Abstract
Data mining technology is widely used for the analysis of large datasets stored in databases. However, conventional data mining is not satisfied with the requirement due to the heterogeneous and distributed of the datasets. Grid computing emerged as an important new field of distributed computing, which could support for distributed knowledge discovery applications. Weka4WS is an open-source framework extended from the Weka toolkit for distributed data mining on Grid, which deploys many of machine learning algorithms provided by Weka Toolkit as WSRF-Compliant services. This paper presents the architecture, implementation and execution of Weka4WS. At last, an example about distributed Classification is given to illustrate the effective of Weka4WS framework further.