Abstract
Traditional methods ignore the imbalance of network data, resulting in unsatisfactory clustering detection results, long detection time, and high rate of missed detection and false alarm. In this regard, this paper proposes a clustering detection method of network intrusion feature based on support vector machine and LCA block algorithm. Firstly, the useless features were deleted by reducing the dimension of the data set, thus improving the clustering detection accuracy. Secondly, the training sample set was divided, and the multi-level support vector model was established by two classification support vector machines. Finally, the LCA algorithm was adopted to identify the network intrusion features, achieving clustering detection of network intrusion feature. The results show that the proposed method achieves better clustering detection results and effectively reduces the average clustering detection time.
Similar content being viewed by others
References
Ji, J. X. (2017). Research on mobile network intrusion feature information extraction and detection. Computer Simulation, 034(003), 289–292.
Gao, N., Gao, L., He, Y. Y., & Wang, H. (2017). Lightweight intrusion detection model based on dimensionality reduction of auto-encoding network features. Chinese Journal of Electronics, 45(003), 730–739.
Dai, M. (2019). Network intrusion detection method based on parallel feature selection and classification. Computer Engineering and Design, 40(03), 61–68.
Hao, J. J., & Zhang, X. Z. (2019). Power grid communication intrusion detection technology based on support vector machines. Electrical Measurement and Instrumentation, 56(22), 109–114.
Dai, Y. F., Chen, X., Chen, H., Ye, L., Lin, J. X., & Guo, W. Z. (2017). Network intrusion detection method based on feature selection. Computer Application Research, 34(008), 2429–2433.
Zhuang, X. (2017). Network intrusion detection system based on mutual information feature selection and lssvm. China Test, 43(011), 134–139.
Liu, J. P., Zhang, W. X., Tang, Z. H., He, J. Z., & Xu, P. F. (2019). Adaptive network intrusion detection based on fuzzy rough set attribute reduction and gmm-lda optimal cluster feature learning. Control and Decision, 34(002), 243–251.
Shi, Y., Chen, Z., & Sun, B. (2016). Network intrusion detection based on mean clustering analysis and multi-layer core set aggregation algorithm. Computer Application Research, 33(002), 518–520.
Song, Y., & Cai, Z. P. (2018). An intrusion detection feature extraction method based on information theory model. Journal of University of Electronic Science and Technology of China, 47(002), 267–271.
Jia, F., & Kong, L. Z. (2017). Intrusion detection algorithm based on convolutional neural network. Journal of Beijing Institute of Technology, 037(012), 1271–1275.
Jiang, H., Chen, S. Q., Hu, H. C., & Qian, K. (2016). Lightweight DDOS attack detection method based on gaig feature selection algorithm. Application Research of Computers, 33(002), 502–506.
Zhou, J., Zhao, L. Y., & Luo, J. F. (2017). Fence intrusion pattern classification method based on temporal feature extraction. Computer Engineering and Applications, 53(021), 98–102.
Peng, K., Feng, C., Wang, S. M., Ai, F., Li, H., Liu, D. M., et al. (2019). Distributed optical fiber intrusion detection system event recognition method based on time/frequency domain comprehensive feature extraction. Acta Optics, 039(006), 338–348.
Qu, H. Q., Gong, G. J., Zhang, C. N., & Wang, Y. P. (2019). Feature extraction and recognition algorithm of optical fiber intrusion signal. Progress in Laser and Optoelectronics, 56(13), 40–47.
Guo, B. Q., & Wang, N. (2018). Railway intrusion pedestrian classification algorithm based on improved deep convolutional network. Optics and Precision Engineering, 26(012), 3040–3050.
Jiang, L. H., Liu, J. S., Xiong, X. L., Wang, W. B., & Li, M. (2017). Research on the feature extraction and recognition method of fiber perimeter intrusion signal. Laser and Infrared, 47(007), 906–913.
Zhu, C. H., Wang, J. P., Li, Q. Y., Zuo, D. S., & Li, W. T. (2016). Recognition and localization of intrusion vibration signals in fiber perimeter based on time-frequency characteristics. China Laser, 043(006), 303–311.
Huang, X. D., Zhang, H. J., Liu, K., Ma, C. Y., & Liu, T. G. (2017). High-efficiency intrusion event recognition based on comprehensive features for optical fiber perimeter security systems. Acta PhysicaSinica, 66(012), 164–173.
Liu, S., Shi, F., Wang, L. J., Qin, J. W., & Guo, Y. (2017). Research on wireless sensor network intrusion detection based on ksom-pso algorithm. Chinese Science and Technology Paper, 12(002), 148–153.
Xing, R. K., & Li, C. H. (2019). Application of improved clustering algorithm in intrusion detection system. Firepower and Command Control, 44(002), 124–128.
Zhang, C. Q., & Xie, L. C. (2018). Network intrusion detection method with improved fcm and rule parameter optimization in cloud environment. Telecommunications Science, 034(001), 72–79.
Yuan, K. Y., & Fei, L. (2016). Network intrusion detection based on selected features of hybrid particle swarm optimization algorithm. Journal of Jilin University (Science Edition), 54(02), 309–314.
Wen, H., & Wang, F. Y. (2017). Using sso to accelerate network intrusion detection of optimal path forest clustering. Journal of Southwest China Normal University: Natural Science Edition, 042(005), 34–40.
Sun, J., Liu, Y., & Zhao, X. J. (2016). Research on application layer ddos attack detection method based on clustering. Computer Engineering and Applications, 52(021), 116–120.
Acknowledgements
The research is supported by 2017 National Natural Science Foundation of China Youth Foundation Project :(2018.1~2020.12)" Research on Multi-scale Analysis and Precision Diagnostic methods of Breast Pathological Image based on Deep Learning "Approval No .61702026;Henan Province 2018 Science and Technology Research Project-the key Technology Research of big data Analysis platform for developing Intelligent Agricultural batches in distributed heterogeneous Environment, Project No .182102110277
Author information
Authors and Affiliations
Corresponding author
Additional information
Publisher's Note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
About this article
Cite this article
Zhang, J., Sun, J. & He, H. Clustering Detection Method of Network Intrusion Feature Based on Support Vector Machine and LCA Block Algorithm. Wireless Pers Commun 127, 599–613 (2022). https://doi.org/10.1007/s11277-021-08353-y
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11277-021-08353-y