The article constructs a data-mining software, which is suitable for distributed settings and dynamically incremental mining, and introduces the implementation of main part of software such as the main part's design proposal, the computation pattern, the system Metadata warehouse, the automatic connection of isomerism data resource pool, the withdrawal of data storage node's Metadata, the increment mechanism, the parallel computing and so on. This software has an ability to make dynamic and distributed data mining and can be easily used into a control system. Through using the history data mining result, this data mining method can obtain the overall data mining result by carrying calculate to the incremental sample data only. The software can reduce time of communication in the distributional data mining process greatly and enhance the systempsilas efficiency.
[1]
Donald F. Ferguson,et al.
From Open Grid Services Infrastructure to WS-Resource Framework: Refactoring and Evolution
,
2004
.
[2]
Martin Scholz.
On the Complexity of Rule Discovery from Distributed Data
,
2005
.
[3]
Gerhard Weikum,et al.
KLEE: A Framework for Distributed Top-k Query Algorithms
,
2005,
VLDB.
[4]
G. Allen,et al.
Supporting Efficient Execution in Heterogeneous Distributed Computing Environments with Cactus and Globus
,
2001,
ACM/IEEE SC 2001 Conference (SC'01).
[5]
Martin Scholz.
On the tractability of rule discovery from distributed data
,
2005,
Fifth IEEE International Conference on Data Mining (ICDM'05).