ALGORITHM FOR CLASSIFICATION OF FIRE HAZARDOUS SITUATIONS BASED ON KOLMOGOROV-ARNOLD NETWORK
Cite as: S. Singh, A.V. Pribylskiy. Algorithm for classification of fire hazardous situations based on Kolmogorov-Arnold network. // Izvestiya SFedU. Engineering Sciences – 2024. – N. 6. - P. 6-15. doi: 10.18522/2311-3103-2024-6-6-15
Abstract
The problem of timely and accurate detection of fire hazardous situations is critical to ensure the
safety of people and property. Traditional monitoring methods based on simple threshold values for smoke
and temperature sensors are often insufficiently effective, as they can lead to false alarms or miss real fire
hazardous situations. Modern methods using neural networks can significantly improve the accuracy of
classifying an emergency situation by analyzing complex patterns in sensor data, which are complex nonlinear
functions with dynamically changing parameters. The development of such models requires attention
to the collection, labeling and processing of data, to the choice of neural network architecture for a
specific task, because high-quality data labeling and the choice of the desired neural network architecture
directly affect the selection of the desired patterns, as well as the detection of hidden patterns that are
impossible or difficult to determine by traditional methods. The article examines an algorithm for classifying fire hazardous situations based on the Kolmogorov-Arnold network (KAN). This algorithm is used to
process data from a complex of interconnected fire sensors and is designed to detect and classify various
types of fire hazardous situations. The key element of the development is the use of the Kolmogorov-
Arnold network, which, due to its architecture, is capable of modeling complex functional dependencies
between input data. Readings from a complex of interconnected fire sensors, such as temperature and
smoke sensors, are used as input data. To improve the accuracy of classification, data is labeled using
expert knowledge. The Python programming language was used to implement the algorithm, together with
the Pytorch, pykan, and scikit-learn libraries. The article presents the results of testing the model on real
data and discusses possible directions for further improvement of the algorithm. During the experiments,
it was shown that the proposed model demonstrates high accuracy in classifying fire hazardous situations,
which is not inferior to traditional methods of data classification.
References
2. Ziming Liu, Yixuan Wang. KAN: Kolmogorov-Arnold Networks, 30 Apr 2024. DOI:
https://doi.org/10.48550/arXiv.2404.19756.
3. Sautin I.G. Protivopozharnaya zashchita: tekhnologii i resheniya [Fire protection: technologies and
solutions], Transport, Protivopozharnaya zashchita. Pozharnaya avtomatika. Sredstva spaseniya
[Transport, Fire protection. Fire automation. Rescue equipment], 2018.
4. Sautin I.G. Osoboe mnenie. Mozhno li doverit' svoyu zhizn' dymovomu pozharnomu izveshchatelyu?
[Dissenting opinion. Can you trust your life to a smoke alarm? ], Algoritm bezopasnosti [Security Algorithm],
2019, No. 6.
5. Singkh S., Pribyl'skiy A.V. Sintez sistemy sverkhbystrogo obnaruzheniya pozharoopasnykh situatsiy na
osnove kompleksa vzaimosvyazannykh datchikov [Synthesis of a system for ultra-fast detection of fire
hazardous situations based on a complex of interconnected sensors], Izvestie YuFU. Tekhnicheskie
nauki [Izvestiya SFedU. Engineering Sciences], 2024, No. 2, pp. 121-132.
6. Singkh S., Pribyl'skiy A.V. Algoritm klassifikatsii pozharoopasnykh situatsiy na osnove neyrosetevykh
tekhnologiy [Algorithm for classification of fire hazardous situations based on neural network technologies],
Izvestie YuFU. Tekhnicheskie nauki [Izvestiya SFedU. Engineering Sciences], 2024, No. 3, pp. 138-147.
7. NFPA 72: National Fire Alarm and Signaling Code, 2019.
8. UL 268: Standard for Smoke Detectors for Fire Protective Signaling Systems, 2019.
9. ISO 7240-14: Fire detection and alarm systems – Part 14: Requirements and test methods for smoke
detectors, 2018.
10. BS 5839-1:2017: Fire alarm systems for commercial and industrial premises. Code of practice for
design, installation, commissioning and maintenance.
11. GOST R 53325-2009: Sistemy pozharnoy signalizatsii. Obshchie tekhnicheskie trebovaniya [GOST R
53325-2009: Fire alarm systems. General technical requirements].
