International Journal of Innovative Research in Computer and Communication Engineering
ISSN Approved Journal | Impact factor: 8.771 | ESTD: 2013 | Follows UGC CARE Journal Norms and Guidelines
| Monthly, Peer-Reviewed, Refereed, Scholarly, Multidisciplinary and Open Access Journal | High Impact Factor 8.771 (Calculated by Google Scholar and Semantic Scholar | AI-Powered Research Tool | Indexing in all Major Database & Metadata, Citation Generator | Digital Object Identifier (DOI) |
| TITLE | Study and Analysis of Sensors and AI Technologies Used to Predict and Prevent Accidents and for Alertness |
|---|---|
| ABSTRACT | Road accidents continue to pose a major challenge worldwide, resulting in millions of fatalities and injuries each year. Conventional safety measures, such as seatbelts, airbags, and traffic signals, primarily respond after an accident has occurred, offering limited preventive capability. In contrast, recent developments in sensor technologies, artificial intelligence (AI), and the Internet of Things (IoT) have enabled the creation of intelligent systems that can anticipate accidents, continuously monitor driver alertness, and provide timely warnings to prevent potential collisions. This study provides a comprehensive examination of the sensors, AI models, and methodologies employed in modern accident prediction and prevention frameworks. It emphasizes the role of integrated AI-sensor architectures in enhancing road safety and explores the associated challenges, as well as avenues for future research and development in this field. Among AI techniques, Convolutional Neural Networks (CNNs) have emerged as a powerful tool for analyzing spatial data, including images from cameras and LIDAR sensors, enabling accurate detection of obstacles, pedestrians, and other vehicles. This paper presents a descriptive study of sensors, CNN-based AI models, and methodologies employed in modern accident prediction and prevention systems. It highlights the impact of CNN-based frameworks on road safety and discusses challenges, limitations, and future research directions. |
| AUTHOR | M. PARVATHI HOD, Dept. of Computer Science, Latha Mathavan Arts and Science College, Tamil Nadu, India |
| VOLUME | 177 |
| DOI | DOI: 10.15680/IJIRCCE.2025.1312139 |
| pdf/139_Study and Analysis of Sensors and AI Technologies Used to Predict and Prevent Accidents and for Alertness.pdf | |
| KEYWORDS | |
| References | 1. Pathik, N. et al., “AI Enabled Accident Detection and Alert System Using IoT and Deep Learning for Smart Cities,” Sustainability, 2022. MDPI 2. Karim, M. M. et al., “A Dynamic Spatial temporal Attention Network for Early Anticipation of Traffic Accidents,” arXiv, 2021. arXiv 3. Mitta, N. R., “AI Based Real Time Safety Systems in Autonomous Driving: Leveraging Computer Vision and Sensor Fusion,” AJDSAI, 2022. AJDSAI 4. Journal of Big Data, “Driver Behavior Monitoring using AI and Computer Vision,” 2024. SpringerOpen 5. MDPI Algorithms, “AI and Machine Learning for Incident Detection in Road Transport Systems,” 2025. MDPI |
