NEUROCOGNITIVE METHODS AND ALGORITHMS OF FEDERATED LEARNING OF INTELLIGENT INTEGRATED INFORMATION MANAGEMENT SYSTEMS IN A REAL COMMUNICATIVE ENVIRONMENT
Abstract
Unlike existing methods of teaching artificial intelligence systems, approaches based on federated
learning will not require a long and expensive procedure for preparing a training sample when
creating and mass practical application of "smart" agricultural systems, autonomous unmanned
agricultural machines and robots, and the knowledge obtained by the decision-making system will be
updated on an ongoing basis. The aim of the research is to develop and implement end-to-end artificial
intelligence technology, the lack of which today prevents the creation of integrated information
management systems for crop and livestock production ("smart" agricultural systems) based on the
group application of unmanned ground and aerial agricultural machines and robots. The introduction
of such intelligent systems is necessary to preserve and improve the products produced and ensure
the sustainable development of agriculture. The article describes neurocognitive methods and
algorithms of federated learning of intelligent agricultural process management systems in a real environment. The structure of data and knowledge exchange in the smart field system based on a
distributed network of intelligent agents managing smart field systems on various agricultural lands,
based on federated learning, is also proposed. Each intelligent agent is a software model of the neurocognitive
processes of reasoning and decision-making within the framework of solving a specific
task. The proposed structure will facilitate the joint accumulation of a knowledge base in the field of
agriculture and will be able to become the basis for many different intelligent agents that effectively
perform specific tasks within a distributed network of smart field management systems. There is also
a description of intelligent agents performing various tasks in a real environment. Examples of autonomous
robotic and software complexes being developed are given, on the basis of which it is
planned to test the proposed concept of federated training of "smart" field systems. At the same time,
the article describes the expected effects of the introduction of technologies based on the developed
methods and algorithms of federated training of intelligent agents controlling smart field systems.
References
rubezhom [Development of smart agriculture in Russia and abroad], Upravlenie riskami r APK
[Risk management in the agro-industrial complex], 2020, No. 2, pp. 62-72. Available at:
http://www.agrorisk.ru.
2. Belykh D.V., Medvedeva L.N. "Umnaya tekhnika" i "umnye tekhnologii" v obespechenii
razvitiya sel'skogo khozyaystva [“Smart technology” and “smart technologies” in ensuring the
development of agriculture], Sovremennoe ekologicheskoe sostoyanie prirodnoy sredy i
nauchno-prakticheskie aspekty ratsional'nogo prirodopol'zovaniya, S. Solenoe Zaymishche, 28
fevralya 2018 goda [Current ecological state of the natural environment and scientific and
practical aspects of rational environmental management, Solenoye Zaimishche Village, February
28, 2018]. – Solenoye Zaimishche Village: Prikaspiyskiy nauchno-issledovatel'skiy institut
aridnogo zemledeliya, 2018, pp. 1349-1353.
3. Bzhikhatlov K.Ch., Zagazezheva O.Z. Razrabotka modeli vzaimodeystviya v sotsio-ekologoekonomicheskoy
sisteme sel'skikh territoriy v usloviyakh vnedreniya novykh tekhnologiy
[Development of a model of interaction in the socio-ecological-economic system of rural territories
in the context of the introduction of new technologies], Izvestiya Kabardino-
Balkarskogo nauchnogo tsentra RAN [News of the Kabardino-Balkarian Scientific Center of
the RAS], 2022, No. 6 (110), pp. 194-202. DOI: 10.35330/1991-6639-2022-6-110-194-202.
4. Chernenko A.B., Chernikov N.S., Baginskiy N.A., Sysoev M.I. Osobennosti primeneniya
robotizirovannykh platform v sel'skom khozyaystve [Features of the use of robotic platforms
in agriculture], Problemy nauki [Problems of science], 2020, No. 8 (153). Available at:
https://cyberleninka.ru/article/n/osobennosti-primeneniya-robotizirovannyh-platform-vselskom-
hozyaystve (accessed 27 February 2024).
5. Pshenokova I.A., Bzhikhatlov K.Ch., Unagasov A.A., Abazokov M.A. Mul'tiagentnyy algoritm
sbora dannykh s meteostantsii dlya prognozirovaniya urozhaynosti i sostoyaniya posevov
[Multi-agent algorithm for collecting data from a weather station to predict the yield and condition
of crops], Izvestiya YuFU. Tekhnicheskie Nauki [Izvestiya SFedU. Engineering Sciences],
2022, No. 1 (225), pp. 91-101.
6. Hachimi C.E., et al. Smart Weather data management based on artificial intelligence and big
data analytics for precision agriculture, Agriculture, 2022, Vol. 13, No. 1, pp. 95.
7. Nagoev Z., Pshenokova I., Anchekov M. Model of the reasoning process in a mul-tiagent cognitive
system, Procedia Computer Science, 2020, 169, pp. 615-619. Available at:
https://DOI.org/10.1016/j.procs. 2020.02.202.
8. Konoshin D.I., Izmes'ev M.M. Osobennosti primeneniya intellektual'nykh sistem opryskivaniya
v sel'skom khozyaystve [Features of the use of intelligent spraying systems in agriculture],
Agrarnaya nauka - 2022: Mater. vserossiyskoy konferentsii molodykh issledovateley, Moskva,
22–24 noyabrya 2022 goda [Agrarian Science - 2022: Proceedings of the All-Russian Conference
of Young Researchers, Moscow, November 22–24, 2022]. Moscow: Rossiyskiy
gosudarstvennyy agrarnyy universitet - MSKhA Im. K.A. Timiryazeva, 2022, pp. 1074-1077.
