In this paper a distributed weight mining algorithm is proposed based on FP-growth. As an important part of network fault management, the association rule takes effect on eliminating redundant alarms and preventing alarm storm. In traditional association rules the importance of each item is seen as equivalent during mining which is not realistic. By considering the different weights of the items, the AHP approach is introduced in the paper. Without any candidate generation process FP-growth performs well in mining alarm records. The distributed architecture of master and slave site can effectively reduced the complexity of the algorithm. The experimental results and comparison with other algorithms prove the validity of this proposed algorithm and good performance of decreasing the run-time. © Springer-Verlag Berlin Heidelberg 2011.
CITATION STYLE
Wang, H., Liu, Y., & Wang, C. (2011). Research on association rule algorithm based on distributed and weighted FP-growth. In Advances in Intelligent and Soft Computing (Vol. 128, pp. 133–138). https://doi.org/10.1007/978-3-642-25989-0_24
Mendeley helps you to discover research relevant for your work.