Comparative Analysis of Intellectual Approaches to Solving the Situation Identification Problem

Abstract

The paper examines application of two intelligent methods in identifying situations based on the associativity property, i.e., the ability to access the stored data using its content. In comparative analysis, the Hopfield neural network as a representative of the neural networks and the Haken synergetic model as an alternative approach to identification are selected. Their characteristics are provided, as well as similarities and differences between them. Operation of these models implemented in the Python programming language was practically studied, and results of the situation identification are presented using the example of identifying a threat category in the helicopter control. Study results demonstrate that the synergetic model is more accurate in identifying the threat category. During the experiments, disadvantages and advantages of each intelligent method were revealed. In particular, the Hopfield neural network shows
a number of disadvantages critical in situations that require a prompt and accurate solution. The synergy model has a number of advantages compared to the neural network, they include absence of the false attractors and ability to rank information by setting the appropriate parameter values

Please cite this article in English as:

Buldakova T.I., Suyatinov S.I., Vishnevskaya Yu.A. Comparative analysis of intellectual approaches to solving the situation identification problem. Herald of the Bauman Moscow State Technical University, Series Instrument Engineering, 2024, no. 2 (147), pp. 84--101 (in Russ.). EDN: RIGGLQ

References

[1] Buldakova T.I., Suyatinov S.I. Assessment of the state of production system components for digital twins technology. Cyber-physical systems: advances in design & modelling. Сham, Springer, 2020, pp. 253--262. DOI: https://doi.org/10.1007/978-3-030-32579-4_20

[2] Proletarsky A., Berezkin D., Popov A., et al. Decision support system to prevent crisis situations in the socio-political sphere. Cyber-physical systems: advances in design & modelling. Cham, Springer, 2020, pp. 301--314. DOI: https://doi.org/10.1007/978-3-030-32648-7_24

[3] Kivan M., Berezkin D.V., Smirnova E.V. Risk management hybrid decision-making support methodology in complex sociotechnical systems. Herald of the Bauman Moscow State Technical University, Series Instrument Engineering, 2023, no. 2 (143), pp. 90--110 (in Russ.). DOI: http://dx.doi.org/10.18698/0236-3933-2023-2-90-110

[4] Buldakova T.I. Issledovanie slozhnykh sistem i protsessov [Study on complex systems and processes]. Moscow, BMSTU Publ., 2016.

[5] Dzhalolov A.S., Buldakova T.I., Proletarsky A. Socio-economic decision support module by unstructured data. EIConRus, 2020, pp. 1931--1934. DOI: https://doi.org/10.1109/EIConRus49466.2020.9039086

[6] Hopfield J.J. Neural networks and physical systems with emergent collective computational abilities. PNAS, 1982, vol. 79, no. 8, pp. 2554--2558. DOI: https://doi.org/10.1073/pnas.79.8.2554

[7] Haken H. The standard model of synergetics for pattern recognition. Synergetic computers and cognition. Berlin, Springer, 2004, pp. 36--50. DOI: https://doi.org/10.1007/978-3-662-10182-7_5

[8] Taherzadeh G., Loo C.K. Image classification using optimized synergetic neural network. FIRA 2013. Berlin, Springer, 2013, pp. 170--180. DOI: https://doi.org/10.1007/978-3-642-40409-2_15

[9] Edwards T., Homola J., Mercer J., et al. Multifactor interactions and the air traffic controller: the interaction of situation awareness and workload in association with automation. Cogn. Tech. Work, 2017, vol. 19, no. 2, pp. 687--698. DOI: https://doi.org/10.1007/s10111-017-0445-z

[10] Zasyadko K.I., Vonarshenko A.P., Soldatov S.K., et al. Analysis of qualities professionally important for flight instructor and their enhancement. Aviakosmicheskaya i ekologicheskaya meditsina [Aerospace and Environmental Medicine], 2020, vol. 54, no. 1, pp. 52--56 (in Russ.). DOI: https://doi.org/10.21687/0233-528X-2020-54-1-52-56

[11] Filimonov A.B., Filimonov N.B. Situational approach in the problems of automation control by technical objects. Mekhatronika, avtomatizatsiya, upravlenie, 2018, vol. 19, no. 9, pp. 563--578 (in Russ.). DOI: https://doi.org/10.17587/mau.19.563-578