9. Nagoev Z., Pshenokova I., Anchekov M. Model of the reasoning process in a mul-tiagent cognitive
system, Procedia Computer Science, 2020, 169, pp. 615-619. Available at:
https://DOI.org/10.1016/j.procs. 2020.02.202.
10. Nagoev Z., Pshenokova I., Nagoeva O., and Kankulov S. Situational analysis model in an intelligent
system based on multi-agent neurocognitive architectures, Journal of Physics: Conference
Series (JPCS), 2021, 2131, 022103. DOI: 10.1088/1742-6596/2131/2/022103.
11. Jabir Brahim, Rabhi Loubna, Falih Noureddine. RNN - and CNN-Based weed detection for
crop improvement: An Overview, Foods And Raw Materials, 2021, No. 2. DOI:
10.21603/2308-4057-2021-2-387-396.
12. Murad N.Y., Mahmood T., Forkan A.R.M, Morshed A., Jayaraman P.P., Siddiqui M.S. Weed
Detection Using Deep Learning: A Systematic Literature Review, Sensors (Basel), 2023 Mar.
31, 23 (7), 3670. DOI: 10.3390/s23073670.
13. Erunova Marina G., Pisman Tamara I., Shevyrnogov Anatoliy P. The technology for detecting
weeds in agricultural crops based on vegetation index VARI (planetscope), Zhurnal SFU.
Tekhnika i tekhnologii [Journal of SFU. Technics and techology], 2021, No. 3. Available at:
https://cyberleninka.ru/article/n/the-technology-for-detecting-weeds-in-agricultural-cropsbased-
on-vegetation-index-vari-planetscope (accessed 29 February 2024).
14. Badhan S., Desai K., Dsilva M., Sonkusare R. and Weakey S. Real-Time Weed Detection using
Machine Learning and Stereo-Vision, 6th International Conference for Convergence in Technology
(I2CT), Maharashtra, India, 2021, pp. 1-5. DOI: 10.1109/I2CT51068.2021.9417989.
15. Filbert H. Juwono, W.K. Wong, Seema Verma, Neha Shekhawat, Basil Andy Lease, Catur
Apriono. Machine learning for weed–plant discrimination in agriculture 5.0: An in-depth review,
Artificial Intelligence in Agriculture, 2023, Vol. 10, pp. 13-25. DOI:
10.1016/j.aiia.2023.09.002.
16. Wang P., Tang Y., Luo F., Wang L., Li C., Niu Q. and Li H. Weed25: A deep learning dataset
for weed identification, Front. Plant Sci., 2022, Vol. 13.
17. Cheng C., Fu J., Su, H., Ren, L. Recent advancements in agriculture robots: Benefits and Challenges,
Machines, 2023, 11, pp. 48. DOI: 10.3390/machines11010048.
18. Mitrofanova Olga & Blekanov Ivan & Sevostyanov Danila & Zhang Jia & Mitrofanov
Evgenii. Development of a robot for agricultural field scouting, In Lecture Notes in Computer
Science, 2023, pp. 185-196. DOI: 10.1007/978-3-031-43111-1_17.
19. Zhang Anzheng & Pan Yuzhen & Zhang Chenyun & Wang Jinhua & Chen Guangrong &
Shang Huiliang. Design and implementation of a novel agricultural robot with multi-modal
kinematics, In Intelligent Robotics and Applications, 2023, pp. 395-406. Springer Nature Singapore.
DOI: 10.1007/978-981-99-6480-2_33.
20. Bzhikhatlov K.Ch., Zagazezheva O.Z., Mambetov I.A. Kontseptsiya intellektual'noy sistemy
zashchity rasteniy i otsenka effektivnosti ee vnedreniya [The concept of an intelligent plant
protection system and assessment of the effectiveness of its implementation], Perspektivnye
sistemy i zadachi upravleniya: Mater. XVIII vserossiyskoy nauchno-prakticheskoy konferentsii
i XIV molodezhnoy shkoly-seminara. Posvyashchaetsya pamyati pochetnogo chlena
orgkomiteta konferentsii, voditelya pervogo lunokhoda, general-mayora V.G. Dovganya, p.
Dombay, Karachevo-Cherkesskaya Respublika, 03–07 aprelya 2023 goda [Perspective systems
and management tasks: Materials of the XVIII All-Russian scientific and practical conference
and the XIV youth school-seminar. Dedicated to the memory of the honorary member
of the conference organizing committee, the driver of the first lunar rover, Major General
V.G. Dovganya, Dombay, Karachevo-Cherkess Republic, April 03–07, 2023]. Taganrog:
Obshchestvo s ogranichennoy otvetstvennost'yu izd-vo "Lukomor'e", 2023, pp. 404-412.
21. Alzaghir A. Flying fog mobile edge computing based on UAV-assisted for iot nodes in smart
agriculture, Proceedings of Telecommunication Universities, 2022, Vol. 8, No. 4, pp. 82-88.
DOI: 10.31854/1813-324x-2022-8-4-82-88.
22. Nagoev Z.V. Intellektika, ili Myshlenie v zhivykh i iskusstvennykh sistemakh [Intelligence, or
Thinking in living and artificial systems]. Nal'chik: Izd-vo KBNTS RAN, 2013.
