A method for hybrid filtering of information from fire sensors based on a weighted median filter with a finite impulse response and a Kalman filter

The relevance of this study necessitated improving the resilience of recursive fire hazard prediction systems to various types of disturbances, such as vibrations, electromagnetic interference, and cumulative forecast errors. In such cases, even a minor impact on predicted time series can lead to false alarms or missed threats, which is especially critical in areas with high occupant illumination, such as subways. Existing filters, when used in isolation, do not consistently suppress Gaussian and impulsive signals, preserving sharp signal changes and minimizing phase shift. Therefore, a hybrid filter method combining a Kalman filter and a weighted FIR hybrid median filter was developed and evaluated. The method's effectiveness is evaluated using synthetic and in-house data (including ~6 million samples from subway sensors) using a combination of metrics: MAE, MSE, SNR, derivative result accuracy, and response time. The proposed hybrid is shown to provide the best results: a reduction in MAE to 0.419, an increase in SNR to 2.05 dB, and an accuracy level of 99.98%. The papers' materials are of practical value to fire safety system developers and early sensor data processing specialists.

1. Janjanam L., Saha S.K., Kar R., Mandal D. Adaptive recursive system identification using optimally tuned Kalman filter by the metaheuristic algorithm. Soft Computing. 2024;28:7013–7037. https://doi.org/10.1007/s00500-023-09503-z

2. Zhou Y., Jing Zh., Dong P., Huang J. Robust median consensus cubature Kalman filter for distributed sensor networks. Digital Signal Processing. 2024;153. https://doi.org/10.1016/j.dsp.2024.104629

3. Tulyakova N., Trofymchuk O. Application of myriad filtering in real-time trend detection algorithms. Journal of Automation and Information Sciences. 2024;69(6):91–106.

4. Pale-Ramon E.G., Shmaliy Y.S., Morales-Mendoza L.J., Lee M.G. Finite Impulse Response (FIR) Filters and Kalman Filter for Object Tracking Process. In: 6th International Technical Conference on Advances in Computing, Control and Industrial Engineering (CCIE 2021), 16–17 October 2021, Hangzhou, China. Singapore: Springer; 2022. P. 665–684. https://doi.org/10.1007/978-981-19-3927-3_66

5. Kou L., Wang P., Ba R., Liu J., Deng Q., Zhang H. Study on Ensemble Kalman Filter Based Building Fire Prediction and Dynamic Situation Awareness for Emergency Response. In: ASME 2023 Heat Transfer Summer Conference collocated with the ASME 2023 17th International Conference on Energy Sustainability, 10–12 July 2023, Washington, DC, USA. New York: ASME; 2023. https://doi.org/10.1115/ht2023-106757

6. Singh S., Pribylskiy A.V., Kosenko E.Y. Development and research of algorithms for forecasting fire hazardous situations. Izvestiya SFedU. Engineering Sciences. 2025;(1):65–81. (In Russ.). https://doi.org/10.18522/2311-3103-2025-1-65-81

7. Su Q., Hu G., Liu Zh. Research on Fire Detection Method of Complex Space Based on Multi-Sensor Data Fusion. Measurement Science and Technology. 2024;35(8). https://doi.org/10.1088/1361-6501/ad437d

8. Guan Sh., Liu B., Chen Sh., et al. Adaptive median filter salt and pepper noise suppression approach for common path coherent dispersion spectrometer. Scientific Reports. 2024;14. https://doi.org/10.1038/s41598-024-66649-y

9. Singh S., Pribylskiy A.V. Synthesis of a system for ultra-fast detection of firehazardous situations based on a complex of interconnected sensors. Izvestiya SFedU. Engineering Sciences. 2024;(2):121–132. (In Russ.). https://doi.org/10.18522/2311-3103-2024-2-121-132

10. Wang T., Hu J., Ma T., Song J. Forest fire detection system based on Fuzzy Kalman filter. In: 2020 International Conference on Urban Engineering and Management Science (ICUEMS), 24–26 April 2020, Zhuhai, China. IEEE; 2020. P. 630–633. https://doi.org/10.1109/ICUEMS50872.2020.00138

11. Jiang Y. Fire detection system based on improved multi-sensor information fusion. In: Fifth International Conference on Computer Information Science and Artificial Intelligence (CISAI 2022), 16–18 September 2022, Chongqing, China. SPIE; 2023. https://doi.org/10.1117/12.2667524

12. Lin Ch.-Ch., Wang L. Real-Time Forecasting of Building Fire Growth and Smoke Transport via Ensemble Kalman Filter. Fire Technology. 2017;53(3):1101–1121. https://doi.org/10.1007/S10694-016-0619-X