LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data

Bang An; Xun Zhou; Amin Vahedian; Nick Street; Jinping Guan; Jun Luo

doi:10.1109/ICDM59182.2024.00008

Back

Conference proceeding

LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data

Bang An, Xun Zhou, Amin Vahedian, Nick Street, Jinping Guan and Jun Luo

Proceedings (IEEE International Conference on Data Mining), pp.11-20

12/09/2024

DOI: 10.1109/ICDM59182.2024.00008

View Online

Abstract

Traffic accident forecasting is an important task for intelligent transportation management and emergency response systems. However, this problem is challenging due to the spatial heterogeneity of the environment. Existing data-driven methods mostly focus on studying homogeneous areas with limited size (e.g. a single urban area such as New York City) and fail to handle the heterogeneous accident patterns over space at different scales. Recent advances (e.g. spatial ensemble) utilize pre-defined space partitions and learn multiple models to improve prediction accuracy. However, external knowledge is required to define proper space partitions before training models and predefined partitions may not necessarily reduce the heterogeneity. To address this issue, we propose a novel Learning-Integrated Space Partition Framework (LISA) to simultaneously learn partitions while training models, where the partitioning process and learning process are integrated in a way that partitioning is guided explicitly by prediction accuracy rather than other factors. Experiments using real-world datasets, demonstrate that our work can capture underlying heterogeneous patterns in a self-guided way and substantially improve baseline networks by an average of 13.0%.

Accidents

Data Mining

Transportation

Accuracy

Forecasting

Predictive models

Spatialtemporal Data Mining

Spatiotemporal phenomena

Time factors

Traffic Accident Forecasting

Training

Urban areas

Details

Title: Subtitle: LISA: Learning-Integrated Space Partitioning Framework for Traffic Accident Forecasting on Heterogeneous Spatiotemporal Data
Creators: Bang An - University of Iowa
Xun Zhou - Harbin Institute of Technology
Amin Vahedian - Northern Illinois University
Nick Street - University of Iowa
Jinping Guan - Massachusetts Institute of Technology
Jun Luo
Resource Type: Conference proceeding
Publication Details: Proceedings (IEEE International Conference on Data Mining), pp.11-20
Publisher: IEEE
DOI: 10.1109/ICDM59182.2024.00008
eISSN: 2374-8486
Number of pages: 10
Grant note: University of Iowa (10.13039/100008893)
Language: English
Date published: 12/09/2024
Academic Unit: Nursing; Business Analytics; Computer Science; Bus Admin College
Record Identifier: 9984793879002771

Metrics

1 Record Views