Prediction Method of Network Security Situation Based on GA-LSSVM Time Series Analysis

Prediction Method of Network Security Situation Based on GA-LSSVM Time Series Analysis

Huan Wang Jian Gu Jianping ZhaoDan Liu Xin Sui Xiaoqiang Di Bo Li

School of Computer Science and Technology, Changchun University of Science and Technology, Changchun 130022, China

School of Opto-electronic Engineering, Changchun University of Science and Technology, Changchun 130022, China

Corresponding Author Email: 
471745553@qq.com
Page: 
370-388
|
DOI: 
https://doi.org/10.18280/ama_b.600208
Received: 
15 May 2017
| |
Accepted: 
10 June 2017
| | Citation

OPEN ACCESS

Abstract: 

To more accurately understand the development trend of network security situation and to solve the prediction problem in network security situation awareness, this paper proposes a prediction model and an optimization method of network security situation based on GA-LSSVM time series analysis. The model adopts the original sequence accumulation method to reduce the interference of the irregular fluctuations of the original sequence and constructs the mixed kernel function based on the combination of RBF and Poly which takes both the learning and generalization ability of the model into account. The genetic algorithm is used to optimize the parameters of the LSSVM model. Through characteristic chromosome coding of the model parameters, the search space is established to obtain the optimal solution through fitness evaluation. The simulation results show that the model can effectively predict the network security situation with an accuracy of about 13% higher than that of HHGA-RBFNN and PSO-SVM.

Keywords: 

LSSVM, Trend prediction, Parameter optimization

1. Introduction
2. The LSSVM-based Prediction Model
3. GA-based LSSVM Joint Parameter Optimization
4. GA-LSSVM-based Prediction
5. Experimental Simulation
6. Conclusion
Acknowledgements
  References

[1] T.Q. Huang, Y. Zhang, An approach to real time network security situation prediction, 2014, Journal of Chinese Computer Systems, vol. 35, no. 2, pp. 303-306.

[2] C.X. Guo, Y. Su, A new optimized algorithm based on quantum evolutionary strategy for network security situation prediction, 2014, Journal of Chinese Computer Systems, vol. 35, no. 9, pp. 2083-2087.

[3] K. Wu, Z.Y. Bai, Trusted network security situational awareness and forecast based on SPA, 2012, Journal of Harbin Institute of Technology, vol. 44, no. 3, pp. 112-118.

[4] C.H. Tang, S.Z. Yu, Method of network security situation prediction based on likelihood BP, 2009, Computer Science, vol. 36, no. 19, pp. 97-100.

[5] S.Y Wu, X.G Tian. Method for anomaly detection of user behaviors based on hidden Markov models, 2007, Journal on Communications, vol. 28, no. 4, pp. 38-43.

[6] Y.L. Liu, D.G. Feng, Y.F. Lian, Network situation prediction method based on spatial-time dimension analysis, 2014, Journal of Computer Research and Development, vol. 51, no. 8, pp. 1681-1694.

[7] S.S. Keerthi, C.J. Lin, Asymptotic behaviors of support vector machines with Gaussian Kernel, 2003, Neural Computation, vol. 15, no. 7, pp. 1667-1689.

[8] S.H. Xiong, C.Y. Zhou, LSSVM prediction model for chaotic time series based on reduction strategy, 2011, Acta Scientiarum Naturalium Universitatis Sunyatseni, vol. 50, no. 1, pp. 53-57.

[9] H.J. XIAO, X.L. Sang, Network security situation prediction based on hyper parameter optimization of relevance vector machine, 2015, Journal of Computer Applications, vol. 35, no. 7, pp. 1888-1891.

[10] M.Y. Zhao, Y. Tang, C.Z. Fu, T. Ming, Feature selection and parameter optimization for SVM based on genetic algorithm with feature chromosomes, 2010, Control and Decision, vol. 25, no. 8, pp. 1133-1138.

[11] Z.C. Wen, Z.G. Chen, Network security situation prediction method based on hidden Markov model, 2015, Journal of Central South University (Science and Technology), vol. 46, no. 10, pp. 3689-3695.

[12] R.R. Xi, X.C. Yun, Y.Z. Zhang. An improved quantitative evaluation method for network security, 2015, Chinese Journal of Computers, vol. 38, no. 4, pp. 749-758.

[13] N. Görnitz, M. Kloft, K. Rieck, Toward supervised anomaly detection, 2013, Journal of Artificial Intelligence Research, vol. 46, no. 2, pp. 235-262.

[14] V. Dutt, Y.S. AHN, C. Gonzalez, Cyber situation awareness modeling detection of cyber attacks with in-stance-based learning theory, 2013, Human Factors: The Journal of the Human Factors and Ergonomics Society, vol. 55, no. 3, pp. 605-618.

[15] R.Z. Fan, M.K. Zhou, Network security awareness and tracking method by GT, 2013, Journal of Computational Information Systems, vol. 9, no. 3, pp. 1043-1050.