1. Science
  2. Publications
  3. Science and Technology of the Air Force of Ukraine
  4. 1(34)'2019
  5. Improved method of classification of air objects

Improved method of classification of air objects

O. Timochko
Annotations languages:


Description: To make decisions on the classification of air objects use a combined method – fuzzy models based on systems with fuzzy logic, as well as models based on the usual Boolean logic. In the previous step, the assessment is carried out by comparing with a reference set of characteristics for each class of air objects. On the basis of the modification of the singleton knowledge base and the optimistic decision criterion, a mechanism for hierarchical logic derivation is proposed. The value of the Singleton membership functions for implicit tree branches of decision making is considered as the value of the computed reliability of the information. The knowledge base is formed as a matrix of the correspondence of possible signs of the behavior of the airspace to each index of mem-bership (class of air objects). The mechanism of logical deduction uses the results of a preliminary analysis of possible solutions, with branches of explicit and implicit decisions. The weighting coefficients of the logical output equation are based on the values of the coefficients of completeness of information, calculated at the stage of analysis of the input information. The obtained equations and logic tree trees allow us to construct a decision-making method for the automated classification of air objects. The offered method of classification of air objects differs from the known: a) the use of heterogeneous sources of information on air objects and the formalization of signs with the help of fuzzy sets, including type 2; b) introduction of the hierarchical system of airspace classifi-cation; c) the calculation of the reliability of information about air objects and its use as values of singletton functions of the mem-bership of the input features; d) the organization of the logical deduction in the deterministic and fuzzy branches of decision making on air objects with the formation of a vector of “trust” to the solution options. An improved method for assessing the quality of airspace classification can be used at the testing stage of an automated classification system.


Keywords: air object, classification of air objects, knowledge base, function of accessory, airborne object sign, logical conclusion

References

1. Rotshtein, A.P. (1999), “Yntellektualjnye tekhnologhyy ydentyfykacyy: nechetkye mnozhestva, ghenetycheskye alghorytmy, nejronnye sety” [Intellectual identification technologies: fuzzy sets, genetic algorithms, neural networks], UNIVERSUM, Vinnitsa, 320 p.
2. Borisov, V.V., Kruglov, V.V. and Fedulov, A.S. (2007), “Nechetkye modely y sety” [Fuzzy models and networks], Hotline – Telecom, Moscow, 284 p.
3. .Nedilko, V.M. (2002), “Zabezpechennja efektyvnosti informacijnoji pidtrymky pryjnjattja rishenj v avtomatyzovanykh systemakh obslughovuvannja povitrjanogho rukhu z elementamy shtuchnogho intelektu: dissertation” [Ensuring the effectiveness of decision-making information support in automated air traffic service systems with artificial intelligence elements: dissertation], NAU, Kyiv, 183 p.
4. Olizarenko, S.A., Kapranov, A.V. and Perepelitsa, A.V. (2011), “Intervalnye nechetkie mnozhestva tipa 2. Terminologiia, predstavlenie, operatsii”, Information Processing Systems, Vol. 2(92), pp. 39-45.
5. Artemenko A.M. “Decision-making methodology for detecting threatening situations in the air” / AM Artemenko G.V. Pevtsov // Science and Technology of the Air Forces of the Armed Forces of Ukraine – X .: ХУПС, 2011. – Вип. 1 (5). – P. 15-20.
6. Brodetsky, G.L. (2010), “Systemnyj analyz v loghystyke. Vybor v uslovyjakh neopredelennosty” [System analysis in logistics. Choice under uncertainty], Academia, Moscow, 336 p.
7. Artemenko, A.M., Kamaltynov, H.H. and Maliarenko, O.S. (2011), “Udoskonalennia pryntsypiv zapytu ta obrobky syhnaliv vidpovidi u zapytuvachakh NRZ-P dlia pidvyshchennia yakosti vpiznavannia”, Systems of Arms and Military Equipment, No. 2(26), pp. 9-14.
8. Tolkachenko, Ye.A., Pavlenko, M.A., Berdnik, P.H. and Chertok, O.A. (2017), “Analiz metodiv erhonomiky dlia otsinky ta rozrobky avtomatyzovanykh robochykh mists v ASU spetsialnoho pryznachennia” [Analysis methods of evaluation and development automation workstations with ergonomic], Scientific Works of Kharkiv National Air Force University, Vol. 4(53), pp. 119-121.
9. Nesmiian, O.Yu. and Pavlenko, M.A. (2016), “Analiz informatsiinoho zabezpechennia ta zavantazhenosti kanaliv pryiomu informatsii operatoramy system ASU” [Analysis of information provision and workload channel receiving information by operators of the automatization controlling systems], Systems of Arms and Military Equipment, No. 2(46), pp. 129-133.
10. Danilov, Iu.A., Obidin, D.N., Timochko, A.A. and Berdnik, P.G. (2017), “Adaptivnyi algoritm soprovozhdeniia traektorii vozdushnykh obieektov s uchetom ikh vozmozhnogo nerazresheniia” [Adaptive algorithm of trajector assignment of air objects with the account f their possible non-resolution], Systems of Arms and Military Equipment, No. 1(49), pp. 101-104.

Reference:
 Timochko, O.O. (2019), “Vdoskonalenyi metod klasyfikatsii povitrianykh obiektiv” [Improved method of classification of air objects], Science and Technology of the Air Force of Ukraine, No. 1(34), pp. 58-63. https://doi.org/10.30748/nitps.2019.34.08.