ALGORITHM FOR CLASSIFICATION OF FIRE HAZARDOUS SITUATIONS BASED ON NEURAL NETWORK TECHNOLOGIES
Abstract
Modern technological requirements and developing urban infrastructure pose the task of developing
methods for recognizing and classifying fire hazardous situations. Quickly and effectively recognizing the
initial signs of a fire becomes a vital aspect of ensuring the safety of people as well as property. In this
regard, systems are developed, implemented, tested and implemented that can automatically recognize
and classify fire hazardous situations. Classification of fire hazardous situations allows you to determine
the degree of danger of detected deviations, which contributes to making more effective decisions to prevent
the consequences of fires and their signs, such as a one-time short-term increase in temperature and
smoke level, which may indicate failure of electrical components located near the sensors. The algorithm
for classifying fire hazardous situations is developed for a complex of interconnected sensors, which in
turn, due to its structure, allows you to detect even the slightest sign of fire. Within the framework of this
study, an algorithm for classifying fire hazardous situations based on neural network technologies is presented.
A description of existing classes of fire hazardous situations is provided, as well as the criteria by
which data for these classes were marked. The algorithm was modeled on training and test samples, presenting
the accuracy parameters used, the formula for their calculations, and the results of classifying fire
hazardous situations. A study was carried out of the influence of the sample step in the database sample
on the accuracy parameters and training time of the neural network. The developed algorithm is implemented
in the Python programming language in the PyCharm IDE. The dataset for training and testing
was obtained from real sources containing information about detected fire hazardous situations in subways in which a complex of interconnected sensors is installed. The results of modeling the algorithm
showed that the proposed algorithm has high accuracy for predictive classification of fire hazardous situations
in real objects.
References
solutions], Transport, Protivopozharnaya zashchita. Pozharnaya avtomatika. Sredstva spaseniya
[Transport, Fire protection. Fire automatics. Rescue means], 2018.
2. Sautin I.G. Osoboe mnenie. Mozhno li doverit' svoyu zhizn' dymovomu pozharnomu izveshchatelyu?
[Special opinion. Can you trust your life to a smoke alarm? ], Algoritm bezopasnosti [Security algorithm],
2019, No. 6.
3. Ermilov A.V., Smirnov V.A. Razvitie intellektual'noy sostavlyayushchey upravlencheskoy kompetentnosti
nachal'nika karaula pozharno-spasatel'noy chasti [Development of the intellectual component of managerial
competence of the chief of the guard of the fire and rescue unit], Tekhnologii tekhnosfernoy
bezopasnosti [Technosphere safety technologies], 2017, No. 3, pp. 178-185.
4. Polekhin P.V. [i dr.]. Pozhary i pozharnaya bezopasnost' v 2020 godu: Sb. statey [Fires and fire safety
in 2020: stat. sat.], under general ed. D.M. Gordienko. Moscow: VNIIPO, 2021, 112 p.
5. Zaytsev A.V. Dostovernost' i svoevremennost' obnaruzheniya pozhara, i kak ikh uchest' v normakh na
SPS [Reliability and timeliness of fire detection, and how to take them into account in the standards
for fire protection systems], Algoritm bezopasnosti [Safety Algorithm], 2016, No. 2.
6. Ivanov A.N., Vikman A.V., Utkin O.V. Primenenie nechetkoy logiki dlya otsenki veroyatnosti
vypolneniya pozharnymi izveshchatelyami funktsii osnovnogo naznacheniya [Application of fuzzy
logic to assess the probability of fire detectors performing their main function], Prirodnye i tekhnogennye
riski (fiziko-matematicheskie i prikladnye aspekty) [Natural and man-made risks (physical,
mathematical and applied aspects)], 2019, No. 4 (32), pp. 48-52.
7. Pronevich O.B., SHubinskiy I.B. Avtomatizirovannaya sistema prognozirovaniya pozharnoy
bezopasnosti ob"ektov zheleznodorozhnogo transporta na osnove otsenki riskov [Automated system
for predicting fire safety of railway transport facilities based on risk assessment], Nadezhnost' [Reliability],
2019, 19 (1), pp. 48-54. Available at: https://doi.org/10.21683/1729-2646-2019-19-1-48-54.
(data obrashcheniya 25.01.23).
8. Ivanov A.N. K voprosu ob otsenke effektivnosti pozharnoy avtomatiki [On the issue of assessing the
effectiveness of fire automatics // Fire safety: modern challenges], Pozharnaya bezopasnost':
sovremennye vyzovy. Problemy i puti resheniya: materialy Vseros. nauch.-prakt. konf. [Fire safety:
modern challenges. Problems and solutions: materials of the All-Russian Scientific and Practical Conference].
Saint Petersburg: Un-t GPS MCHS Rossii, 2021.
9. Presnov A.I. [i dr.]. Pozharnaya tekhnika: ucheb. [Firefighting equipment: textbook]: in 2nd part. Part
2. Saint Petersburg: Un-t GPS MCHS Rossii, 2016, 404 p.
10. Rassel Dzhessi. Assotsiativnaya pamyat' na neyronnykh setyakh [Associative memory on neural networks].
Moscow: VSD, 2018, 804 p.
11. Solovyeva E. Types of recurrent neural networks for non-linear dynamic system modeling, Proceedings
of 2017 XX IEEE International Conference on Soft Computing and Measurements (SCM2017).
St. Petersburg: Saint-Petersburg Electrotechnical University «LETI». Russia, St. Petersburg, May
24−26, 2017, pp. 1-4.
12. Wang, Z., Yan, W., Oates, T. Time series classification from scratch with deep neural networks:
A strong baseline, In: 2017 International Joint Conference on Neural Networks. IJCNN, IEEE, 2017,
pp. 1578-1585.
13. Kate R.J. Using dynamic time warping distances as features for improved timeseries classification,
Data Min. Knowl. Discov., 2016, 30 (2), pp. 283-312.
14. Peng Y., Kondo N., Fujiura T., Suzuki T., Ouma S., Yoshioka H., Itoyama E., et al. Dam behavior patterns
in Japanese black beef cattle prior to calving: Automated detection using LSTM-RNN, Comput.
Electron. Agric., 2020, 169, 105178.
15. Rahman A., Smith D., Little B., Ingham A., Greenwood P., Bishop-Hurley G. Cattle behaviour classification
from collar, halter, and ear tag sensors, Inform. Process. Agric., 2018, 5 (1), pp. 124-133.
16. Abandah G., Abdel-Karim A. Accurate and fast recurrent neural network solution for the automatic
diacritization of Arabic text, Jordan. J. Comp. Inform. Technol., 2020, 6 (2), pp. 103-121.
17. Géron A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and
techniques to build intelligent systems. O’Reilly Media, 2019.
18. Google TensorFlow, TensorFlow. Available at: https://www.tensorflow.org/. 2024 (accessed 22
January 2023).
19. Graves A., Mohamed A.R., Hinton G. Speech recognition with deep recurrent neural networks, In: 2013
IEEE International Conference on Acoustics, Speech and Signal Processingб 2013, pp. 6645-6649.
20. PyTorch documentation. Available at: https://pytorch.org/docs/stable/index.html (accessed 21 January
2023).
21. Candelaria M.D.E., Chua N.M.M., Kee S.-H. Evaluation of Heat-Induced Damage in Concrete Using
Machine Learning of Ultrasonic Pulse Waves, Materials (Basel), 2022, 15 (22), 7914. Available at:
https://doi.org/10.3390/ma15227914.
