Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{188815,
        author = {Ankitha K V and Chethan Kumar T and Dr. Rajashekar K J and Preethi Kumari and Likhitha M N},
        title = {Enhancing Accident Prediction Through Integrated KNN & DBSCAN Algorithms For Superior Accuracy},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {7},
        pages = {3601-3605},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=188815},
        abstract = {Accurate accident prediction is essential for improving road safety and enabling timely emergency response. This paper presents a hybrid prediction model that combines the strengths of the K-Nearest Neighbors (KNN) classifier and the DBSCAN clustering algorithm to enhance accuracy and reduce noise in accident-related data. DBSCAN is first applied to identify meaningful clusters and remove outliers, providing a cleaner dataset for improved analysis. The refined data is then processed using KNN to classify accident severity based on critical traffic and environmental features. The system ensures higher reliability, robustness, and predictive performance compared to traditional single-model approaches, making it suitable for intelligent traffic monitoring and decision- support systems interface.},
        keywords = {Accident Prediction, KNN, DBSCAN, Machine Learning, Hybrid Model, Traffic Analysis, Classification.},
        month = {December},
        }