Knowledge Integration in a Parallel and Distributed Environment With Association Rule Mining Using XML Data
In distributed data mining, the mining process is carried out in distributed locations parallel and generates frequent itemsets on the local areas. It is necessary to analyze these local patterns to gain global patterns when putting all the knowledge derived from local distributed location to a single one. Knowledge integration is the problem of combining the mined results obtained from the data residing at different sources, and providing the user with a unified view of these knowledge. Such a unified view is structured according to a so-called global schema, which represents the intentional level of the integrated data. Association rules are used for the mining process and hence local interestingness measure differs from the global interested patterns.