ITSC 2024 Paper Abstract

Close

Paper WeBT17.6

Kaviani, Niloofar (University of Calgary), Demissie, Merkebe Getachew (University of Calgary, Calgary, Canada), Kattan, Lina (University of Calgary)

Leveraging Clustering Methods for Enhancing Traffic Safety in the Era of Connected and Autonomous Vehicles in Calgary

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

Keywords Incident Management, Data Mining and Data Analysis, Automated Vehicle Operation, Motion Planning, Navigation

Abstract

This research investigates at how clustering techniques can be used to improve traffic safety in Calgary, with a focus on potential applications for connected and autonomous vehicles (CAVs). We identified and analyzed traffic collision hotspots using a two-step cluster analysis combined with association rule mining, using a collision dataset that spanned over eight years. Our approach highlights the flexibility in managing high-dimensional information by applying the DBSCAN and COOLCAT algorithms to identify spatial clusters (namely as collision hotspots in Calgary) and categorize collisions inside these clusters based on categorical data, respectively. Our research reveals important trends in traffic collisions and the elements that lead to them; these trends were then investigated further to create realistic, scenario-based models for CAVs. We combined these patterns into practical insights by utilizing association rule mining, which encourages preventive measures suited to certain high-risk situations. This strategy not only improves traffic management systems' predictive powers but also helps the public embrace and trust future CAV technologies. Our research provides a roadmap for municipalities to incorporate cutting-edge data analysis methods into their traffic safety plans. In the age of CAVs, our study contributes to the creation of safer urban mobility solutions by giving data-driven insights.

 

 

All Content © PaperCept, Inc.


This site is protected by copyright and trademark laws under US and International law.
All rights reserved. © 2002-2024 PaperCept, Inc.
Page generated 2024-10-14  01:32:06 PST  Terms of use