The Application of Improved Genetic Neural Network in IDS for Material Detecting

Abstract:

The basic idea of twice genetic algorithm optimization of BP neural network model(TGB)is rough selection network model using genetic algorithm, then use BP neural network to determine the parameters which can make the error function obtained the minimum and determine its position in the parameter space, then the genetic algorithm again to solve the problem of possible local minima.Feature selection is a new formulation of dimension reduction methods. It can simplify the size of neural network and improve real-time and the accuracy of the system.The simulation results TGB-based network intrusion detection algorithm improve intrusion detection rate of samples in different degrees. It can reduce significantly training time and test time. It further demonstrates the effectiveness and feasibility of this method. The study is very useful to detect materials. So from the analysis, you can learn some skills for materials detecting.

• Periodical: Advanced Materials Research (Volume 321)
• Pages: 213-217
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.321.213
• Online since: August 2011
• Authors: Qing Yu, Jin Lin Wang, Xiao Chen Sui
• Keywords: BP Neural Network (BPNN), GA, Intrusion Detection, KDDCUP’99

References

[1] Lidong Wang, Yaping Li and Binxin Fang, A neural network-based intrusion detection system [J], Computer Engineering, 1999, 25(10): 56~58.

[2] Zhengjun Tang, Intrusion Detection, Qinghua University Press, (2004).

[3] Yanpeng Liu, Based on Improved Genetic Neural Network Intrusion Detection System Research [D], Master Thesis, Chongqing University, (2005).

[4] Hong Zheng, BP neural network based intrusion detection system implementation classifier, Hefei University of Technology, 2003, 26(2): 281~285.

[5] Ping Yang and Jinhua Zheng, Comparison of genetic operators and research [J], Computer Engineering and Applications, 2007, 43(15): 59-65.