Journal
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
Volume 35, Issue 3, Pages 2796-2808Publisher
IEEE COMPUTER SOC
DOI: 10.1109/TKDE.2021.3112977
Keywords
Standards; Deformable models; Autocorrelation; Predictive models; Urban areas; Shape; Residual neural networks; Traffic flow prediction; spatial nonstationarity; deformable convolution; deep learning
Ask authors/readers for more resources
Deep neural networks, such as convolutional neural networks (CNNs) and graph neural networks (GNNs), are widely used for short-term traffic flow prediction. CNNs are suitable for region-wise prediction, while GNNs perform better on graph-structured traffic data. DeFlow-Net, a deep deformable convolutional residual network, is proposed to model global spatial dependence, local spatial nonstationarity, and temporal periodicity of traffic flows. The use of pre-conceived regions or self-organized regions for traffic flow aggregation and network input also improves the performance of DeFlow-Net.
Deep neural networks are being increasingly used for short-term traffic flow prediction, which can be generally categorized as convolutional (CNNs) or graph neural networks (GNNs). CNNs are preferable for region-wise traffic prediction by taking advantage of localized spatial correlations, whilst GNNs achieves better performance for graph-structured traffic data. When applied to region-wise traffic prediction, CNNs typically partition an underlying territory into grid-like spatial units, and employ standard convolutions to learn spatial dependence among the units. However, standard convolutions with fixed geometric structures cannot fully model the nonstationary characteristics of local traffic flows. To overcome the deficiency, we introduce deformable convolution that augments the spatial sampling locations with additional offsets, to enhance the modeling capability of spatial nonstationarity. On this basis, we design a deep deformable convolutional residual network, namely DeFlow-Net, that can effectively model global spatial dependence, local spatial nonstationarity, and temporal periodicity of traffic flows. Furthermore, to better fit with convolutions, we suggest to first aggregate traffic flows according to pre-conceived regions or self-organized regions based on traffic flows, then dispose to sequentially organized raster images for network input. Extensive experiments on real-world traffic flows demonstrate that DeFlow-Net outperforms GNNs and existing CNNs using standard convolutions, and spatial partition by pre-conceived regions or self-organized regions further enhances the performance. We also demonstrate the advantage of DeFlow-Net in maintaining spatial autocorrelation, and reveal the impacts of partition shapes and scales on deep traffic flow prediction.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available