Abstract
This article considers an approach to identifying abnormal situations in network segments of the Internet of Things by means of an ensemble of classifiers. Classification algorithms are adjusted for different kinds of events and anomalies with the help of training samples of various compositions. An ensemble of algorithms allows obtaining more accurate results by collective voting. An experiment using three neural networks with equal architectures is described. The estimation results are obtained both separately for each classifier and using the ensemble.
Similar content being viewed by others
REFERENCES
Gao, D., Reiter, M., and Song, D., Beyond output voting: Detecting compromised replicas using HMM-based behavioral distance, IEEE Trans. Dependable Secure Comput., 2009, vol. 6, no. 2, pp. 96–110. https://doi.org/10.1109/TDSC.2008.39
Devesh, M., Kant, A.K., Suchit, Y.R., Tanuja, P. and Kumar, S.N., Fruition of CPS and IoT in context of Industry 4.0, Intelligent Communication, Control and Devices, Choudhury, S., Mishra, R., Mishra, R.G., and Kumar, A., Eds., Advances in Intelligent Systems and Computing, vol. 989, Singapore: Springer, 2020, pp. 367–375. https://doi.org/10.1007/978-981-13-8618-3_39
Amosov, O.S., Magola, D.S., and Baena, S.G., Network classification of information security attacks based on intelligent technologies, fractal and wavelet analysis, Uch. Zap. Komsomol’skogo-Na-Amure Gos. Tekh. Univ., 2017, vol. 1, no. 4, pp. 19–29.
Demidov, R.A., Pechenkin, A.I., Zegzhda, P.D., and Kalinin, M.O., Application model of modern artificial neural network methods for the analysis of information systems security, Autom. Control Comput. Sci., 2018, vol. 52, no. 8, pp. 965–970. https://doi.org/10.3103/S0146411618080072
Demidov, R.A., Zegzhda, P.D., and Kalinin, M.O., Threat analysis of cyber security in wireless adhoc networks using hybrid neural network model, Autom. Control Comput. Sci., 2018, vol. 52, no. 8, pp. 971–976. https://doi.org/10.3103/S0146411618080084
Lavrova, D., Zegzhda, D., and Yarmak, A., Predicting cyber attacks on industrial systems using the kalman filter, Third World Conf. on Smart Trends in Systems Security and Sustainability (WorldS4), London, 2019, IEEE, 2019, pp. 317–321. https://doi.org/10.1109/WorldS4.2019.8904038
Lavrova, D., Zegzhda, D., and Yarmak, A., Using GRU neural network for cyber-attack detection in automated process control systems, IEEE Int. Black Sea Conf. on Communications and Networking (BlackSeaCom), Sochi, Russia, 2019, IEEE, 2019, pp. 1–3. https://doi.org/10.1109/BlackSeaCom.2019.8812818
Lavrova, D. and Zaitceva, E., and Zegzhda, P., Bio-inspired approach to self-regulation for industrial dynamic network infrastructure, CEUR Workshop Proc., Moscow, 2019, Basarab, M. and Markov, A.S., Eds., Moscow: CEUR Workshop Proceedings, 2019, pp. 34–39.
Bevir, M.K., O’Sullivan, V.T., and Wyatt, D.G., Computation of electromagnetic flowmeter characteristics from magnetic field data, J. Phys. D.: Appl. Phys., 1981, vol. 14, no. 3, pp. 373–388. https://doi.org/10.1088/0022-3727/14/3/007
Semenov, V.V., Lebedev, I.S., Sukhoparov, M.E., and Salakhutdinova, K.I., Application of an autonomous object behavior model to classify the cybersecurity state, Internet of Things, Smart Spaces, and Next Generation Networks and Systems. NEW2AN 2019, ruSMART 2019, Galinina, O., Andreev, S., Balandin, S., and Koucheryavy, Y., Eds., Lecture Notes in Computer Science, vol. 11660, Cham: Springer, 2019, pp. 104–112. https://doi.org/10.1007/978-3-030-30859-9_9
Kaftannikov, I.L. and Parasich, A.V., Problems of training set’s formation in machine learning tasks, Vestn. Yuzhno-Ural. Gos. Univ. Ser.: Komp’yut. Tekhnol., Upr., Radioelektron., 2016, vol. 16, no. 3, pp. 15–24. https://doi.org/10.14529/ctcr160302
Xiao, T., Xia, T., Yang, Y., Huang, C., and Wang, X., Learning from massive noisy labeled data for image classification, IEEE Conf. on Computer Vision and Pattern Recognition (CVPR), Boston, 2015, IEEE, 2015, pp. 2691–2699. https://doi.org/10.1109/CVPR.2015.7298885
Tsoumakas, G. and Katakis, I., Multi-label classification: An overview, Int. J. Data Warehousing Mining, 2007, vol. 3, no. 3, pp. 1–13. https://doi.org/10.4018/jdwm.2007070101
Semenov, V.V., Lebedev, I.S., and Sukhoparov, M.E., Identification of the state of individual elements of cyber-physical systems based on external behavioral characteristics, J. Appl. Inf., 2018, vol. 13, no. 5, pp. 72–83.
Sukhoparov, M.E. and Lebedev, I.S., Identification the information security status for the Internet of Things devices in information and telecommunication systems, Sist. Upr., Svyazi Bezop., 2020, no. 3, pp. 252–268. https://doi.org/10.24411/2410-9916-2020-10310
Sukhoparov, M.E., Lebedev, I.S., and Garanin, A.V., Application of classifier sequences in the task of state analysis of Internet of Things devices, Telekommun. Sist. Komp’yut. Seti, 2020, vol. 13, no. 3, pp. 44–54. https://doi.org/10.18721/JCSTCS.13304
Voroncov, K.V., Lectures on Algorithmic Compositions. http://www.machinelearning.ru/wiki/images/0/0d/Voron-ML-Compositions.pdf. Cited April 8, 2021.
D’yakonov, A., Methods for solving classification problems with categorical features, in Prikladnaya matematika i informatika (Applied Mathematics and Informatics), Moscow: MAKS Press, 2014, pp. 103–127.
Zhou, Z.-H., Ensemble Methods: Foundations and Algorithms, New York: Chapman & Hall/CRC, 2012.
Yu, Y., Zhou, Z.-H., and Ting, K.M., Cocktail ensemble for regression, Seventh IEEE Int. Conf. on Data Mining (ICDM 2007), Omaha, Neb., 2007, IEEE, 2007, pp. 721–726. https://doi.org/10.1109/ICDM.2007.60
Author information
Authors and Affiliations
Corresponding author
Ethics declarations
The authors declare that they have no conflicts of interest.
Additional information
Translated by S. Kuznetsov
About this article
Cite this article
Sukhoparov, M.E., Lebedev, I.S. Application of Ensembles of Neural Networks Trained on Unbalanced Samples for Analyzing Statuses of IoT Devices. Aut. Control Comp. Sci. 55, 1136–1141 (2021). https://doi.org/10.3103/S0146411621080319
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.3103/S0146411621080319