Machine Learning-Based Multi-Sensor IoT System for Intelligent Indoor Fire Detection
Downloads
Purpose of the study: This study aims to develop an intelligent indoor fire detection system by integrating low-cost Internet of Things (IoT) sensors with machine learning-based multi-sensor data fusion to improve early fire hazard detection accuracy while reducing false alarms compared to conventional single-sensor fire detection systems.
Methodology: The system is implemented using an ESP32 microcontroller connected to temperature, humidity, flame, and sound sensors for real-time data acquisition. A dataset of 1,500 sensor samples is collected and labeled into Normal, Fire-Risk, and Fire classes. Decision Tree, Support Vector Machine, and Random Forest classifiers are trained and evaluated using Python-based machine learning libraries.
Main Findings: Experimental results indicate that the Random Forest model outperforms the other classifiers, achieving 95% overall accuracy, perfect recall for fire events, and a Macro ROC-AUC score of 0.993. Feature importance analysis reveals that humidity and temperature are the most influential parameters for early fire detection in indoor environments.
Novelty/Originality of this study: This study proposes a lightweight intelligent fire detection framework that integrates multi-sensor Internet of Things data including temperature, humidity, flame, and sound signals with machine learning–based classification for indoor environments. Unlike conventional systems that rely on single-sensor or threshold-based detection, the proposed approach utilizes multi-sensor data fusion and ensemble learning to improve early fire-risk identification while remaining computationally efficient for low-cost platforms such as the ESP32 microcontroller.
Downloads
S. Medved, “Buildings fires and fire safety,” in Building Physics: Heat, Ventilation, Moisture, Light, Sound, Fire, and Urban Microclimate. Cham, Switzerland: Springer, 2021, pp. 407–451, doi: 10.1007/978-3-030-74390-1_6.
V. Kodur, et al., “Fire hazard in buildings: Review, assessment and strategies for improving fire safety,” PSU Res. Rev., vol. 4, no. 1, pp. 1–23, 2020, doi: 10.1108/PRR-12-2018-0033.
M. Yu, et al., “Building fire alarm model based on fire source inversion according to smoke arrival time intervals,” J. Build. Eng., vol. 73, Art. no. 106650, 2023, doi: 10.1016/j.jobe.2023.106650.
R. Kuti, G. Zólyomi, G. László, C. Hajdu, L. Környei, and F. Hajdu, “Examination of effects of indoor fires on building structures and people,” Heliyon, vol. 9, no. 1, Art. no. e12720, Jan. 2023, doi: 10.1016/j.heliyon.2022.e12720.
M. L. Ivanov and W. K. Chow, “Fire safety in modern indoor and built environment,” Indoor Built Environ., vol. 32, no. 1, pp. 3–8, Jan. 2023, doi: 10.1177/1420326X221134765.
M. T. Bashir, “Fire protection and prevention in perspective of human, environment and workplace,” Int. J. Sci. Technol. Res., vol. 10, no. 3, pp. 38–42, Mar. 2021. [Online]. Available: https://web.archive.org/web/20210814084738/http://www.ijstr.org/final-print/mar2021/Fire-Protection-And-Prevention-In-Perspective-Of-Human-Environment-And-Workplace.pdf
L. Deng, et al., “Large-space fire detection technology: A review of conventional detector limitations and image-based target detection techniques,” Fire, vol. 8, no. 9, Art. no. 358, 2025, doi: 10.3390/fire8090358.
G. Tejaswi, R. Bhavani, S. Srihitha, S. Arshiha, and R. V. S. Sarayu, “Predicting fire alarms using multi-sensor data: A binary classification approach,” Turkish J. Comput. Math. Educ., vol. 15, no. 1, pp. 242–255, 2024, doi: 10.61841/turcomat.v15i1.14617.
C. L. Wu, et al., “False-alarm susceptibility of spot-type smoke detectors under realistic fire and nuisance conditions,” Fire Saf. J., Art. no. 104621, 2025, doi: 10.1016/j.firesaf.2025.104621.
S. Chen, J. Ren, Y. Yan, M. Sun, F. Hu, and H. Zhao, “Multi-sourced sensing and support vector machine classification for effective detection of fire hazard in early stage,” Comput. Electr. Eng., vol. 101, Art. no. 108046, 2022, doi: 10.1016/j.compeleceng.2022.108046.
J. Baek, et al., “Intelligent multi-sensor detection system for monitoring indoor building fires,” IEEE Sensors J., vol. 21, no. 24, pp. 27982–27992, Dec. 2021, doi: 10.1109/JSEN.2021.3124266.
H. Zhu, et al., “Automotive fire alarm system based on multi-sensor fusion,” in Proc. Int. Conf. Sensors Inf. Technol., 2024, pp. 159–164, doi: 10.1117/12.3029223.
A. Solórzano, et al., “Early fire detection based on gas sensor arrays: Multivariate calibration and validation,” Sens. Actuators B, Chem., vol. 352, Art. no. 130961, 2022, doi: 10.1016/j.snb.2021.130961.
