Mishra, Moumita (Indian Institute of Technology Kharagpur), Ghosh, Shreya (IIT Bhubaneswar), Maitra, Bhargab (Indian Institute of Technology Kharagpur), Ghosh, Soumya (Indian Institute of Technology Kharagpur)

Exploring Spatio-Temporal Multimodal Data for Accident Count Prediction: A Case Study of Kolkata

Scheduled for presentation during the Poster Session "Incident and emergency management" (WeBT17), Wednesday, September 25, 2024, 14:30−16:30, Foyer

2024 IEEE 27th International Conference on Intelligent Transportation Systems (ITSC), September 24- 27, 2024, Edmonton, Canada

This information is tentative and subject to change. Compiled on October 14, 2024

Abstract

Road safety is a paramount concern in urban environments, particularly in populated cities like Kolkata, India, where the frequency and severity of traffic accidents pose significant challenges. Each day, numerous preventable accidents occur, leading to unnecessary fatalities and highlighting the urgent need for improved safety measures. This study aims to identify accident prone area and analyze the multifaceted factors related to these incidents. This paper explores the correlation between road accidents and diverse influences like temporal elements, weather conditions, and geographic specifics. We utilize a comprehensive dataset of 2017-2020 and 2021-2023. The data undergoes rigorous preprocessing to extract geographical coordinates, followed by integrating historical weather conditions accessed via an API. Advanced cluster analysis and regression analysis are used. Utilizing models like Decision Tree, and Random Forest have demonstrated superior predictive capabilities with high R2 scores. The findings of this research not only shed light on the patterns and predictors of road accidents but also contribute significantly to the development of targeted data-driven interventions aimed at enhancing road safety measures in Kolkata. By leveraging detailed spatio-temporal analysis, this study provides valuable insights that can help policymakers and strategic planners to mitigate road traffic accidents in urban settings.