Research of Potential Inclined Intrusion Data Mining Method in Large Network

Abstract:

Network intrusion is shown in more and more concealment, and some intrusion data is potential with inclination property. This paper is aimed to mine the potential inclined intrusion data effectively, and ensure the security of large network. On the basis of the traditional fractional Fourier transform data mining method. An improved potential inclined intrusion accurate data mining algorithm is proposed. New algorithm can separate the time and frequency coupling effectively. The discrete fractional Fourier transform is implemented for the network intrusion data firstly. The data is gathered in the fractional Fourier domain, the inclined intrusion data accumulation is increased. The network signal interference is suppressed effectively. Simulation results show that the proposed data mining algorithm can extract the potential inclined intrusion data in strong concealment. The mining performance is much better than the traditional algorithm, and it can be applied in the network security defense area perfectly.

• Periodical: Applied Mechanics and Materials (Volumes 543-547)
• Pages: 2024-2027
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.543-547.2024
• Online since: March 2014
• Authors: Chang Jiang Zhu*, Wen Kui Zheng
• Keywords: Data Mining (DM), Large Network, Network Security, Potential Intrusion Data

References

[1] Liang Hong, Hong Kang, Yang Changsheng. Lattice structure adaptive IIR notch filter based on least square kurtosis[J]. Systems Engineering and Electronics, 2009, 20 (6): 1188-1192.

DOI: 10.1109/asc-icsc.2008.4675528

[2] Wei Xindan. Simulation Research on the Fuzzy C Algorithm In Network Intrusion Protection[J]. Bulletin of Science and Technology, 2012; 28(12): 221-223.

[3] HU Guangbo, LIANG Hong, XU Qian. Research on Chaotic Feature Extraction of Ship Radiated Noise[J]. Computer Simulation, 2011, 28(2): 22-24.

[4] WU Chun-qiong. Network Intrusion Detection Model Based on Feature Selection[J]. Computer Simulation, 2012; 29(6): 136-139.

[5] Ye Qing, Huang Yanlei. Non-uniform Distribution Intrusion Detection Research and Simulation of the Model[J]. Bulletin of Science and Technolog, 2013; 29(8): 169-171.