Network fault detection: Classifier training method for anomaly fault detection in a production network using test network information
Document Type
Conference Proceeding
Publication Date
1-1-2002
Abstract
We have prototyped a hierarchical, multi-tier, multi-window, soft fault detection system, namely the Generalized Anomaly and Fault Threshold (GAFT) system, which uses statistical models and neural network based classifiers to detect anomalous network conditions. In installing and operating GAFT, while both normal and fault data may be available in a test network, only normal data may be routinely available in a production network, thus GAFT may be ill-trained for the unfamiliar network environment. We present in detail two approaches for adequately training the neural network classifier in the target network environment, namely the re-use and the grafted classifer methods. The re-use classifier method is better suited when the target network environment is fairly similar to the test network environment, while the grafted method can also be applied when the target network may be significantly different from the test network.
Identifier
33747081327 (Scopus)
ISBN
[0769515916]
Publication Title
Proceedings Conference on Local Computer Networks LCN
External Full Text Location
https://doi.org/10.1109/LCN.2002.1181820
First Page
473
Last Page
482
Volume
2002-January
Recommended Citation
Li, Jun and Manikopoulos, C., "Network fault detection: Classifier training method for anomaly fault detection in a production network using test network information" (2002). Faculty Publications. 14872.
https://digitalcommons.njit.edu/fac_pubs/14872
