Novokuznetsk, Russian Federation
The paper introduces a comprehensive review of various approaches to using neural networks in the design of control systems for closed-end agricultural facilities. The empirical part of the study featured technical statistics of agro-industrial enterprises. It applied trained neural networks to agricultural enterprise data for prediction purposes. The resulting root mean square error was 0.120, and the standard deviation did not exceed 0.093. Neural networks proved efficient as part of specialized software for monitoring technical objects of the agro-industrial complex and predicting their development.
neural networks, machine learning, multilayer perceptron, statistics, forecasting, models, forecasting, agriculture, agro-industrial complex equipment
1. Kartechina N. V. Vidy neyronnyh setey i ih primenenie / N. V. Kartechina [i dr.] // Nauka i Obrazovanie. 2021. T. 4. № 3.
2. Mak-Kallok U. S. Logicheskoe ischislenie idey, otnosyaschihsya k nervnoy aktivnosti / U. S. Mak-Kallok, V. Pitts. // Avtomaty. Pod red. K. E. Shennona i Dzh. Makkarti. - M.: Izd-vo inostr. lit., 1956. - S. 363-384.
3. Yan Lekun. Kak uchitsya mashina. Revolyuciya v oblasti neyronnyh setey i glubokogo obucheniya / Lekun Yan. - M.: Al'pina non-fikshn, 2021. - 351 s.
4. Timofeev M. G. Iskusstvennyy intellekt v sel'skom hozyaystve / M. G. Timofeev [i dr.] // Nauka i Obrazovanie. 2020. T. 3. № 4. S. 71.
5. Yurchenko, I. F. Integraciya cifrovyh sistem v sferu agroproizvodstva na meliorirovannyh zemlyah / Yurchenko I. F. // Mezhdunarodnyy tehniko-ekonomicheskiy zhurnal. 2020. № 4. S. 73-80.
6. Ilyshev, A. P. Iskusstvennyy intellekt i neyrosetevye tehnologii v cifrovoy platforme proryvnogo razvitiya rossiyskogo APK / A. P. Ilyshev, O. M. Tolmachev // Ekonomika i socium: sovremennye modeli razvitiya. 2019. T. 9, № 4(26). S. 492-507. DOI: https://doi.org/10.18334/ecsoc.9.4.100453
7. Torikov V. E. Sostoyanie cifrovoy transformacii sel'skogo hozyaystva / V. E. Torikov [i dr.] // Vestnik Kurskoy GSHA. 2020. № 9. S. 6-13.
8. Windsor F. M. Network science: Applications for sustainable agroecosystems and food security / Fredric M. Windsor [et al.] // Perspectives in Ecology and Conservation. 2022. Vol. 20, No. 2. P. 79-90.
9. Petrescu I. E. Risk Management of Agri-Food Value Chains-Exploring Research Trends from the Web of Science / I. E. Petrescu [et al.] // Digitalization and Big Data for Resilience and Economic Intelligence. - Springer, Cham, 2022. - P. 55-66.
10. Grachev A. V. O metode ocenivaniya promezhutochnyh uzlov peredachi dannyh dlya marshrutizacii v ierarhicheskih setyah raznoy topologii / A. V. Grachev [i dr.] // Vestnik Voronezhskogo gosudarstvennogo universiteta. Seriya: Sistemnyy analiz i informacionnye tehnologii. 2015. № 1. S. 32-38.
11. Tokarev K. E. Teoriya i cifrovye tehnologii intellektual'noy podderzhki prinyatiya resheniy dlya uvelicheniya bioproduktivnosti agroekosistem na osnove neyrosetevyh modeley / K. E. Tokarev [i dr.] // Izvestiya Nizhnevolzhskogo agrouniversitetskogo kompleksa: Nauka i vysshee professional'noe obrazovanie. 2021. № 4(64). S. 421-440.