12. Polekhin P.V. [i dr.]. Pozhary i pozharnaya bezopasnost' v 2020 godu: Sb. statey [Fires and fire safety in
2020: Collection of articles], under the general ed. of D.M. Gordienko. Moscow: VNIIPO, 2021, 112 p.
13. 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.
14. 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.
15. Fedorov A., Bytcinskaya T., Lukyanchenko A., Hung T.D. Trends in the development of automatic fire
detectors, Technol. Technosphere Saf., 2009, 23, pp. 111-114. Available online: https://cyberleninka.ru/
article/n/tendentsii-razvitiya-avtomaticheskih-pozharnyh-izveschateley-1 (accessed on 20 December
2023).
16. Han J., Kamber M., & Pei J. Data Normalization for Big Data Analytics, IEEE Transactions on
Knowledge and Data Engineering, 2017, 29 (10), pp. 2435-2448. DOI: 10.1109/TKDE.2017.2734444.
17. Rao S.S., Iyengar S.S., & Venayagamoorthy G.K. Big Data Normalization: A Survey, IEEE Transactions
on Big Data, 2018, 4 (2), pp. 149-163. DOI: 10.1109/TBDATA.2018.2823718.
18. Singh A.K., Singh S.K., & Singh R.K. Data Parsing and Normalization for Social Media Analytics, Journal
of Intelligent Information Systems, 2020, 56 (2), pp. 257-273. DOI: 10.1007/s10844-019-00563-4.
19. Liu J., Zhang Y., & Li X. Machine Learning for Data Normalization in Big Data Analytics, IEEE
Transactions on Neural Networks and Learning Systems, 2019, 30 (1), pp. 201-214. DOI:
10.1109/TNNLS.2018.2873818.
20. Kate R.J. Using dynamic time warping distances as features for improved timeseries classification,
Data Min. Knowl. Discov, 2016, 30 (2), pp. 283-312.
21. 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.
22. Géron A. Hands-on machine learning with Scikit-Learn, Keras, and TensorFlow: Concepts, tools, and
techniques to build intelligent systems. O’Reilly Media, 2019.
23. Pykan documentation and apps. Available at: https://github.com/KindXiaoming/pykan (accessed 03
August 2024).
24. Scikit-learn for supervised learning documentation. Available at: https://scikit-learn.org/stable/ supervised_
learning.html (03 August 2024).
25. MathWorks. «MATLAB & Simulink Help Center» MathWorks, 2023. Available at:
https://www.mathworks.com/help/index.html (accessed 20 December 2023).
26. Bozorgasl Z., & Chen H. Wav-KAN: Wavelet kolmogorov-arnold networks, arXiv preprint
arXiv:2405.12832, June 2024. Retrieved from https://arxiv.org/abs/2405.12832.
27. Federico Girosi, Tomaso Poggio. Representation Properties of Networks: Kolmogorov's Theorem Is
Irrelevant, Neural Comput., 1989, 1 (4), pp. 465-469. DOI: https://doi.org/10.1162/neco.1989.1.4.465.
28. Galitsky B.A. Kolmogorov-Arnold Network for Word-Level Explainable Meaning Representation,
Preprints, 2024. Retrieved from https://www.preprints.org/manuscript/202405.1981.
29. Hao H., Zhang X., Li B., & Zhou A. A First Look at Kolmogorov-Arnold Networks in Surrogateassisted
Evolutionary Algorithms, arXiv preprint arXiv:2405.16494, 2024. Retrieved from
https://arxiv.org/abs/2405.16494.
30. Vaca-Rubio C.J., Blanco L., & Pereira R. Kolmogorov-Arnold Networks (KANs) for Time Series
Analysis, arXiv preprint arXiv:2405.08790, 2024. Retrieved from https://arxiv.org/abs/2405.08790.
31. Galitsky B.A. Kolmogorov-Arnold Network for Word-Level Explainable Meaning Representation,
Preprints, 2024. Retrieved from https://www.preprints.org/manuscript/202405.1981.
32. Genet R., & Inzirillo H. TKAN: Temporal Kolmogorov-Arnold Networks, arXiv preprint
arXiv:2405.07344, 2024. Retrieved from https://arxiv.org/abs/2405.07344.