[12] Endsley M.R. A systematic review and meta-analysis of direct objective measures of situation awareness: a comparison of SAGAT and SPAM. Hum. Factors, 2021, vol. 63, no. 1, pp. 124--150. DOI: https://doi.org/10.1177/0018720819875376

[13] Merkulov V.I., Mikheev V.A., Lipatov A.A., et al. Features of the information integration and complex processing in the airborne situational awareness systems. Uspekhi sovremennoy radioelektroniki [Achievements of Modern Radioelectronics], 2016, no. 6, pp. 3--21 (in Russ.). EDN: WIDAUV

[14] Fedunov B.E. Artificial intelligence agents in the knowledge databases of onboard real-time advisory expert systems for the typical situations of the functioning of an anthropocentric object. J. Comput. Syst. Sc. Int., 2019, vol. 58, no. 6, pp. 932--944. DOI: https://doi.org/10.1134/S1064230719040051

[15] Costa P.D., Mielke I.T., Pereira I., et al. A model-driven approach to situations: situation modeling and rule-based situation detection. IEEE 16th Int. Enterprise Distributed Object Computing Conf., 2012, pp. 154--163. DOI: https://doi.org/10.1109/EDOC.2012.26

[16] Sholomov D.L. Correction of recognized text using classification methods. Sb. tr. ISA RAN, 2007, vol. 29, pp. 352--366 (in Russ.). EDN: KBYLQH

[17] Manzhikov T.V., Slavin O.A., Faradzhev I.A., et al. Algorithm for applying N-grams to correct recognition results. Matematicheskie metody v tekhnike i tekhnologiyakh [Mathematical Methods in Technologies and Technics], 2017, vol. 2, pp. 121--125 (in Russ.). EDN: ZDDPHL

[18] Anokhin A., Burov S., Parygin D., et al. Development of scenarios for modeling the behavior of people in an urban environment. Society 5.0: cyberspace for advanced human-centered society. Cham, Springer, 2021, pp. 103--114. DOI: https://doi.org/10.1007/978-3-030-63563-3_9

[19] Buldakova T.I., Mikov D.A., Sokolova A.V. Data security at remote monitoring of human state. Herald of the Bauman Moscow State Technical University, Series Instrument Engineering, 2020, no. 4 (133), pp. 42--57 (in Russ.). DOI: http://dx.doi.org/10.18698/0236-3933-2020-4-42-57

[20] Bolshakov A.A., Kulik A.A. Investigation of the integrated control system of a helicopter type aircraft in case of onboard equipment failures. Mekhatronika, avtomatizatsiya, upravlenie, 2019, vol. 20, no. 9, pp. 568--575 (in Russ.). DOI: https://doi.org/10.17587/mau.20.568-575

[21] Bolshakov A.A., Kulik A., Sergushov I., et al. Decision support algorithm for parrying the threat of an accident. Studies in Systems, Decision and Control, 2020, vol. 260, pp. 237--247. DOI: https://doi.org/10.1007/978-3-030-32648-7_19

[22] Suyatinov S.I., Buldakova T.I., Vishnevskaya Yu.A. Mathematical methods in technologies and technics comparison of neural network and synergetic approaches when identifying situations. Matematicheskie metody v tekhnike i tekhnologiyakh [Mathematical Methods in Technologies and Technics], 2023, no. 3, pp. 85--89 (in Russ.). EDN: LTBYWG

[23] Radhakrishnan R., Trout B.L. Order parameter approach to understanding and quantifying the physico-chemical behavior of complex systems. Handbook of materials modeling. Dordrecht, Springer, 2005, pp. 1613--1626. DOI: https://doi.org/10.1007/978-1-4020-3286-8_81

[24] Suyatinov S.I., Buldakova T.I., Vishnevskaya Yu.A. Identification of situations based on synergetic model. SUMMA, 2021, pp. 509--514. DOI: https://doi.org/10.1109/SUMMA53307.2021.9632207

[25] Suyatinov S.I., Buldakova T.I., Vishnevskaya Yu.A. Synergistic model of situational awareness of the human operator. Society 5.0: Human-centered society challenges and solutions. Cham, Springer, 2022, pp. 331--340. DOI: https://doi.org/10.1007/978-3-030-95112-2_27