Development of a method for calculating the safe position of military units by using artificial neural networks based on swarm algorithms

Authors

DOI:

https://doi.org/10.15587/2312-8372.2018.120750

Keywords:

neural networks, safe position, forecasting of solutions, cover of clusters

Abstract

The object of research is development of a method for finding a safe position for military units in combat conditions, using swarm algorithms and neural networks. One of the most problematic places is the complexity of testing the developed method. The difficulty lies in the fact that to check the method in real time, financial costs and military weapons are necessary.

The data are obtained due to a multicriteria problem, which allowed to calculate the errors of subjects and objects of research.

The obtained results show that the hybrid method allowed to calculate the safe position with greater accuracy, namely by 25–50 % more accurately than using the classical approach. This is due to the fact that the proposed method calculates all possible errors.

This makes it possible to obtain the flexibility of the method for finding a safe position. In comparison with the analogous methods known in the formulation of the classical problem of calculating the trajectory and the damage region, only one mathematical value (region, trajectory) is taken into account, and using a hybrid approach one can take into account a number of errors simultaneously. This approach ensures the flexibility of the system and the possibility of expanding a number of mathematical calculations and improving the accuracy of the result.

Author Biographies

Vasyl Lytvyn, National University «Lviv Polytechnic», 12, S. Bandery str., Lvіv, Ukraine, 79013

Doctor of Technical Sciences, Professor

Department of Information Systems and Networks

Dmytro Uhryn, Chernivtsi Faculty of the National Technical University «Kharkiv Polytechnic Institute», 203A, Holovna str., Chernivtsi, Ukraine, 58000

PhD, Associate Professor

Department of Information Systems

Olexiy Iliiyuk, Chernivtsi Faculty of the National Technical University «Kharkiv Polytechnic Institute», 203A, Holovna str., Chernivtsi, Ukraine, 58000

Department of Information Systems 

Oleg Klichuk, Chernivtsi Faculty of the National Technical University «Kharkiv Polytechnic Institute», 203A, Holovna str., Chernivtsi, Ukraine, 58000

PhD, Associate Professor

Department of Information Systems 

References

  1. Wiener, N. (1964). Extrapolation, Interpolation, and Smoothing of Stationary Time Series with Engineering Applications. Cambridge, MA: MIT Press, 176.
  2. McCulloch, W. S., Pitts, W. (1990). A logical calculus of the ideas immanent in nervous activity. Bulletin of Mathematical Biology, 52 (1–2), 99–115. doi:10.1007/bf02459570
  3. Hebb, D. O. (2002). The Organization of Behavior: A Neuropsychological Theory. New York: Psychology Press, 335. doi:10.4324/9781410612403
  4. Hopfield, J. J. (1982). Neural networks and physical systems with emergent collective computational abilities. Proceedings of the National Academy of Sciences, 79 (8), 2554–2558. doi:10.1073/pnas.79.8.2554
  5. Rumelhart, D. E., Hinton, G. E., Williams, R. J. (1988). Learning Internal Representations by Error Propagation. Readings in Cognitive Science,399–421. doi:10.1016/b978-1-4832-1446-7.50035-2
  6. Shannon, C.E. (2001).A Mathematical Theory of Communication. Mobile Computing and Communications Review, 5 (I),3–55.
  7. Lippmann, R. P. (1988). An introduction to computing with neural nets. ACM SIGARCH Computer Architecture News, 16 (1), 7–25. doi:10.1145/44571.44572
  8. Sun-Yuan Kung, Taur, J., Shang-Hung Lin. (1999). Synergistic modeling and applications of hierarchical fuzzy neural networks. Proceedings of the IEEE, 87 (9), 1550–1574. doi:10.1109/5.784235
  9. Ackley, D. H., Hinton, G. E., Sejnowski, T. J. (1985). A Learning Algorithm for Boltzmann Machines. Cognitive Science, 9 (1), 147–169. doi:10.1207/s15516709cog0901_7
  10. Loh, W.-Y. (2011). Classification and regression trees. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1 (1), 14–23. doi:10.1002/widm.8
  11. Giles, C. L., Maxwell, T. (1987). Learning, invariance, and generalization in high-order neural networks. Applied Optics, 26 (23), 4972–4978. doi:10.1364/ao.26.004972
  12. Farlow, S.J. (1984). Self-Organizing Methods in Modeling: GMDH Type Algorithms (Statistics: A Series of Textbooks and Monographs). CRC Press, 368.
  13. Hampshire, J. B., Pearlmutter, B. (1991). Equivalence Proofs for Multi-Layer Perceptron Classifiers and the Bayesian Discriminant Function. Connectionist Models, 159–172. doi:10.1016/b978-1-4832-1448-1.50023-8

Published

2017-12-28

How to Cite

Lytvyn, V., Uhryn, D., Iliiyuk, O., & Klichuk, O. (2017). Development of a method for calculating the safe position of military units by using artificial neural networks based on swarm algorithms. Technology Audit and Production Reserves, 1(2(39), 4–9. https://doi.org/10.15587/2312-8372.2018.120750

Issue

Section

Information Technologies: Original Research