Pervasive Sensing to Correlate Vehicle Driving Behavior With City-Scale Traffic Dynamics
- 17 April 2025
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Pervasive Computing
- Vol. 24 (2) , 39-47
Abstract
Individual driving behavior is a pivotal element that shapes the overall traffic dynamics in a city. In this work, we study and analyze the complex web of relationships between individual driving behaviors and their impact on the overall traffic dynamics of a smart city with two primary objectives: first, understanding the spatial interaction between individual vehicles and their impact on each other, and second, finding anomalous driving behaviors, which lead to congestion and traffic incidents. Specifically, we introduce an overarching modular framework investigating human factors of driver characteristics, vehicle attributes, geographical terrain surrounding the road infrastructure, and environmental conditions. Analyzing driving maneuvers considering such diverse factors emphasizes the removal of the bias in driving behavior prediction. Our study serves as an essential foundation to delve into the problem of traffic dynamics in a city and further motivates the need for a deeper understanding of the correlation between driving behavior and traffic management.Keywords
Funding Information
- Missouri University of Science and Technology
- Institute Ethical Committee, IIT Kharagpur (IIT/SRIC/DEAN/2023)
- Ubiquitous and Networked Systems
- India and Missouri University of Science and Technology, USA
- NSF (OAC-2320951, CNS-2030611, ECCS-2319995, OAC-2104078, CNS-2030624)
This publication has 11 references indexed in Scilit:
- Why Slammed the Brakes On? Auto-annotating Driving Behaviors from Adaptive Causal Modeling2022
- Predicting Road Accident Risk Using Geospatial Data and Machine Learning (Demo Paper)2021
- The inD Dataset: A Drone Dataset of Naturalistic Road User Trajectories at German Intersections2020
- BDD100K: A Diverse Driving Dataset for Heterogeneous Multitask Learning2020
- Investigating rear-end collision avoidance behavior under varied foggy weather conditions: A study using advanced driving simulator and survival analysisAccident Analysis & Prevention, 2020
- Characterizing Driving Context from Driver Behavior2017
- Smart-phone based Spatio-temporal Sensing for Annotated Transit Map Generation2017
- Fine-Grained Abnormal Driving Behaviors Detection and Identification with SmartphonesIEEE Transactions on Mobile Computing, 2016
- Risky Driving Behavior and Road Traffic Crashes Among Young Asian Australian Drivers: Findings From the DRIVE StudyTraffic Injury Prevention, 2010
- Matching With Doses in an Observational Study of a Media Campaign Against Drug AbuseJournal of the American Statistical Association, 2001