Chen Weijun
Anyang Normal University, Anyang, 455000, Henan, China
Jia Weifeng
Anyang Normal University, Anyang, 455000, Henan, China
ABSTRACT
This study introduces a scheme of adaptable distance calculation based on t-distribution which is on the basis of analysis of the scheme of SOM network anomaly detection. The solution sets up a confidence interval between the test sample and BMU distance using t-distribution. It ensures that network anomaly occurs when the distance between the test sample and BMU is not within the range of the confidence interval. In order to test its validity, the improved method is compared with the method of the network anomaly detection based on OC-SVM. Finally, the experimental result shows that this kind of method has characteristics of implementing easily, detecting correctly and having low false alarm rate.
PDF References Citation
How to cite this article
Chen Weijun and Jia Weifeng, 2013. A New Method of SOM Network Anomaly Detection on the Basis of T-Distribution. Information Technology Journal, 12: 4647-4650.
DOI: 10.3923/itj.2013.4647.4650
URL: https://scialert.net/abstract/?doi=itj.2013.4647.4650
DOI: 10.3923/itj.2013.4647.4650
URL: https://scialert.net/abstract/?doi=itj.2013.4647.4650
REFERENCES
- Gao, J., L. Xu and Y. Dai, 2004. An intrusion detection system model based on Self-organizing map. Proceedings of the 5th World Congress on Intelligent Control and Automation, June 15-19, 2004, Hangzhou, China, pp: 4367-4369.
CrossRef - Ramadas, M., S. Ostermann and B. Tjaden, 2003. Detecting anomalous network traffic with Self-organizing maps. Proceedings of the 6th International Symposium on Recent Advances in Intrusion Detection, September 8-10, 2003, Pittsburgh, PA, USA., pp: 36-54.
CrossRef