Yang, Z. and Zhou, H., 2018. Deep intrusion data mining method forship monitoring network under cloud computing. In: Liu, Z.L. and Mi, C. (eds.), Advances in Sustainable Port and Ocean Engineering. Journal of Coastal Research, Special Issue No. 83, pp. 668–672. Coconut Creek (Florida), ISSN 0749-0208.

In the cloud computing environment, the network space with different type and different scale are completely different in the destructiveness of intrusion and intrusion features. The traditional intrusion mining is mainly to weight these differentiated intrusion results, and calculating a fused threshold, measuring whether it is invaded, but this method does not subdivide intrusion features in ship monitoring network, and has high false alarm rate and rate of missing report. This paper proposed data mining method of the ship monitoring network intrusion mining based on the fuzzy C mean clustering algorithm and improved support vector machine algorithm. Firstly, this paper carried out dimensionality reduction and classification processing for the different type data, and collected related data for the extraction and analysis of sample feature, and calculated the overall threshold of data, and used the improved support vector machine algorithm to normalize the collected data, and obtained the data signal with uniform format. Experimental results show that the improved algorithm in the ship monitoring network under cloud computing deepness intrusion mining can improve the accuracy of mining, reduce the false alarm rate and improve the mining efficiency.

This content is only available as a PDF.
You do not currently have access to this content.