Hetero-ConvLSTM: A Deep Learning Approach to Traffic Accident Prediction on Heterogeneous Spatio-Temporal Data

By Zhuoning Yuan, Xun Zhou, Tianbao Yang. Knowledge Discovery and Data Mining, 2018

406 citations recorded by the source corpus.

Predicting traffic accidents is a crucial problem to improving transportation and public safety as well as safe routing. The problem is also challenging due to the rareness of accidents in space and time and spatial heterogeneity of the environment (e.g., urban vs. rural). Most previous research on traffic accident prediction conducted by domain researchers simply applied classical prediction models on limited data without addressing the above challenges properly, thus leading to unsatisfactory performance. A small number of recent works have attempted to use deep learning for traffic accident prediction. However, they either ignore time information or use only data from a small and homogeneous study area (a city), without handling spatial heterogeneity and temporal auto-correlation properly at the same time. In this paper we perform a comprehensive study on the traffic accident prediction problem using the Convolutional Long Short-Term Memory (ConvLSTM) neural network model. A number of detailed features such as weather, environment, road condition, and traffic volume are extracted from big datasets over the state of Iowa across 8 years. To address the spatial heterogeneity challenge in the data, we propose a Hetero-ConvLSTM framework, where a few novel ideas are implemented on top of the basic ConvLSTM model, such as incorporating spatial graph features and spatial model ensemble. Extensive experiments on the 8-year data over the entire state of Iowa show that the proposed framework makes reasonably accurate predictions and significantly improves the prediction accuracy over baseline approaches.

Subfields: Building and Construction, Safety, Risk, Reliability and Quality, Transportation

View Paper: https://www.semanticscholar.org/paper/9288096eefc817d25c22c31a6e37b5f2a2bd2c4c

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Building and Construction

In Transportation

Citations in the corpus

Decoupled Dynamic Spatial-Temporal Graph Neural Network for Traffic Forecasting (2022, background): “This functionality fuels a wide range of services related to traffic management [4], urban computing [52], public safety [48], and beyond [14, 28, 34, 47].”
Spatio-Temporal Self-Supervised Learning for Traffic Flow Prediction (2022, positive): “Recently, some works model the heterogeneity by using multiple models (Yuan, Zhou, and Yang 2018) or multiple sets of parameters (Bai et al. 2020; Li and Zhu 2021), and some use meta learning to generate different weights based on static features of different regions (Pan et al. 2019a; Ye et al.…”
Process (2020, background): “Most of the previous works [10, 11, 12, 13, 14, 15, 16, 17, 18, 19] on traffic modeling focus on predicting speed, volume, density and travel time, which have achieved remarkable success in this field.”
Graph Neural Networks for Intelligent Transportation Systems: A Survey (2023, methodology): “The performance of their framework is evaluated using two real datasets and baseline models including ARIMA, LSTM, Hetero-ConvLSTM [204], STGCN [27], STG2seq [51], STSGCN [205], STDN [206], DFN [207], MTPSO [208].”