Q. Su, G. Hu, and Z. Liu, “Research on fire detection method of complex space based on multi-sensor data fusion,” Meas. Sci. Technol., vol. 35, no. 8, Art. no. 085107, 2024, doi: 10.1088/1361-6501/ad437d.
A. Rehman, et al., “Smart fire detection and deterrent system for human savior by using Internet of Things (IoT),” Energies, vol. 14, no. 17, Art. no. 5500, 2021, doi: 10.3390/en14175500.
S. K. Mekni, “Design and implementation of a smart fire detection and monitoring system based on IoT,” in Proc. Int. Conf. Appl. Autom. Ind. Diagn., 2022, pp. 1–5, doi: 10.1109/ICAAID51067.2022.9799505.
B. E. Raju, K. R. Chandra, K. V. N. Gupta, K. N. V. Rao, R. Devi, and P. V. Kumar, “Fuzzy logic-enhanced multi-sensor hardware module for real-time fire detection and notification,” in Proc. 7th Int. Conf. Contemp. Comput. Inform. (IC3I), 2024, pp. 1–6, doi: 10.1109/IC3I61595.2024.10828880.
A. Al-Dahoud, M. Fezari, A. A. Alkhatib, M. N. Soltani, and A. Al-Dahoud, “Forest fire detection system based on low-cost wireless sensor network and Internet of Things,” WSEAS Trans. Environ. Dev., vol. 19, pp. 506–513, 2023, doi: 10.37394/232015.2023.19.49.
A. A. Almohammedi, et al., “Design and implementation of IoT-enabled intelligent fire detection system using neural networks,” in Lecture Notes in Computer Science, vol. 14202, 2023, doi: 10.1007/978-3-031-45140-9_6.
U. Dampage, et al., “Forest fire detection system using wireless sensor networks and machine learning,” Sci. Rep., vol. 12, Art. no. 46, 2022, doi: 10.1038/s41598-021-03882-9.
././// J. Desikan, et al., “Hybrid machine learning-based fault-tolerant sensor data fusion and anomaly detection for fire risk mitigation in IIoT environment,” Sensors, vol. 25, no. 7, Art. no. 2146, 2025, doi: 10.3390/s25072146.
J. C. N. Bittencourt, D. G. Costa, P. Portugal, and F. Vasques, “Towards lightweight fire detection at the extreme edge based on decision trees,” in Proc. IEEE 22nd Mediterranean Electrotech. Conf. (MELECON), Jun. 2024, pp. 873–878, doi: 10.1109/MELECON56669.2024.10608598.
F. Khan, et al., “Recent advances in sensors for fire detection,” Sensors, vol. 22, no. 9, Art. no. 3310, 2022, doi: 10.3390/s22093310.
A. Doshi and Y. Rai, “IoT-based fire and gas monitoring system,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 9, no. 7, pp. 3110–3117, 2021, doi: 10.22214/ijraset.2021.37026.
M. N. Khan, et al., “Real-time environmental monitoring using low-cost sensors in smart cities with IoT,” Int. J. Future Mach. Res., vol. 6, pp. 1–11, 2024, doi: 10.36948/ijfmr.2024.v06i01.23163.
R. F. Chisab, A. A. Majeed, and H. S. Hamid, “IoT-based smart wireless communication system for electronic monitoring of environmental parameters with a data-logger,” Int. J. Electr. Electron. Eng. Telecommun., vol. 12, no. 6, pp. 450–458, 2023, doi: 10.18178/ijeetc.12.6.450-458.
S. Chitram, et al., “Enhancing fire and smoke detection using deep learning techniques,” Eng. Proc., vol. 62, no. 1, Art. no. 7, 2024, doi: 10.3390/engproc2024062007.
J. Pincott, et al., “Indoor fire detection utilizing computer vision-based strategies,” J. Build. Eng., vol. 61, Art. no. 105154, 2022, doi: 10.1016/j.jobe.2022.105154.
A. Gaur, et al., “Video flame and smoke based fire detection algorithms: A literature review,” Fire Technol., vol. 56, pp. 1943–1980, 2020, doi: 10.1007/s10694-020-00986-y.
S. Suklabaidya and I. Das, “Processing IoT sensor fire dataset using machine learning techniques,” in Proc. Int. Conf. Intell. Syst. Adv. Comput. Commun. (ISACC), Feb. 2023, pp. 1–7, doi: 10.1109/ISACC56298.2023.10084317.
A. Secilmis, N. Aksu, F. A. Dael, I. Shayea, and A. A. El-Saleh, “Machine learning-based fire detection: A comprehensive review and evaluation of classification models,” JOIV: Int. J. Inform. Visualization, vol. 7, no. 3-2, pp. 1982–1988, 2023, doi: 10.30630/joiv.7.3-2.2332.
U. Ahad, Y. Singh, P. Anand, Z. A. Sheikh, and P. K. Singh, “Intrusion detection system model for IoT networks using ensemble learning,” J. Interconnection Netw., vol. 22, no. 3, Art. no. 2145008, 2022, doi: 10.1142/S0219265921450080.
