Извините, этот техт доступен только в “Американский Английский”. For the sake of viewer convenience, the content is shown below in the alternative language. You may click the link to switch the active language.
STATE ANALYSIS INTERNET OF THINGS DEVICES BASED ON BAGGING
Mikhail E. Sukhoparov, Saint-Petersburg federal research center of Russian science academy, sukhoparovm@gmail.com
Ilya S. Lebedev, Saint-Petersburg federal research center of Russian science academy, isl_box@mail.ru
Abstract
The development of IoT concept makes it necessary to search and improve models and methods for analyzing the state of remote autonomous devices. Due to the fact that some devices are located outside the controlled area, it becomes necessary to develop universal models and methods for identifying the state of low-power devices from a computational point of view, using complex approaches to analyzing data coming from various information channels. The article discusses an approach to identifying IoT devices state, based on parallel functioning classifiers that process time series received from elements in various states and modes of operation. The aim of the work is to develop an approach for identifying the state of IoT devices based on time series recorded during the execution of various processes. The proposed solution is based on methods of parallel classification and statistical analysis, requires an initial labeled sample. The use of several classifiers that give an answer «independently» from each other makes it possible to average the error by «collective» voting. The developed approach is tested on a sequence of classifying algorithms, to the input of which the time series obtained experimentally under various operating conditions were fed. Results are presented for a naive Bayesian classifier, decision trees, discriminant analysis, and the k nearest neighbors method. The use of a sequence of classification algorithms operating in parallel allows scaling by adding new classifiers without losing processing speed. The method makes it possible to identify the state of the Internet of Things device with relatively small requirements for computing resources, ease of implementation, and scalability by adding new classifying algorithms.
Keywords:state analysis, internet of things, bootstrap aggregating, discriminant analysis, state monitoring, classification algorithm, Bayesian classifier, decision trees.
References
1. Farwell J. P. and Rogozinski R. (2011) Stuxnet and the future of cyber war. Survival. Global Politics and Strategy. Vol. 53, Issue 1. P. 23-40. DOI: 10.1080/00396338.2011.555586.
2. Yeung D. Y. and Ding Y. (2003) Host-based intrusion detection using dynamic and static behavioral models. Pattern recognition. Vol. 36, Issue 1. P. 229-243. DOI: 10.1016/S0031-3203(02)00026-2.
3. Igure V., Laughter S., and Williams R. (2006) Security issues in SCADA networks. Computers & Security. Vol. 25, Issue 7. P. 498-506. DOI: 10.1016/j.cose.2006.03.001.
4. Semenov V. V., Lebedev I. S., and Sukhoparov M. E. (2019) State identification of information security of unmanned vehicles using artificial neural networks. Methods and information security engineering: Proceedings of the 28th Scientific and Technical Conference, June 24-27, 2019. Issue 28. P. 46-47 (in Russian).
5. Zikratov I.A., Zikratova T. V., and Lebedev I. S. (2014) Trusted model of information security of multi-agent robotics systems with decentralized control. Scientific and Technical Journal of Information Technologies. Mechanics and Optics. Issue 2 (90). P. 47-52 (in Russian)
6. Gao D., Reiter M. K., and Song D. (2009) Beyond output voting: Detecting compromised replicas using HMM-based behavioral distance. IEEE Transactions on Dependable and Secure Computing. Vol. 6, Issue 2. P. 96-110. DOI: 10.1109/TDSC.2008.39.
7. Devesh M., Kant A. K., Suchit Y. R., Tanuja P., and Kumar S. N. (2020) Fruition of CPS and IoT in context of Industry 4.0. Intelligent Communication, Control and Devices. Advances in Intelligent Systems and Computing. Vol. 989. P. 367-375.
8. Bevir M. K., Osullivan V. T., and Wyatt D. G. (1981) Computation of electromagnetic flowmeter characteristics from magnetic field data. Journal of Physics D: Applied Physics. Vol. 14, Issue 3. P. 373-388. DOI: 10.1088/0022-3727/14/3/007.
9. 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; 2019, pp. 104-112. DOI: 10.1007/978-3-030-30859-9_9.
10. Semenov V. V., Lebedev I. S., and Sukhoparov M. E. (2018) Approach to classification of the information security state of elements of cyber physical systems by applying side electromagnetic radiation. Scientific and Technical Journal of Information Technologies, Mechanics and Optics. Vol. 18, Issue 1. P. 98-105 (in Russian). DOI: 10.17586/2226-1494-2018-18-1-98-105.
11. Soshnikova L. A, Tamashevich V. N., Ushbe G., and Shefer M. (1999) Multivariate statistical analysis in economics: manual for graduate students. Moscow: UNITI — Dana. 598 p. (in Russian)
12. Sukhoparov M. E., Semenov V. V., Salakhutdinova K. I., and Lebedev I. S.(2020) Detection of abnormal functioning of Industry 4.0 devices based on behavioral patterns. Information Security Problems. Computer Systems. Issue 1 (41). P. 96-102. (in Russian)
13. Bendat Dzh. and Pirsol A. (1983) Application of correlation and spectral analysis. Translation from English. Moscow: Mir Publ. 312 p. (in Russian)
14. Zasov V. A., Tarabardin M. A., and Nikonorov E. N. (2009) Algorithms and devices for identification of input signals in tasks of control and diagnostics of dynamic objects. Vestnik of Samara University. Aerospace and Mechanical Engineering. Issue 2. P. 115-123 (in Russian)
Information about authors:
Mikhail E. Sukhoparov, Senior researcher of Intelligent Systems Laboratory, Saint-Petersburg federal research center of Russian science academy, Saint-Petersburg, Russia
Ilya S. Lebedev, Head of Intelligent Systems Laboratory, Saint-Petersburg federal research center of Russian science academy, Saint-Petersburg, Russia