Russian Federation
Saint-Petersburg university of State fire service of EMERCOM of Russia (department of fire, emergency rescue equipment and automotive industry, applicant)
Russian Federation
Peter the Great Saint-Petersburg polytechnic university (head of the rector's administrative office)
Russian Federation
The article addresses the critically important task of enhancing the efficiency of emergency monitoring and response systems through the integration and intelligent analysis of heterogeneous data sources. The authors systematize existing state and departmental information systems of EMERCOM of Russia, highlighting the challenge of processing large volumes of unstructured information under time constraints. Particular attention is paid to social networks as the largest source of operational data, which, however, is characterized by a high level of information noise and low reliability. The work substantiates the necessity of applying artificial intelligence and machine learning algorithms to automate processes of verification, classification, and forecasting. A set of principles for processing primary information is proposed, including source reliability assessment, semantic content analysis, emergency classification, and statistical modeling of their development. The key result is a methodological approach aimed at creating a unified intelligent platform capable of ensuring more prompt and evidence-based decision-making for emergency response services, which will ultimately minimize damage and save lives.
emergency forecasting, social networks, artificial intelligence, real-time monitoring, data analysis, information system of EMERCOM of Russia, big data processing
1. Theoretical basis for designing integrated security systems of potentially hazardous facilities / A.V. Matveev [et al.] // International Journal of Applied Engineering Research. 2017. T. 12. № 22. S. 12357–12361.
2. Salekhan M., Kim D.Dzh. Prognozirovanie effektivnosti onlajn-obzorov potrebitelej: podhod k analitike Big Data na osnove analiza nastroenij // Podderzhka Syst. 2016. P. 30–40.
3. El'berg M.S. Imitacionnoe modelirovanie. Krasnoyarsk: Sibirskij federal'nyj un-t, 2017. 128 s.
4. Schastlivcev V.A., Bilyatdinov K.Z. Matematicheskaya model' centra upravleniya v krizisnyh situaciyah MCHS Rossii na osnove ocenki effektivnosti funkcionirovaniya i matric sostoyaniya // Sibirskij pozharno-spasatel'nyj vestnik. 2025. № 2 (37). S. 72–79.
5. Schastlivcev V.A., Bilyatdinov K.Z. Metodika i kompleks algoritmov sovershenstvovaniya upravleniya strukturnymi podrazdeleniyami centra upravleniya v krizisnyh situaciyah MCHS Rossii // Sibirskij pozharno-spasatel'nyj vestnik. 2025. № 4 (39). S. 32–41.
6. Nikolaev D.V., Vostryh A.V., Procenko T.V. Ocenka specializirovannyh programm raschyota bezopasnosti potencial'no opasnyh ob"ektov // Problemy upravleniya riskami v tekhnosfere. 2020. № 2 (54). S. 11–17.
7. Bujnevich M.V., Maksimov A.V., Pelekh M.T. Principy informacionnoj podderzhki sistemnogo proektirovaniya razvitiya seti pozharnyh depo na territorii megapolisa // Nauchno-analiticheskij zhurnal «Vestnik Sankt-Peterburgskogo universiteta Gosudarstvennoj protivopozharnoj sluzhby MCHS Rossii». 2017. № 3. S. 129–135.
8. Bujnevich M.V., Shurakova D.G., Vostryh A.V. Dvuhurovnevaya klasterizaciya suboptimal'nyh zon prikrytiya g. Kostromy podrazdeleniyami MCHS Rossii pri vozniknovenii proisshestvij // Nauchno-analiticheskij zhurnal «Vestnik Sankt-Peterburgskogo universiteta Gosudarstvennoj protivopozharnoj sluzhby MCHS Rossii». 2018. № 2. S. 121–127.
9. Metod ocenki dostovernosti kolichestvennogo analiza riska na ob"ektah neftegazovoj otrasli / A.V. Matveev [i dr.] // Pozharovzryvobezopasnost'. 2018. T. 27. № 1. S. 35–49.
10. Vinsent P. Obnaruzhenie i otslezhivanie lesnyh pozharov v real'nom vremeni s ispol'zovaniem mashinnogo obucheniya i sputnikovyh dannyh // Izvlechenie znanij i mashinnoe obuchenie. 2020. T. 2. № 3. S. 433–446.
11. Pang B. Collecting opinions and analyzing moods // Fundamentals and trends in the search for information. 2008. Vol. 2. № 1. P. 543–561
12. Metodika analiza dannyh o chrezvychajnyh situaciyah v social'nyh setyah / A.V. Vostryh [i dr.] // Sovremennye naukoemkie tekhnologii. 2023. № 6. S. 81–88.
