Abstract
Road accidents are one of the primary causes of death around the globe, and these can be avoided if timely actions are taken by the driver of the vehicle. This paper proposes a system known as the Intelligent Accident Prevention and Alert System, which makes use of various sensors and machine learning algorithms to predict potential hazards on the road in real time. This system utilizes data from various sensors such as accelerometers, gyroscopes, GPS, proximity sensors, and driver sensors. This data is fed into a feature extraction module, where a random forest algorithm is utilized to classify the level of risk of an accident occurring. Based on this, an alert signal is sent to the driver, enabling them to take timely action. A feedback mechanism has been included in the system to ensure dynamic risk assessment. The performance of the proposed system is evaluated through a scenario-based simulated dataset, and the results show an accuracy of 93.5%, thereby proving the efficiency and reliability of the proposed system in detecting hazardous driving conditions. The proposed system also provides timely alerts, thereby enhancing the efficiency and effectiveness of accident prevention. The results prove that the proposed system offers an efficient and effective solution for accident prevention in real-world applications.
References
- Hozhabr Pour, Hawzhin, Frédéric Li, Lukas Wegmeth, Christian Trense, Rafał Doniec, Marcin Grzegorzek, and Roland Wismüller. "A machine learning framework for automated accident detection based on multimodal sensors in cars." Sensors 22, no. 10 (2022): 3634.
- Jayanthi, L. N., R. Usha, G. Sekar, V. T. Lakshmi, and N. Mohankumar. "Early Detection of Road Traffic Injuries with IoT Sensor Networks and K-Nearest Neighbors Algorithm." In 2025 International Conference on Visual Analytics and Data Visualization (ICVADV), pp. 773-778. IEEE, 2025.
- Vasireddy Satish, and Pyla Karuna Sagar. “Real-time Accident Detection and Emergency Notification System for Mobile Devices.” jraset Journal For Research in Applied Science and Engineering Technology. 2025. https://doi.org/10.22214/ijraset.2025.73438
- Alsayaydeh, Jamil Abedalrahim Jamil, Mohd Faizal bin Yusof, Mohamad Amirul Aliff Abdillah, Ahmed Jamal Abdullah bin Al-Gburi, Safarudin Gazali Herawan, and Andrii Oliinyk. "Enhancing Vehicle Safety: A Comprehensive Accident Detection and Alert System." International Journal of Advanced Computer Science & Applications 14, no. 11 (2023).
- Reddy, K. Ramakrishna, T. Sathish Kumar, Sreenivasulu Gogula, Abhisek Sethy, Veeraswamy Ammisetty, M. N. Sharath, Koppuravuri Gurnadha Gupta, Ravi Kiran, and Lavish Kansal. "Harnessing sensor fusion and AI for accurate accident detection and classification in the safety of smart cities." In MATEC Web of Conferences, vol. 392, p. 01102. EDP Sciences, 2024.
- Balfaqih, Mohammed, Soltan Abed Alharbi, Moutaz Alzain, Faisal Alqurashi, and Saif Almilad. "An accident detection and classification system using internet of things and machine learning towards smart city." Sustainability 14, no. 1 (2021): 210.
- Tasgaonkar, Pankaj P., Rahul Dev Garg, and Pradeep Kumar Garg. "An IoT-based framework of vehicle accident detection for Smart City." IETE Journal of Research 70, no. 5 (2024): 4744-4757.
- Pathik, Nikhlesh, Rajeev Kumar Gupta, Yatendra Sahu, Ashutosh Sharma, Mehedi Masud, and Mohammed Baz. "AI enabled accident detection and alert system using IoT and deep learning for smart cities." Sustainability 14, no. 13 (2022): 7701.
- Uma, S., and Rajagopal Eswari. "Accident prevention and safety assistance using IOT and machine learning." Journal of Reliable Intelligent Environments 8, no. 2 (2022): 79-103.
- Bhakat, Akash, Neetigya Chahar, and V. Vijayasherly. "Vehicle accident detection & alert system using IoT and artificial intelligence." In 2021 Asian conference on innovation in technology (ASIANCON), pp. 1-7. IEEE, 2021.