A Multi-modal Graph Neural Network Approach to Traffic Risk Forecasting in Smart Urban Sensing

Yang Zhang, Xiangyu Dong, Lanyu Shang, Daniel Zhang, Dong Wang

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Forecasting traffic accidents at a fine-grained spatial scale is essential to provide effective precautions and improve traffic safety in smart urban sensing applications. Current solutions primarily rely on complete historical traffic accident records and/or accurate real-time traffic sensor data for traffic risk prediction. These solutions are prone to various limitations (e.g., facility availability, privacy and legal constraints). In this paper, we address those limitations by exploring two types of widely available and complementary data sources: social media sensing and remote sensing. However, three important technical challenges exist: i) the social media data and remote sensing data often have different data modalities and characteristics, which makes it difficult to effectively fuse them for traffic risk forecasting; ii) the social media data is often noisy, providing fuzzy evidence to capture the spatialoral dynamics of traffic accident occurrences; iii) the remote sensing data often contains complex visual features, making it a non-trivial task to explore the accident occurrence correlation between different locations. To address the above challenges, we propose GraphCast, a multi-modal graph neural network framework to accurately forecast the traffic risks in a city by jointly exploring the social media sensing and remote sensing paradigms. The evaluation results on a real-world case study in New York City show that our GraphCast scheme significantly outperforms the state-of-the-art conventional and deep learning baselines in accurately forecasting the traffic risks in a city.

Original languageEnglish (US)
Title of host publication2020 17th IEEE International Conference on Sensing, Communication and Networking, SECON 2020
PublisherIEEE Computer Society
ISBN (Electronic)9781728166308
DOIs
StatePublished - Jun 2020
Externally publishedYes
Event17th IEEE International Conference on Sensing, Communication and Networking, SECON 2020 - Virtual, Online, Italy
Duration: Jun 22 2020Jun 25 2020

Publication series

NameAnnual IEEE Communications Society Conference on Sensor, Mesh and Ad Hoc Communications and Networks workshops
ISSN (Print)2155-5486
ISSN (Electronic)2155-5494

Conference

Conference17th IEEE International Conference on Sensing, Communication and Networking, SECON 2020
Country/TerritoryItaly
CityVirtual, Online
Period6/22/206/25/20

Keywords

  • Graph Neural Network
  • Remote Sensing
  • Smart Cities
  • Social Sensing
  • Traffic Risk Forecasting

ASJC Scopus subject areas

  • Computer Networks and Communications
  • Hardware and Architecture
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'A Multi-modal Graph Neural Network Approach to Traffic Risk Forecasting in Smart Urban Sensing'. Together they form a unique fingerprint.

Cite this