Authors : Golla Akhila; Prakash O. Sarangamath; Dr. Girish Kumar D.

Volume/Issue : Volume 11 - 2026, Issue 4 - April

Google Scholar : https://tinyurl.com/bddr94wh

Scribd : https://tinyurl.com/yacx38x7

DOI : https://doi.org/10.38124/ijisrt/26apr1824

Note : A published paper may take 4-5 working days from the publication date to appear in PlumX Metrics, Semantic Scholar, and ResearchGate.

Abstract : Recent developments in machine learning, embedded sensing, and cloud-connected communication systems have enabled the creation of intelligent safety solutions for transportation. This work presents a real-time accident risk detection and alert system that integrates synthetic vehicular sensor data, a machine-learning risk classifier, and automated emergency notification through an SMS gateway. The proposed framework uses dynamically generated parameters—vehicle speed, acceleration, and steering angle—to simulate sensor behavior, which is then evaluated using a trained Random Forest model to estimate accident probability. A Flask-based web interface allows users to trigger the monitoring process, while the Twilio communication API delivers instant SMS alerts containing risk assessments and sensor readings. The system is lightweight, deployable on cloud or local servers, and capable of issuing warnings when hazardous driving conditions are predicted. Experimental evaluation on a synthetically generated dataset demonstrates reliable classification performance and real-time responsiveness. The study highlights the potential of combining web technologies, supervised learning models, and cloud communication services to develop affordable and accessible vehicular safety solutions.

Keywords : Machine Learning, Accident Prediction, Vehicle Safety Systems, Sensor Data Simulation, Random Forest Classifier, Real-Time Alerting, SMS Notification System, Flask Web Application, Intelligent Transportation, Embedded Safety Monitoring.

References :

1. S. Sharma, A. Verma, and R. Gupta, “Review of artificial intelligence applications in intelligent transportation systems,” IEEE Access, vol. 9, pp. 45012– 45029, 2021.
2. J. Li, X. Wang, and M. Chen, “Current trends and challenges in machine learning for road traffic accident prediction,” Journal of Transportation Safety & Security, vol. 13, no. 4, pp. 421–440, 2021.
3. P. K. Singh and S. Kumar, “IoT-enabled vehicle monitoring and alert systems: A survey,” IEEE Internet of Things Journal, vol. 8, no. 15, pp. 11987–12003, 2021.
4. R. Das and V. Kumar, “Cloud-based real-time accident detection and alert using machine learning,” International Journal of Intelligent Transportation Systems Research, vol. 18, pp. 345–360, 2020.
5. M. A. Rahman, A. K. M. R. Alam, and T. Ahmed, “Design and implementation of SMS-based emergency alert systems for vehicle accidents,” IEEE Transactions on Intelligent Transportation Systems, vol. 22, no. 9, pp. 5550–5561, 2021.
6. H. Zhang, Y. Liu, and J. Wang, “Random forest and sensor data for traffic accident prediction,” Journal of Advanced Transportation, vol. 2020, Article ID 884321, 2020.
7. L. Fernandez, P. Torres, and D. Garcia, “Review of AI- enhanced safety systems for smart vehicles,” IEEE Transactions on Vehicular Technology, vol. 70, no. 5, pp. 4182–4195, 2021.
8. A. K. Bhatia and S. Choudhury, “Intelligent vehicle monitoring for accident prevention using cloud technologies,” International Journal of Cloud Applications and Computing, vol. 11, no. 2, pp. 1–15, 2021.
9. R. S. Patel and M. N. Desai, “Challenges and solutions in integrating AI and IoT for real-time accident alerts,” IEEE Access, vol. 9, pp. 85045–85059, 2021.
10. V. Kumar, S. Sharma, and P. Jain, “Development and evaluation of machine learning-based vehicle accident alert systems,” Journal of Intelligent & Connected Vehicles, vol. 4, no. 3, pp. 121–134, 2022.