Early Forecast of Traffic Accident Impact Based on a Single-Snapshot Observation (Student Abstract)

Authors

  • Guangyu Meng University of Notre Dame
  • Qisheng Jiang Shanghai Tech University
  • Kaiqun Fu South Dakota State University
  • Beiyu Lin University of Nevada, Las Vegas
  • Chang-Tien Lu Virginia Tech
  • Zhiqian Chen Mississippi State University

DOI:

https://doi.org/10.1609/aaai.v36i11.21644

Keywords:

Graph Neural Network, Traffic Prediction, Graph Wavelet

Abstract

Predicting and quantifying the impact of traffic accidents is necessary and critical to Intelligent Transport Systems (ITS). As a state-of-the-art technique in graph learning, current graph neural networks heavily rely on graph Fourier transform, assuming homophily among the neighborhood. However, the homophily assumption makes it challenging to characterize abrupt signals such as traffic accidents. Our paper proposes an abrupt graph wavelet network (AGWN) to model traffic accidents and predict their time durations using only one single snapshot.

Downloads

Published

2022-06-28

How to Cite

Meng, G., Jiang, Q., Fu, K., Lin, B., Lu, C.-T., & Chen, Z. (2022). Early Forecast of Traffic Accident Impact Based on a Single-Snapshot Observation (Student Abstract). Proceedings of the AAAI Conference on Artificial Intelligence, 36(11), 13015-13016. https://doi.org/10.1609/aaai.v36i11.21644