With the development of a three-level mivar expert system (MES) for fire detection, the need for mathematical and algorithmic support arises. The previously proposed model and method defined the logical structure of the MES and the method of information processing. The article proposes mathematical and algorithmic support for information processing and decision-making in the operation of a three-level mivar expert system for fire detection. The proposed support includes: a formalized description of the MES operating cycle; information support for forming MES input information based on the coordination of data from visual, infrared, temperature, gas and acoustic channels; as well as algorithmic support for MES working memory and logical inference. The implementation uses asynchronous sensor-stream alignment, INT8 weight quantization of the FNN, and indexed access to the DOM tree. On a synthetic test set of 5,000 records, the FNN INT8 + MES configuration achieved 94.88 % accuracy, an F1-score of 94.87 %, and an FPR of 5.00 %; the median update latency for 52 parameters decreased from 3.202 to 0.039 ms. The scientific novelty of the work lies in the development of mathematical and algorithmic support for information processing and decision-making in the operation of a three-level mivar expert system for fire detection, including a formalized description of the MES operating cycle, information support for forming MES input information, and algorithmic support for working memory and logical inference.
1. Dheyab O.A., Chernikov D.Yu., Selivanov A.S. Integration of deep learning and wireless sensor networks for accurate fire detection in indoor environment. Journal of Siberian Federal University. Engineering and Technologies. 2024;17(1):124–135.
2. Kanashchenkov A.I., Tikhonov A.I., Novikov S.V., Kulakova D.S. Application of radio-electronic systems for remote monitoring of agriculture for fire detection and firefighting support. Moscow Economic Journal. 2016;1(4):10. (In Russ.). URL: https://qje.su/ru/nauka/publications/article/6a9c154632807fdbab868031/primenenie-radioelektronnyh-sistem-dlya-distancionnogo-monitoringa-sel-skogo-hozyaystva-s-cel-yu-obnaruzheniya-i-obespecheniya-tusheniya-pozharov/view
3. Kataev M.Yu., Kartashov E.Yu. Computer Vision Method for Forest Fires Detection Based on RGB Images Obtained by Unmanned Motor Glider. Light & Engineering. 2021;29(5):71–78. https://doi.org/10.33383/2021-009
4. Bokadarov S.A., Gudkov M.A., Shcherbachenko D.G. Application of GIS technologies for rapid forest fire detection and monitoring of the forest fire situation. Modern Technologies for Civil Defense and Emergency Response. 2015;(1-2):164–167. (In Russ.).
5. Astratov O.S., Smirnov V.M., Filatov V.N., Mitko A.V. Video monitoring system for forest fire detection near an industrial enterprise. Delovoy zhurnal Neftegaz.RU. 2020;(2):58–61. (In Russ.).
6. Abdusalomov A.B., Islam B.M.S., Nasimov R., Mukhiddinov M., Whangbo T.K. An improved forest fire detection method based on the Detectron2 model and a deep learning approach. Sensors. 2023;23(3):1512. https://doi.org/10.3390/s23031512
7. Yar H., Khan Z.A., Rida I., Ullah W., Kim M.J., Baik S.W. An efficient deep learning architecture for effective fire detection in smart surveillance. Image and Vision Computing. 2024;145(1):104989. https://doi.org/10.1016/j.imavis.2024.104989
8. Ahn Y., Choi H., Kim B.S. Development of early fire detection model for buildings using computer vision-based CCTV. Journal of Building Engineering. 2022;65:105647. https://doi.org/10.1016/j.jobe.2022.105647
9. Yang S., Huang Q., Yu M. Advancements in remote sensing for active fire detection: a review of datasets and methods. The Science of The Total Environment. 2024;943(11):173273. https://doi.org/10.1016/j.scitotenv.2024.173273
10. Pincott J., Tien P.W., Wei Sh., Calautit J.K.S. Indoor fire detection utilizing computer vision-based strategies. Journal of Building Engineering. 2022;61(5):105154. https://doi.org/10.1016/j.jobe.2022.105154
11. Talaat F.M., ZainEldin H. An improved fire detection approach based on YOLO-v8 for smart cities. Neural Computing and Applications. 2023;35(28):20939–20954. https://doi.org/10.1007/s00521-023-08809-1
12. Zhao H., Jin J., Liu Y., Guo Y., Shen Y. FSDF: a high-performance fire detection framework. Expert Systems with Applications. 2023;238(41):121665. https://doi.org/10.1016/j.eswa.2023.121665
13. Mashchenko E.I., Karpov D.K., Varlamov O.O., Adamova L.E., Balenko E.G. Creation of a Mivar Expert System for Understanding Images and Making Decisions When People Fall. Problems of Artificial Intelligence. 2024;(4):88–100. (In Russ.). https://doi.org/10.24412/2413-7383-2024-4-88-100
14. Varlamov O.O. Application of mivar technologies of logical artificial intelligence for creation of smart manufacturing systems. Information and Mathematical Technologies in Science and Management. 2025;(2):32–46. (In Russ.). https://doi.org/10.25729/ESI.2025.38.2.003
15. Turchaninov D.V., Varlamov O.O. Mivar expert system for safety monitoring in a mega-laboratory. Sistemy upravleniya i informatsionnye tekhnologii. 2025;(2-1):60–69. (In Russ.).
16. Gong S. Mivar Decision-Making System for Distribution and Transportation of Cargo by a Team of Warehouse Robots. Sistemy upravleniya i informatsionnye tekhnologii. 2025;(2):23–29. (In Russ.).
17. Gong S. Mivar decision-making system for optimized cargo distribution for groups of warehouse robots. Modeling, Optimization and Information Technology. 2025;13(3). (In Russ.). https://doi.org/10.26102/2310-6018/2025.50.3.047
18. Aladin D.V. Mivar knowledge base automatic generation method for solving management tasks in state space. Problems of Artificial Intelligence. 2025;(3):88–99. (In Russ.). https://doi.org/10.24412/2413-7383-2025-3-38-88-99
19. Aladin D.V. Mivar Knowledge Base Model for Management Task Solving in State Space. Neurocomputers. 2025;27(4):66–71. (In Russ.). https://doi.org/10.18127/j19998554-202504-06
20. Dou L. Method for information processing and modification of threshold parameters of rules in a mivar expert system using large language models. Problems of Artificial Intelligence. 2025;(4):194–205. (In Russ.). https://doi.org/10.24412/2413-7383-2025-4-39-194-205
21. Dou L. Decision-making model for fire detection based on pattern recognition and mivar expert system. Sistemy upravleniya i informatsionnye tekhnologii. 2025;(3):59–65. (In Russ.).
22. Dou L. Mathematical and algorithmic support for automatic rule updates in a mivar expert system using large language models. Modeling, Optimization and Information Technology. 2026;14(5). (In Russ.). https://doi.org/10.26102/2310-6018/2026.56.5.013
