining and ontology-learning services and interfaces,
• To develop a testbed consisting of several demonstrator applications from a diverse set of sectors, including the bioinformatics, healthcare, and automotive industries, and
• To align and integrate these technologies with emerging grid standards and infrastructures.