13. TaduResi A. Railway assets: a potential area for big data analysis // Procedia Computer Science. 2015. Vol. 53. P. 457–467.
14. Leontiev A.A. Fundamentals of psycholinguistics // SENSE. 1997. 287 s.
15. Sadegh M. Collecting Opinions and sentiment Analysis // International Journal of Computers and Technologies. 2012. S. 171–178.
16. Marishkina O.A., Schastlivcev V.A. Modul' programmno-apparatnogo kompleksa izvlecheniya informacii iz social'nyh setej, dlya sistem podderzhki prinyatiya reshenij, intellektual'nogo poiska i analiza // Aktual'nye voprosy sovremennoj nauki i obrazovaniya: sb. statej XLII Mezhdunar. nauch.-prakt. konf. Penza, 2024. P. 42–44.
17. Vostryh A.V., Shurakova D.G. Komponenty special'noj informacionnoj tekhnologii postroeniya optimal'nyh marshrutov // Aktual'nye problemy infotelekommunikacij v nauke i obrazovanii (APINO 2018): sb. statej VII Mezhdunar. nauch.-tekhn. i nauch.-metod. konf.: v 4-h t.; pod red. S.V. Bachevskogo. 2018. P. 213–218.
18. Reshenie zadachi vybora optimal'nogo marshruta sledovaniya sil i sredstv podrazdelenij MCHS Rossii k mestu vozniknoveniya proisshestvij s pomoshch'yu algoritma Dejkstry / M.V. Bujnevich [i dr.] // Problemy upravleniya riskami v tekhnosfere. 2018. № 3 (47). P. 68–79.
19. Krahmal'nickaya A.A. Psihologicheskie aspekty upravleniya sotrudnikami v podrazdeleniyah MCHS Rossii: vyzovy i resheniya // Materialy Vseros. nauch.-prakt. konf., posvyashch. Dnyu obrazovaniya grazhdanskoj oborony Rossijskoj Federacii. Himki, 2025. S. 284–287.
20. Fedoruk V.S., Popov P.A., Fedotov S.B. Otchet o nauchno-prakticheskoj rabote «Osnovnye puti povysheniya effektivnosti primeneniya avarijno-spasatel'nyh sluzhb pri likvidacii chrezvychajnyh situacij» // Strategiya grazhdanskoj zashchity: problem i issledovaniya. 2013. Vyp. № 1. T. 3. P. 213–231.
21. Andreev A.V. Iskusstvennyj intellekt i ego rol' v obrabotke bol'shih dannyh // Umnaya cifrovaya ekonomika. 2023. T. 3. № 1. S. 65–69.
22. Kubanov I.N., Schastlivcev V.A., Pasynkov I.V. Prototip programmnogo produkta prognozirovaniya kolichestva pozharov // Aktual'nye voprosy sovremennoj nauki i obrazovaniya: sb. statej XLII Mezhdunar. nauch.-prakt. konf. Penza, 2024. S. 39–41.
23. Karpov Yu. Imitacionnoe modelirovanie sistem. Vvedenie v modelirovanie s AnyLogic 5. SPb.: BHV Peterburg. 2005. 400 s.
24. Frenks B. Revolyuciya v analitike. Kak v epohu Big Data uluchshit' vash biznes s pomoshch'yu operacionnoj analitiki. M.: Tekhnosfera. 2016. 430 s.
25. Onil K. Ubijstvennye bol'shie dannye. Kak matematika prevratilas' v oruzhie massovogo porazheniya. M.: Izdatel'stvo AST. 2017. 340 s.
26. Korshenko O.P. Bezopasnost' zhiznedeyatel'nosti v chrezvychajnyh situaciyah: ucheb. posobie dlya vuzov. Vladivostok: Dal'nevostochnyj federal'nyj un-t, 2014. 85 s.
27. Klaus A. Ob"edinenie dannyh dlya klassifikacii i izvlecheniya ob"ektov. M.: Issledovatel'skij centr virtual'noj real'nosti i vizualizacii VRVis, 2015. 340 s.
28. Grigor'ev I. Anylogic za tri dnya. SPb.: SPPU, 2016. 202 s.
29. Kupriyashkin A.G. Osnovy modelirovaniya sistem. Noril'sk: NII, 2015. 135 s.
30. Barsegyan A.A. Metody i modeli analiza dannyh: OLAP i Data Mining. SPb.: BHV-Peterburg, 2004. 336 s.
