doctoral candidate from 01.01.2024 until now
Tambov State University after G. R. Derzhavin (Department of Mathematical Modeling and Information Technologies, associate professor)
employee from 01.01.2018 until now
Tambov, Tambov, Russian Federation
004.8
Modern automated fire monitoring systems play a key role in preventing catastrophic consequences in technical systems and critical infrastructure facilities. This paper examines contemporary fire detection methods, including the use of wireless sensors, geographic information systems, machine learning technologies, and neural networks. Special attention is given to the application of YOLOv8 algorithms for real-time fire and smoke detection based on video camera images, including those installed on unmanned aerial vehicles and mobile platforms. The study covers the development, training, and optimi-zation of an intelligent decision support system (DSS) inte-grated with the YOLOv8 model. During the experiments, the impact of the number of training epochs, data structure, and preprocessing methods on model accuracy was analyzed using mAP50, Precision, Recall, and F1-score metrics. The results demonstrated that increasing the training dataset, including negative examples, and adapting hyperparameters significantly improve detection accuracy. The developed system provides automatic operator notifi-cations, activation of fire prevention measures, and initiation of emergency response protocols. The paper also discusses prospects for further system development, including fire spread prediction, risk analysis, and integration with emergency management systems.
Artificial intelligence, decision support system, fire monitoring, computer vision.
1. Muhammad K., Ahmad J., Baik S. W. Early fire detection using convolutional neural networks during surveillance for effective disaster management //Neurocomputing. – 2018. – T. 288. – S. 30-42. – DOIhttps://doi.org/10.1016/j.neucom.2017.04.083.
2. Bot K., Borges J. G. A systematic review of applications of machine learning techniques for wildfire management decision support //Inventions. – 2022. – T. 7. – №. 1. – S. 15. – DOIhttps://doi.org/10.3390/inventions7010015.
3. Cruz H. et al. Machine learning and color treatment for the forest fire and smoke detection systems and algorithms, a recent literature review //Artificial Intelligence, Computer and Software Engineering Advances: Proceedings of the CIT 2020 Volume 1. – 2021. – S. 109-120. – DOIhttps://doi.org/10.1007/978-3-030-68080-0_8.
4. Abid, F. A survey of machine learning algorithms based forest fires prediction and detection systems //Fire technology. – 2021. – T. 57. – №. 2. – S. 559-590. – DOIhttps://doi.org/10.1007/s10694-020-01056-z.
5. Lourenço, M. et al. An integrated decision support system for improving wildfire suppression management //ISPRS International Journal of Geo-Information. – 2021. – T. 10. – №. 8. – S. 497. – DOIhttps://doi.org/10.3390/ijgi10080497.
6. Vásquez, F. et al. Decision support system development of wildland fire: a systematic mapping //Forests. – 2021. – T. 12. – №. 7. – C. 943. – DOIhttps://doi.org/10.48550/arXiv.2203.08221.
7. Fillmore, S. D., Paveglio T. B. Use of the Wildland Fire Decision Support System (WFDSS) for full suppression and managed fires within the Southwestern Region of the US Forest Service //International journal of wildland fire. – 2023. – T. 32. – №. 4. – S. 622-635. – DOIhttps://doi.org/10.1071/WF22206.
8. Laptev, N. V. Issledovanie vozmozhnostej iskusstvennyh nejronnyh setej v zadache klassifikacii dinamicheskih priznakov ob"ektov / N. V. Laptev, O. M. Gerget, V. V. Laptev, D. Yu. Kolpashchikov // Izvestiya TPU. Promyshlennaya kibernetika. – 2023. – T. 1, № 1. – S. 44-49. – DOIhttps://doi.org/10.18799/29495407/2023/1/13. – EDN CDLDES.
9. Bryuhanov, A. V. Razvitie sredstv navigacii i sistem podderzhki prinyatiya reshenij v lesnom pozharotushenii / A. V. Bryuhanov, R. V. Kotel'nikov // Sibirskij lesnoj zhurnal. – 2023. – № 6. – S. 128-140. – DOIhttps://doi.org/10.15372/SJFS20230613. – EDN NJBQFM.
10. Shevcov, M. V. Sistema monitoringa pozharnoj i mediko-ekologicheskoj bezopasnosti s ispol'zovaniem analiza videodannyh s bespilotnyh letatel'nyh apparatov: [Tekst]: dis. kand. tekhn. nauk: 23.10.00/ M.V. Shevcov, 2022. – 157 s.
