Sistema de Alerta Temprana de Incendios para Personas con Discapacidad Auditiva Basado en IoT y Señales Hápticas

Héctor Caballero Hernández; German Becerril Donato; Vianney Muñoz Jiménez; Marco Antonio Ramos Corchado

Authors

Héctor Caballero Hernández 📩 Universidad Autónoma del Estado de México, México
German Becerril Donato Tecnológico de Estudios Superiores de Jocotitlán, México https://orcid.org/0009-0006-8436-8890
Vianney Muñoz Jiménez Universidad Autónoma del Estado de México, México https://orcid.org/0000-0003-2180-6743
Marco Antonio Ramos Corchado Universidad Autónoma del Estado de México, México

Keywords:

IoT, fuzzy logic, Wear OS, fire detection, wearable computing

Abstract

This paper describes the development of a hybrid IoT security system designed for early detection of fires. It integrates temperature and humidity (DHT11) and CO (MQ-7) sensors connected to an ESP32, which sends the information to a smartwatch and a smartphone (SMS/Telegram) to alert users with hearing impairments in real time. The method consists of a data acquisition stage (ESP32 board) and a processing stage using a fuzzy inference engine implemented on a TicWatch E3 with Wear OS 3.5. The Kotlin programming language is used to analyze the input variables and figure out the risk level (Low, Medium, High, and Extreme). The system automatically distinguishes between smoke and active fire threats, supported by visual confirmation using the Yolov8s algorithm. Detection results are sent via a Telegram message. The results show that the application can activate haptic feedback and play a video with Mexican Sign Language alerts on the smartwatch when safety thresholds are exceeded. During the testing phase, outstanding results were obtained when applying the precision and accuracy metrics, with a result of 97%, while MAE (Mean Absolute Error) presented a score of 0.0327 in a Monte Carlo simulation of 3000 cases to validate the fuzzy engine, while in the tests in the real environment, the system reacted accurately, with a favorable acceptance by the users who participated in the experiments.

References

Ahn, Y., Choi, H., & Kim, B. S. (2023). Development of early fire detection model for buildings using computer vision-based CCTV. Journal of Building Engineering, 65, 105647. https://doi.org/10.1016/j.jobe.2022.105647

Ahrens, M. (2021). Smoke Alarms in U.S. Home Fires. National Fire Protection Association (NFPA).

Alam, G. M. I., Tasnia, N., Biswas, T., Hossen, M. J., Tanim, S. A., & Miah, M. S. U. (2025). Real-Time Detection of Forest Fires Using FireNet-CNN and Explainable AI Techniques. IEEE Access. 10.1109/ACCESS.2025.3552352.

Ali, M. M., & Ghodrat, M. (2025). Toward reliable fire detection in indoor CCTV footage: Reducing false alarms from benign flames using 3D attention CNNs. IEEE Access. 10.3390/fire8070285.

An, L., Chen, L., & Hao, X. (2023). Indoor fire detection algorithm based on second-order exponential smoothing and information fusion. Information, 14(5), 258. https://doi.org/10.3390/info14050258

Arifia, R., & Mulyana, I. (2025). Development of an IoT-Based Fire Detection System Using ESP32 with Fire Alerts via Telegram Bot. Prosiding Seminar Nasional Universitas Ma Chung, 5(1), 45-58.

Aksüt, G., & Eren, T. (2025). Evaluation of wearable device technology in terms of health and safety in firefighters. Technology and Health Care, 33(2), 726-736. https://doi.org/10.1177/09287329241291385

Cahyadi, H. D., & Teary, M. G. (2026). IoT-Based Fire Detection System Using ESP32 and Telegram. Media Journal of General Computer Science, 3(1), 1-9. https://doi.org/10.62205/mjgcs.v3i1.146

Centre for Research on the Epidemiology of Disasters (CRED). (2025). State of wildfires 2024–2025. PreventionWeb.

Chen, Y., et al. (2025). Evaluation of wearable device technology in terms of health and safety in firefighters. International Journal of Industrial Ergonomics, 90, 103325.

Consejo Nacional para el Desarrollo y la Inclusión de las Personas con Discapacidad. (2017). Diccionario de Lengua de Señas Mexicana. Secretaría de Salud. https://educacionespecial.sep.gob.mx/storage/recursos/2023/05/xzrfl019nV-4Diccionario_lengua_%20Senas.pdf

Copernicus Atmosphere Monitoring Service. (2024). State of Wildfires 2023-24: CAMS data supports assessment. European Union.