J. Jose and J. E. Judith, “Unveiling the IoT’s dark corners: Anomaly detection enhanced by ensemble modelling,” Automatika, vol. 65, no. 2, pp. 584–596, 2024, doi: 10.1080/00051144.2024.2304369.
R. A. Khan, et al., “Fire and smoke detection using capsule network,” Fire Technol., vol. 59, pp. 581–594, 2023, doi: 10.1007/s10694-022-01352-w.
F. Daghero, et al., “Dynamic decision tree ensembles for energy-efficient inference on IoT edge nodes,” IEEE Internet Things J., vol. 11, no. 1, pp. 742–757, 2024, doi: 10.1109/JIOT.2023.3286276.
H. Wang, J. Li, and K. He, “Hierarchical ensemble reduction and learning for resource-constrained computing,” ACM Trans. Des. Autom. Electron. Syst., vol. 25, no. 1, pp. 1–21, 2019, doi: 10.1145/3365224.
S. Uppal, S. Raheja, and N. R. Das, “Fire detection alarm system using deep learning,” in Proc. 13th Int. Conf. Cloud Comput. Data Sci. Eng. (Confluence), Jan. 2023, pp. 54–58, doi: 10.1109/Confluence56041.2023.10048842.
A. Hassan and A. I. Audu, “A lightweight CNN model for vision-based fire detection on embedded systems,” FUOYE J. Eng. Technol., vol. 9, no. 4, pp. 624–628, 2024, doi: 10.4314/fuoyejet.v9i4.9.
S. Sawant, B. Chauhan, S. Kumbhar, G. Chaudhari, and P. Thakar, “Integrated fire detection system using machine learning and IoT,” Int. J. Res. Appl. Sci. Eng. Technol., vol. 12, no. 5, pp. 2091–2100, 2024, doi: 10.22214/ijraset.2024.60063.
M. Milli and M. Milli, “Reducing false positives in building fire detection systems via multiple metal oxide sensors,” IEEE Access, early access, 2025, doi: 10.1109/ACCESS.2025.3606584.
,.... N. Dilshad, T. Khan, and J. Song, “Efficient deep learning framework for fire detection in complex surveillance environment,” Comput. Syst. Sci. Eng., vol. 46, no. 1, pp. 749–764, 2023, doi: 10.32604/csse.2023.034475.
A. K. Vishwakarma and M. Deshmukh, “CNNM-FDI: Novel convolutional neural network model for fire detection in images,” IETE J. Res., vol. 71, no. 4, pp. 1105–1118, 2025, doi: 10.1080/03772063.2025.2453877.
N. D. Ismail, et al., “A systematic literature review of vision-based fire detection, prediction and forecasting,” J. Kejuruteraan, vol. 37, no. 1, pp. 191–218, 2025, doi: 10.17576/jkukm-2025-37(1)-13.
M. S. Mohammed, A. H. Abbas, and N. A. Abdullah, “Intelligent surveillance systems for fire detection in open areas: A survey,” Iraqi J. Sci., vol. 65, no. 5, pp. 2813–2827, 2024, doi: 10.24996/ijs.2024.65.5.36.
F. A. Nafis, et al., “An efficient IoT-based fire detection system using quantized deep learning model on resource-constrained devices,” in Proc. 27th Int. Conf. Comput. Inf. Technol. (ICCIT), Dec. 2024, pp. 3182–3187, doi: 10.1109/ICCIT64611.2024.11021729.
H. L. Farhan and A. S. Daghal, “Improving the detection and warning fire system on the smart campus area using ANFIS,” Al-Furat J. Innov. Electron. Comput. Eng., vol. 3, no. 2, pp. 422–436, 2024, doi: 10.46649/fjiece.v3.2.28a.7.6.2024.
H. T. Thai, N. Y. Tran-Van, K. H. Le-Minh, and K. H. Le, “An edge-based fire detection system for real-time IoT applications,” in Proc. IEEE Int. Conf. Commun. Netw. Satell. (COMNETSAT), Nov. 2023, pp. 646–651, doi: 10.1109/COMNETSAT59769.2023.10420588.
D. Kaliyev, O. Shvets, S. Grigoryeva, and A. Alimkhanova, “Intelligent forest fire detection using CNN and UAVs,” in Proc. IEEE 6th Int. Symp. Logist. Ind. Inform. (LINDI), Oct. 2024, pp. 131–134, doi: 10.1109/LINDI63813.2024.10820427.
R. D. Shirwaikar and L. Mathews, “CNN-based video surveillance for fire and localization detection,” in Proc. Int. Conf. Cogn. Comput. Inf. Process. (CCIP), Dec. 2022, pp. 1–8, doi: 10.1109/CCIP57447.2022.10058625.
S. Khirani, A. Souahlia, A. Rabehi, et al., “Advanced evaluation of pre-trained CNN models for accurate forest fire detection,” Nat. Hazards, vol. 122, Art. no. 234, 2026, doi: 10.1007/s11069-026-07976-3.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and acknowledge that the Journal of Educational Technology and Learning Creativity is the first publisher licensed under a Creative Commons Attribution 4.0 International License.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges and earlier and greater citation of published work.
.png)
.png)
.png)
