TOWARDS EFFICIENT EMERGENCY RESPONSE: A MULTI-SENSOR APPROACH TO ACCIDENT DETECTION
DOI:
https://doi.org/10.59277/RRST-EE.2026.3.16Keywords:
Automatic accident detection, Sensor network, Emergency response, Accident severity detectionAbstract
The emergence of sensor technologies and embedded devices has created significant potential for autonomous accident-detection systems that will enhance emergency response and road safety. In this paper, an automated accident detection system is proposed that rapidly notifies the emergency center of the accident’s location and severity. Five sensors, such as a gyroscope, an IR flame sensor, a glass-break sensor, a smoke sensor, and a vibration sensor, are integrated with the STM32 microcontroller board. An algorithm is proposed with three severity levels based on the activation of a sensor or group of sensors. Emergency responders can prioritize their interventions by categorizing accidents into severity levels, thereby allocating resources more efficiently and effectively. The proposed method offers significant potential to strengthen road safety and enhance emergency response to road accidents.
References
(1) ***World Health Organization, “8th UN Global Road Safety Week,” World Health Organization (2025).
(2) K.S.K. Veni, J.C.S. Thomas, J.P.P. Paul, J. Joyce, “IoT-based voltage control in smart grid with feed-forward control in automatic voltage regulator,” Rev. Roum. Sci. Techn. – Électrotech. et Énerg., 70, 1, pp. 75–80 (2025).
(3) D. Belega, D. Petri, “Real-valued damped sinusoid parameter estimation using a three-point interpolated discrete Fourier transform algorithm,” Rev. Roum. Sci. Techn. – Électrotech. et Énerg., 69, 4, pp. 373–376 (2024).
(4) D. Chouaibi, W. Chagra, “A new hybrid optimization method used in predictive control of a nonlinear fractional model based on fractional Hammerstein structure,” Rev. Roum. Sci. Techn. – Électrotech. et Énerg., 69, 4, pp. 437–448 (2024).
(5) M.S.K. Niya, “The effects of hybrid sliding mode learning control and feedforward angle droop controller with high droop gain in hybrid microgrid with load uncertainty and nonlinearity,” Rev. Roum. Sci. Techn. – Électrotech. et Énerg., 69, 3, pp. 277–282 (2024).
(6) A. Appathurai, A.S.I. Tinu, M. Narayanaperumal, “MEG and PET images-based brain tumor detection using Kapur’s Otsu segmentation and Sooty optimized MobileNet classification,” Rev. Roum. Sci. Techn. – Électrotech. et Énerg., 69, 3, pp. 359–364 (2024).
(7) S. Gatade, S.V. Kulkarni, S.N., “Automated vehicle accident detection and healthcare unit alerting using IoT,” Proc. IEEE 2nd Mysore Sub Section International Conference (MysuruCon), pp. 1–5 (2022).
(8) N. Pathik, R.K. Gupta, Y. Sahu, A. Sharma, M. Masud, M. Baz, “AI-enabled accident detection and alert system using IoT and deep learning for smart cities,” Sustainability, 14, 13, pp. 7701–7710 (2022).
(9) G.D. Krishnamoorthy, K. Balasubramanian, S. Chinnusamy, “Design of an IoT-based autonomous vehicle accident detection and rescue system,” AIP Conf. Proc., 2581, 1, pp. 1–10 (2023).
(10) S. Kayser, M. Siam, K. Sumaiya, R. Al-Amin, T. Turjo, A. Islam, A.H.M.A. Rahim, M.R. Hasan, “Real-time accident detection and physiological signal monitoring to enhance motorbike safety and emergency response,” arXiv preprint, pp. 1–10 (2024).
(11) A. More, M. Mahajan, H. Gholap, “AI and IoT-based road accident detection and reporting system,” Int. J. Res. Appl. Sci. Eng. Technol., 11, 13, pp. 1–10 (2023).
(12) R. Thommandru, B. Swaroopa Ran, “IoT-based automatic vehicle accident detection and rescue system,” Int. J. Mod. Trends Sci. Technol., 10, 3, pp. 94–99 (2024).
(13) S. Pujari, “Accident alerting system using GPS and GSM,” Int. J. Res. Appl. Sci. Eng. Technol., 12, 3, pp. 1055–1058 (2024).
(14) G.A.E. Satish Kumar, J. Swetha Priyanka, A.S. Deepthi, “Vehicle accident and alcohol detection system using IoT platform,” Indian J. Sci. Technol., 15, 39, pp. 2004–2010 (2022).
(15) J. Arthanareeswaran, B. Karunanidhi, S. Muruganantham, A. Dhamodharan, S.K.C. Swarnamma, “Automatic vehicle accident indication and reporting system for roadways using Internet of Things,” Int. J. Saf. Secur. Eng., 11, 3, pp. 269–277 (2021).
(16) Y. Chavan, S. Shelar, V. Bharambe, “Integrating IoT and GNSS for advanced accident detection and road safety enhancement,” Res. Rev. J. Space Sci. Technol., 14, 1, pp. 1–10 (2025).
(17) R. Javed, T. Mazhar, M. Aoun, T. Shahzad, H.A. Al-AlShaikh, Y.Y. Ghadi, A.K.J. Saudagar, M.A. Khan, “Deep learning and IoT-enabled accident detection and reporting for smart cities domain,” KSII Trans. Internet Inf. Syst., 19, 4, pp. 1140–1166 (2025).
(18) I. Song, J. Lee, “Real-time traffic accident anticipation with feature reuse,” arXiv preprint, arXiv:2505.17449 (2025).
(19) Z. Xi, X. Liu, Y. Liu, Y. Cai, Y. Zheng, “Integrating generative adversarial networks and convolutional neural networks for enhanced traffic accident detection and analysis,” arXiv preprint, arXiv:2506.16186 (2025).
(20) V.A. Adewopo, N. Elsayed, “Smart city transportation: deep learning ensemble approach for traffic accident detection,” IEEE Access, 12, pp. 59134–59147 (2024).
(21) V.S. Saravanarajan, R.C. Chen, C. Dewi, et al., “Car crash detection using ensemble deep learning,” Multimedia Tools Appl., 83, pp. 36719–36737 (2024).
(22) S. Banerjee, M.K. Mondal, M. Roy, W.S. Alnumay, U. Biswas, “A deep learning-based car accident detection framework using edge and cloud computing,” IEEE Access, 12, pp. 130107–130115 (2024).
(23) G.C. Seriţan et al., "Comparison study of top development boards in the context of IoT", Rev. Roum. Sci. Techn. – Électrotechn. et Énerg., 67, 4, pp. 483–486 (2022).
Downloads
Published
Issue
Section
License
Copyright (c) 2026 REVUE ROUMAINE DES SCIENCES TECHNIQUES — SÉRIE ÉLECTROTECHNIQUE ET ÉNERGÉTIQUE
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