Deng, X., Shi, X., Wang, H., Wang, Q., Bao, J., & Chen, Z. (2023). An indoor fire detection method based on multi-sensor fusion and a lightweight convolutional neural network. Sensors, 23(24), 9689. https://doi.org/10.3390/s23249689

El-Madafri, I., Peña, M., & Olmedo-Torre, N. (2024). Real-Time Forest Fire Detection with Lightweight CNN Using Hierarchical Multi-Task Knowledge Distillation. Fire, 7(11), 392. https://doi.org/10.3390/fire7110392

FEMA, Agencia Federal para el Manejo de Emergencias. (2023). Sistemas de detección de incendios y nuevas tecnologías de respuesta. Departamento de Seguridad Nacional. URL: https://www.usfa.fema.gov.

Hou, F., Rui, X., Chen, Y., & Fan, X. (2023). Flame and smoke semantic dataset: Indoor fire detection with a deep semantic segmentation model. Electronics, 12(18), 3778. https://doi.org/10.3390/electronics12183778

Institute of Electrical and Electronics Engineers. (2020). IEEE Standard for an Architectural Framework for the Internet of Things (IoT) (IEEE Std 2413-2019). 10.1109/IEEESTD.2020.9032420

Istre, G. R., et al. (2020). Smoke alarms and prevention of house-fire-related deaths and injuries. Western Journal of Emergency Medicine, 15(2), 145.

James, G., Witten, D., Hastie, T., & Tibshirani, R. (2013). An Introduction to Statistical Learning: with Applications in R. Springer.

Jocher, G., Chaurasia, A., & Qiu, J. (2023). Ultralytics YOLOv8 (Versión 8.0.0) [Software]. https://github.com/ultralytics/ultralytics

Kroese, D. P., Taimre, T., & Botev, Z. I. (2011). Handbook of Monte Carlo Methods. John Wiley & Sons.

Li, Y., Shang, J., Yan, M., Ding, B., & Zhong, J. (2023). Real-time indoor early fire detection and localization on embedded platforms using fully convolutional one-stage object detection. Sustainability, 15(3), 1794. https://doi.org/10.3390/su15031794

Mahbub, M., Hossain, M. M., & Gazi, M. S. A. (2021). Cloud-Enabled IoT-based and cloud-enabled integrated system for smart indoor lighting and ventilation as well as early fire detection and prevention. Computer Networks, 184, 107673. https://doi.org/10.1016/j.comnet.2020.107673

Mukhiddinov, M., Abdusalomov, A. B., & Cho, J. (2022). Automatic fire detection and notification system based on improved YOLOv4 for blind and visually impaired people. Sensors, 22(9), 3307. https://doi.org/10.3390/s22093307

National Fire Protection Association. (2024). NFPA 72: National Fire Alarm and Signaling Code (Ed. 2025). NFPA.

Nazir, A., Mosleh, H., Takruri, M., Jallad, A. H., & Alhebsi, H. (2022). Early fire detection: A novel indoor laboratory dataset and data distribution analysis. Fire, 5(1), 11. https://doi.org/10.3390/fire5010011

Peng, B., & Kim, T.-K. (2025). YOLO-HF: Early Detection of Home Fires Using YOLO. IEEE Access, 13, 79451–79466. 10.1109/ACCESS.2025.3566907

Pincott, J., Tien, P. W., Wei, S., & Calautit, J. K. (2022). Indoor fire detection utilizing computer vision-based strategies. Journal of Building Engineering, 61, 105154. https://doi.org/10.1016/j.jobe.2022.105154

Rachman, F. Z., & Hendrantoro, G. (2020, June). A fire detection system using multi-sensor networks based on fuzzy logic in indoor scenarios. In 2020 8th International Conference on Information and Communication Technology (ICoICT) (pp. 1-6). IEEE.10.1109/ICoICT49345.2020.9166416.

Rachman, F. Z., & Hendrantoro, G. (2020). A fire detection system using multi-sensor networks based on fuzzy logic in indoor scenarios. Proc. 8th Int. Conf. on Information and Communication Technology (ICoICT), 1–6. https://doi.org/10.1109/ICoICT49345.2020.9166432

Russell, S. J., & Norvig, P. (2021). Artificial Intelligence: A Modern Approach (4a ed.). Pearson.

Vaegae, N., Annepu, V., & Al-Mhiqani, M. (2024). Multisensor fuzzy logic approach for enhanced fire detection in smart cities. Journal of King Saud University-Computer and Information Sciences, 36(2), 101-115. 10.1155/2024/8511649.