TY - GEN
T1 - Heterogeneous spatio-temporal graph convolution network for traffic forecasting with missing values
AU - Zhong, Weida
AU - Suo, Qiuling
AU - Jia, Xiaowei
AU - Zhang, Aidong
AU - Su, Lu
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021/7
Y1 - 2021/7
N2 - Accurate traffic prediction is indispensable for intelligent traffic management. The availability of large-scale road sensing data collected by connected wireless sensors and mobile devices have provided unrealized potential for traffic prediction. However, sensory data is often incomplete due to various factors in the process of data acquisition and transmission. The missingness of traffic data brings a key challenge to the traffic prediction task since the state-of-the-art ML-based traffic prediction models (e.g., Graph Convolutional Networks (GCN)) often rely on spatial and temporal completion of the data. Moreover, existing GCN-based methods usually build a static graph based on geographical distances and are limited in their ability to capture the time-evolving relationships amongst road segments. In this paper, we develop a heterogeneous spatio-temporal prediction framework for traffic prediction using incomplete historical data. In the framework, we build multiple graphs to explicitly model the dynamic correlations among road segments from both geographical and historical aspects, and employ recurrent neural networks to capture temporal correlations for each road segment. We impute missing values in a recurrent process, which is seamlessly embedded in the prediction framework so they can be jointly trained. The proposed framework is evaluated on a public dataset of static sensors and a private dataset collected by our roving sensor system. Experimental results show the effectiveness of the proposed framework compared to state-of-the-art methods, and indicate the potential to be deployed into real-world traffic prediction systems.
AB - Accurate traffic prediction is indispensable for intelligent traffic management. The availability of large-scale road sensing data collected by connected wireless sensors and mobile devices have provided unrealized potential for traffic prediction. However, sensory data is often incomplete due to various factors in the process of data acquisition and transmission. The missingness of traffic data brings a key challenge to the traffic prediction task since the state-of-the-art ML-based traffic prediction models (e.g., Graph Convolutional Networks (GCN)) often rely on spatial and temporal completion of the data. Moreover, existing GCN-based methods usually build a static graph based on geographical distances and are limited in their ability to capture the time-evolving relationships amongst road segments. In this paper, we develop a heterogeneous spatio-temporal prediction framework for traffic prediction using incomplete historical data. In the framework, we build multiple graphs to explicitly model the dynamic correlations among road segments from both geographical and historical aspects, and employ recurrent neural networks to capture temporal correlations for each road segment. We impute missing values in a recurrent process, which is seamlessly embedded in the prediction framework so they can be jointly trained. The proposed framework is evaluated on a public dataset of static sensors and a private dataset collected by our roving sensor system. Experimental results show the effectiveness of the proposed framework compared to state-of-the-art methods, and indicate the potential to be deployed into real-world traffic prediction systems.
KW - Data imputation
KW - Graph neural network
KW - Traffic prediction
UR - https://www.scopus.com/pages/publications/85115129178
U2 - 10.1109/ICDCS51616.2021.00073
DO - 10.1109/ICDCS51616.2021.00073
M3 - Conference contribution
AN - SCOPUS:85115129178
T3 - Proceedings - International Conference on Distributed Computing Systems
SP - 707
EP - 717
BT - Proceedings - 2021 IEEE 41st International Conference on Distributed Computing Systems, ICDCS 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 41st IEEE International Conference on Distributed Computing Systems, ICDCS 2021
Y2 - 7 July 2021 through 10 July 2021
ER -