Cluster computing data mining based on massive intrusion interference constraints in hybrid networks
- 90 Downloads
To solve the problem that massive intrusion data in hybrid networks greatly interfere network intrusion detection and cause relatively great difficulty to detection due to their frequency discontinuity, a mining algorithm of massive intrusion cluster computing data in hybrid networks based on spectral feature extraction under fixed constraints of time–frequency window is proposed in this paper. The multi-component cross-detection method is used to collect massive intrusion information in hybrid networks and construct a model of massive intrusion signal in hybrid networks. Cascading notch method is used to suppress intrusion interference under constraints of fixed time–frequency window, and extract fundamental quantity and primary function with locality in massive interference information, and obtain a complete energy distribution spectrum on the time–frequency plane. The energy distribution spectrum is used as guidance function to realize cluster calculating data mining with massive intrusion interference constraints. Simulation results show that, in the intrusion detection process of signal-to-noise ratio from − 15 to − 5 dB, the detection accuracy of the method proposed in this paper is always better than that of others. When the signal-to-noise ratio is − 9 dB, the detection accuracy of this method is over 90%. When the signal-to-noise ratio is −9 dB, the detection accuracy of this method can reach 100%. About the detection time, especially after the Number of intrusion date is 2000, the detection time difference between the three methods is increased, and the detection time of other methods is 2–3 times of paper method. The method proposed can accurately locate mass intrusion distribution sources in hybrid networks under the large frequency oscillation of intrusion data in the hybrid networks, realize network intrusion detection and interference suppression and can filter interference information well, so this method improves intrusion detection probability in hybrid networks.
KeywordsHybrid network Intrusion Detection data mining Cluster computing
Funding were provided by National Natural Science Foundation of China (Grant No. 61461017), the Hainan Natural Science Foundation Innovation Research Team Project (Grant No. 2017CXTD0004), the Hainan Province Key Research and Development Projects (Grant No. ZDYF2016002), the Innovative Research Project of Postgraduates in Hainan Province (Grant No. Hyb2017-07), the Open Topic of State Key Laboratory of Marine Resources Utilization in South China Sea of Hainan University (Grant No. 2016013A), and the Key Laboratory of Sanya Project (Grant No. L1410).
- 2.Dai, L., Gao, X., Wang, Z.: Energy-efficient hybrid precoding based on successive interference cancelation for millimeter-wave massive MIMO systems [C]. In: Radio and Antenna Days of the Indian Ocean, pp. 1–2. IEEE (2015)Google Scholar
- 4.Jia, W., Xiao, L., Zhu, D.: A mini-ripple control method for doubly salient electromagnetic motor control system [C]. In: Applied Power Electronics Conference and Exposition, pp. 1886–1890. IEEE (2017)Google Scholar
- 8.Meng, B., Zhang, J.L., Lu, J.T.: Automatic analysis of authentication of OpenID connect protocol based on the computational model [J]. J. South Central Univ. Natl. 35(3), 123–129 (2016)Google Scholar
- 9.Wang, H.X., Wang, S.Y., Wang, X., et al.: Analysis of LFM signals and improvement of IFM system [J]. Acta Armamentarii 35(8), 1193–1199 (2014)Google Scholar
- 10.Yan, K.Q., Wang, S.C., Liu, C.W.: A hybrid intrusion detection system of cluster-based wireless sensor networks [J]. Lect. Notes Eng. Comput. Sci. 2174(1), 477–480 (2009)Google Scholar
- 12.Tran, H., Zepernick, H.J., Phan, H., et al.: Cognitive cooperative networks with cluster-based relaying under interference constraints[C]. In: International Conference on Ubiquitous & Future Networks, pp. 542–546. IEEE (2013)Google Scholar
- 13.Xie, M.G., Jia, X.D., Zhou, M.: Research on energy efficiency of hybrid networks based on massive MIMO and D2D [J]. J. Signal Process. 16(24), 53–58 (2017)Google Scholar
- 16.Yousef, E.L., Toumanari, A., Bouirden, A., et al.: Intrusion detection techniques in wireless sensor network using data mining algorithms: comparative evaluation based on attacks detection [J]. Int. J. Adv. Comput. Sci. Appl. 6(9), 13–17 (2015)Google Scholar
- 19.Kurras, M., Thiele, L., Caire, G.: Multi-stage beamforming for interference coordination in massive MIMO networks[C]. In: Asilomar Conference on Signals, Systems and Computers, pp. 700–703. IEEE (2015)Google Scholar