11. Filist, S. A. Intellektual'naya sistema obrabotki izobrazhenij, poluchaemyh s bespilotnyh letatel'nyh apparatov / S. A. Filist, R. A. Tomakova, N. G. Nefedov [i dr.] // Izvestiya Yugo-Zapadnogo gosudarstvennogo universiteta. Seriya: Upravlenie, vychislitel'naya tekhnika, informatika. Medicinskoe priborostroenie. – 2022. – T. 12, № 4. – S. 64-85. – DOI;https://doi.org/10.21869/2223-1536-2022-12-4-64-85. – EDN VYCWMU.
12. Gromov, Yu. Yu. Postroenie GIS dlya ocenki dinamiki konturov lesnyh pozharov / Yu. Yu. Gromov, K. A. Slezin // Pribory i sistemy. Upravlenie, kontrol', diagnostika. – 2018. – № 4. – S. 16-28. – EDN XMTBRZ.
13. Gromov, Yu. Yu. Nejronechetkij klassifikator modelej intellektual'noj geoinformacionnoj sistemy modelirovaniya konturov pozharov / Yu. Yu. Gromov, K. A. Slezin, M. A. Ivanovskij // Promyshlennye ASU i kontrollery. – 2018. – № 10. – S. 15-21. – EDN YLVQHJ.
14. Aparin, A. A. Primenenie videomonitoringa dlya informacionnoj podderzhki prinyatiya upravlencheskih reshenij pri reagirovanii na tekhnogennyj pozhar / A. A. Aparin // Sovremennye problemy grazhdanskoj zashchity. – 2022. – № 3(44). – S. 5-11.
15. Damdynchap, Ch. A. Primenenie nejronnyh setej dlya raspoznavaniya dyma i pozhara na izobrazheniyah / Ch. A. Damdynchap, A. A. Sharapov // Interekspo Geo-Sibir'. – 2021. – T. 7, № 2. – S. 38-43. – EDN QUEEZI.
16. Yakovleva, O. V. O vybore metoda postroeniya nechetkoj modeli prognozirovaniya sostoyaniya akkumulyatora / O. V. Yakovleva, Yu. V. Stroganov, I. V. Rudakov // Vestnik Moskovskogo gosudarstvennogo tekhnicheskogo universiteta im. N.E. Baumana. Seriya Priborostroenie. – 2022. – № 4(141). – S. 36-55. – DOIhttps://doi.org/10.18698/0236-3933-2022-4-36-55. – EDN TIUVXY.
17. Hurtik, P. et al. Binary cross-entropy with dynamical clipping //Neural Computing and Applications. – 2022. – T. 34. – №. 14. – S. 12029-12041. – DOIhttps://doi.org/10.1007/s00521-022-07091-x.
18. Rusiecki, A. Trimmed categorical cross‐entropy for deep learning with label noise //Electronics Letters. – 2019. – T. 55. – №. 6. – S. 319-320. – DOIhttps://doi.org/10.1049/el.2018.7980.
19. Mei S. et al. Research on Fabric Defect Detection Algorithm Based on Improved YOLOv8n Algorithm //Electronics. – 2024. – T. 13. – №. 11. – S. 2009. – DOIhttps://doi.org/10.3390/electronics13112009.
20. Zhou, G., Liu, X., Bi, H. Recognition of UAVs in infrared images based on YOLOv8 //IEEE Access. – 2024. – DOIhttps://doi.org/10.1109/ACCESS.2024.3500583
21. Mihajlichenko, A. A. Analiticheskij obzor metodov ocenki kachestva algoritmov klassifikacii v zadachah mashinnogo obucheniya / A. A. Mihajlichenko // Vestnik Adygejskogo gosudarstvennogo universiteta. Seriya 4: Estestvenno-matematicheskie i tekhnicheskie nauki. – 2022. – № 4(311). – S. 52-59. – DOIhttps://doi.org/10.53598/2410-3225-2022-4-311-52-59. – EDN FVSMBM.
22. Goryachkin, B. S. Analiz chuvstvitel'nosti metrik bi-narnoj klassifikacii k disbalansu dannyh / B. S. Goryachkin, A. A. CHechnev // E-Scio. – 2021. – № 4(55). – S. 23-34. – EDN FQSJTV.
