Intelligent technology development of anomalie detection in the ecosystem of Sevastopol water area

A.V. Skatkov1, A.A. Bryukhovetskiy1, Y.E. Shishkin1,2

1 Federal State Educational Institution of Higher Education «Sevastopol State University», Russian Federation, Sevastopol, Universitetskaya St., 33

2 Institute of Natural and Technical Systems, Russian Federation, Sevastopol, Lenin St., 28


DOI: 10.33075/2220-5861-2019-1-27-34

UDC 004.9   


   The organization of monitoring systems in modern conditions of increasing scale and complexity of cloud computing environments requires new approaches. Therefore, the problem of developing methods that form the basis for building intelligent technology for detecting anomalies of ecosystems in the water area of the city of Sevastopol in order to ensure continuous monitoring of key environmental indicators presented in the form of non-uniform information flows: hydrometeorological information, data on pollution and composition of air, soil, environmental monitoring, monitoring of maximum permissible emissions of harmful substances to detect changes in the state of the data flow of monitoring considered in this article  is relevant.

   Therefore, to solve these problems, it is proposed to use an integrated approach to the construction of monitoring systems, which has distinctive functional and structural features. The monitoring system being developed has obvious advantages over the known ones. The main differences of the proposed solutions are in using:

  • small sample sizes when measuring the metrics of physical objects of the environment,
  • low complexity and high speed methods,
  • criteria for evaluating information situations of object state changing,
  • adaptive approaches that allow tracking the variability of information states of objects and taking into account the nonstationarity of the environment,
  • method of updating databases containing information on monitored environmental objects.

   The use of the adaptive approach to building intelligent monitoring systems will allow to make the transition to a qualitatively new knowledge, optimize the processes of processing, analysis, and integration of heterogeneous data, increase the reliability and efficiency of the decisions made. The implementation of this approach is based on the application of mathematical models: a non-stationary optimization model of management and a model for ensuring the quality of the monitoring system.

Keywords: monitoring systems, anomalies detection, intelligent technology, big data, modeling of complex system, data mining.

Full text in PDF (RUS)


  1. Skatkov A.V., Bryukhovetsky A.A., Moiseev D.V. Methodology for organizing monitoring processes for solving large-scale tasks in cloud computing environments // Information technologies and information security in science, technology and education “INFOTECH-2017”: collection of articles vseros. scientific-technical Conf. Sevastopol state University, Institute of Information technologies and management in technical systems. Sevastopol: Sevsu, 2017. P. 78-80.
  2. Bryukhovetsky A. A., Skatkov A.V., Shishkin Yu. E. Modeling of anomaly detection processes in complex-structured monitoring data // Monitoring systems of environment. 2017. № 9 (29). P. 45–49.
  3. Skatkov A.V., Shishkin Yu. E. Development of a monitoring optimization model with partial uncertainty in the form of a Queuing system // Development of the methodology of modern economic science and management: materials of the first Interdisciplinary all-Russian conference. scientific-practical Conf. (Sevastopol may 4-5, 2017). Sevastopol: Sevsu. 2017. P. 611–618. ISBN 978-5-9907603-9-4.
  4. Skatkov A.V., Shishkin Yu. E. Data clustering in problems of anomaly detection based on orthogonal filters // Monitoring systems of environment. 2018. № 11 (31). P. 36–43.
  5. Novikova A. M., Averyanova E. A. Application of GIS technologies for complex problem solving spatial modeling in Oceanography and ecology // Ecological problems of the Azov-black sea region and integrated management of biological resources: materials of scientific practice. young. Conf. Sevastopol, 2016. P. 200-203.
  6. Bondur V. G. Aerospace monitoring of oil and gas complex objects. Moscow: Nauchny Mir, 2012, 558 p.
  7. Ratner Yu. b., Tolstosheev A. P., Kholod A. L. Creating a database for monitoring the Black sea using drifting surface buoys // Marine hydrophysical journal. 2009. no. 3. P. 50-69.
  8. Lavrova O. Yu., Kostyanoy A. G., Lebedev S. A. Complex satellite monitoring of Russian seas, Moscow: IKI RAS, 2011, 480 p.
  9. Korotaev G. K., Demyshev S. G., Li M. E. Satellite monitoring of marine waters. Kiev: Akademperiodika, 2014. P. 91-100.
  10. Balashov I. V., Khalikova O. A. Organization of automatic receipt of sets of information products from the centers of archiving and distribution of satellite and meteorological data // Modern problems of remote sensing of the Earth from space, 2013, Vol. 10, No. 3, P. 9-20.
  11. Shiryaev A. N. Probabilistic-statistical methods in the theory of decision making. 2-e Izd., new. Moscow: mtsnmo, 2014. 144 p.
  12. Scheduling in distributed systems: A cloud computing perspective / L.F. Bittencourt, A. Goldman, R.M. Madeira [et al.] Computer Science Review. 2018. Vol. 30. P. 31–54 DOI: 10.1016/j.cosrev.2018.08. 002
  13. Monsalve S.A., Carballeira F.G., Calderon A. A heterogeneous mobile cloud computing model for hybrid clouds // Future Generation Computer Systems. 2018. Vol. 87. P. 651–666. DOI: 10.1016/j.future.2018.04.005
  14. Matishov G. G., Berdnikov S. V., Zhichkin A. P. [et al.]. Atlas of climate change in large marine ecosystems of the Northern hemisphere (1878-2013). Region 1. Eastern Arctic Seas. Region 2. Black, Azov and Caspian seas. Rostov n / D: publishing house of the UNC RAS, 2014. 256 p.
  15. Li X., Ma. H., Wang X. Feature proposal model on multidimensional data clustering and its application // Pattern Recognition Letters. 2018. Vol. 112. P. 41–48. DOI: 10.1016/j.patrec.2018.05.025