Event correlation using rule and object based techniques
Proceedings of the fourth international symposium on Integrated network management IV
Proceedings of the fourth international symposium on Integrated network management IV
Intelligent filtering in network management systems
Proceedings of the fourth international symposium on Integrated network management IV
Kohonen Maps
Self-Organizing Maps
IJCAI'99 Proceedings of the 16th international joint conference on Artifical intelligence - Volume 1
Clustering of the self-organizing map
IEEE Transactions on Neural Networks
Logic-based representation, reasoning and machine learning for event recognition
Proceedings of the Fourth ACM International Conference on Distributed Event-Based Systems
Hi-index | 0.00 |
In this paper we propose a method to pre-process a telecommunication alarm log with the aim of discovering more accurately frequent patterns. In a first step, the alarm types which present the same temporal behavior are clustered with a self organizing map. Then, the log areas which are rich in alarms of the clusters are searched. The sublogs are built based on the selected areas. We will show the efficiency of our preprocessing method through experiments on an actual alarm log from an ATM network.