HintNet: Hierarchical Knowledge Transfer Networks for Traffic Accident Forecasting on Heterogeneous Spatio-Temporal Data

Bang An; Amin Vahedian; Xun Zhou; W Nick Street; Yanhua Li

doi:10.48550/arXiv.2203.03100

Back

HintNet: Hierarchical Knowledge Transfer Networks for Traffic Accident Forecasting on Heterogeneous Spatio-Temporal Data

Preprint

Open access

HintNet: Hierarchical Knowledge Transfer Networks for Traffic Accident Forecasting on Heterogeneous Spatio-Temporal Data

Bang An, Amin Vahedian, Xun Zhou, W Nick Street and Yanhua Li

arXiv.org

Cornell University

03/07/2022

DOI: 10.48550/arXiv.2203.03100

Files and links (1)

url

https://doi.org/10.48550/arXiv.2203.03100View

Preprint (Author's original)This preprint has not been evaluated by subject experts through peer review. Preprints may undergo extensive changes and/or become peer-reviewed journal articles. Open Access

Abstract

Traffic accident forecasting is a significant problem for transportation management and public safety. However, this problem is challenging due to the spatial heterogeneity of the environment and the sparsity of accidents in space and time. The occurrence of traffic accidents is affected by complex dependencies among spatial and temporal features. Recent traffic accident prediction methods have attempted to use deep learning models to improve accuracy. However, most of these methods either focus on small-scale and homogeneous areas such as populous cities or simply use sliding-window-based ensemble methods, which are inadequate to handle heterogeneity in large regions. To address these limitations, this paper proposes a novel Hierarchical Knowledge Transfer Network (HintNet) model to better capture irregular heterogeneity patterns. HintNet performs a multi-level spatial partitioning to separate sub-regions with different risks and learns a deep network model for each level using spatio-temporal and graph convolutions. Through knowledge transfer across levels, HintNet archives both higher accuracy and higher training efficiency. Extensive experiments on a real-world accident dataset from the state of Iowa demonstrate that HintNet outperforms the state-of-the-art methods on spatially heterogeneous and large-scale areas.

Knowledge Management

Mathematical Models

Forecasting

Heterogeneity

Public safety

Safety management

Spatiotemporal data

Traffic accidents

Transportation management

Transportation networks

Details

Title: Subtitle: HintNet: Hierarchical Knowledge Transfer Networks for Traffic Accident Forecasting on Heterogeneous Spatio-Temporal Data
Creators: Bang An
Amin Vahedian
Xun Zhou
W Nick Street
Yanhua Li
Resource Type: Preprint
Publication Details: arXiv.org
DOI: 10.48550/arXiv.2203.03100
eISSN: 2331-8422
Publisher: Cornell University; Ithaca
Language: English
Date posted: 03/07/2022
Academic Unit: Bus Admin College; Nursing; Computer Science; Business Analytics
Record Identifier: 9984380405202771

Metrics

61 Record Views