AAAI

Association for the Advancement of Artificial Intelligence

Home > Proceedings / Proceedings of the AAAI Conference on Artificial Intelligence, 35 > No. 5: AAAI-21 Technical Tracks 5

GSNet: Learning Spatial-Temporal Correlations from Geographical and Semantic Aspects for Traffic Accident Risk Forecasting

Authors

Beibei Wang

School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China


Youfang Lin

School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China CAAC Key Laboratory of Intelligent Passenger Service of Civil Aviation, Beijing, China Key Laboratory of Transport Industry of Big Data Appalication Technologies for Comprehensive Transport, Beijing, China


Shengnan Guo

School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China Key Laboratory of Transport Industry of Big Data Appalication Technologies for Comprehensive Transport, Beijing, China


Huaiyu Wan

School of Computer and Information Technology, Beijing Jiaotong University, Beijing, China Beijing Key Laboratory of Traffic Data Analysis and Mining, Beijing, China CAAC Key Laboratory of Intelligent Passenger Service of Civil Aviation, Beijing, China


Proceedings:

No. 5: AAAI-21 Technical Tracks 5

Volume

Issue:

Proceedings of the AAAI Conference on Artificial Intelligence, 35

Track:

AAAI Technical Track on Data Mining and Knowledge Management

Downloads:

Download PDF

Abstract:

Traffic accident forecasting is of great importance to urban public safety, emergency treatment, and construction planning. However, it is very challenging since traffic accidents are affected by multiple factors, and have multi-scale dependencies on both spatial and temporal dimensional features. Meanwhile, traffic accidents are rare events, which leads to the zero-inflated issue. Existing traffic accident forecasting methods cannot deal with all above problems simultaneously. In this paper, we propose a novel model, named GSNet, to learn the spatial-temporal correlations from geographical and semantic aspects for traffic accident risk forecasting. In the model, a Spatial-Temporal Geographical Module is designed to capture the geographical spatial-temporal correlations among regions, while a Spatial-Temporal Semantic Module is proposed to model the semantic spatial-temporal correlations among regions. In addition, a weighted loss function is designed to solve the zero-inflated issue. Extensive experiments on two real-world datasets demonstrate the superiority of GSNet against the state-of-the-art baseline methods.

DOI:

10.1609/aaai.v35i5.16566


AAAI

Proceedings of the AAAI Conference on Artificial Intelligence, 35