An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction
Accurate traffic prediction is a powerful factor of intelligent transportation systems to make assisted decisions. However, existing methods are deficient in modeling long series spatio-temporal characteristics. Due to the complex and nonlinear nature of traffic flow time series, traditional methods...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-01-01
|
| Series: | Journal of Advanced Transportation |
| Online Access: | http://dx.doi.org/10.1155/2022/7682274 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832545947704360960 |
|---|---|
| author | Shanchun Zhao Xu Li |
| author_facet | Shanchun Zhao Xu Li |
| author_sort | Shanchun Zhao |
| collection | DOAJ |
| description | Accurate traffic prediction is a powerful factor of intelligent transportation systems to make assisted decisions. However, existing methods are deficient in modeling long series spatio-temporal characteristics. Due to the complex and nonlinear nature of traffic flow time series, traditional methods of prediction tasks tend to ignore the heterogeneity and long series dependencies of spatio-temporal data. In this paper, we propose an attentional encoder-decoder dual graph convolution model with time-series correlation (AED-DGCN-TSC) for solving the spatio-temporal sequence prediction problem in the traffic domain. First, the time-series correlation module calculates the sequence similarity by fast Fourier transform and inverse fast Fourier transform, while obtaining multiple possible lengths as possible solutions for the sequence period length. Then, K possible periods fetches are selected and the corresponding sequences are weighted and aggregated to the target sequence. Then, the gated dual graph convolution recurrent unit uses the graph convolution operation, which combines the ideas of node embedding, and dual graph, as an operation inside the gated recurrent structure to capture the spatio-temporal heterogeneity relationship of long sequences. The gated decomposition recurrent module decomposes the time series into the period and trend terms, which are modelled by convolutional gated recurrent unit (ConvGRU) and then fused with features, respectively, and output after graph convolution. Finally, multi-step prediction of future traffic flow is performed in the form of encoder-decoder. Experimental evaluations are conducted on two real traffic datasets, and the results demonstrate the effectiveness of the proposed model. |
| format | Article |
| id | doaj-art-bd20b67920164ee0845ab2c5b7bc9499 |
| institution | Kabale University |
| issn | 2042-3195 |
| language | English |
| publishDate | 2022-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Journal of Advanced Transportation |
| spelling | doaj-art-bd20b67920164ee0845ab2c5b7bc94992025-02-03T07:24:18ZengWileyJournal of Advanced Transportation2042-31952022-01-01202210.1155/2022/7682274An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow PredictionShanchun Zhao0Xu Li1School of Traffic and TransportationSchool of Traffic and TransportationAccurate traffic prediction is a powerful factor of intelligent transportation systems to make assisted decisions. However, existing methods are deficient in modeling long series spatio-temporal characteristics. Due to the complex and nonlinear nature of traffic flow time series, traditional methods of prediction tasks tend to ignore the heterogeneity and long series dependencies of spatio-temporal data. In this paper, we propose an attentional encoder-decoder dual graph convolution model with time-series correlation (AED-DGCN-TSC) for solving the spatio-temporal sequence prediction problem in the traffic domain. First, the time-series correlation module calculates the sequence similarity by fast Fourier transform and inverse fast Fourier transform, while obtaining multiple possible lengths as possible solutions for the sequence period length. Then, K possible periods fetches are selected and the corresponding sequences are weighted and aggregated to the target sequence. Then, the gated dual graph convolution recurrent unit uses the graph convolution operation, which combines the ideas of node embedding, and dual graph, as an operation inside the gated recurrent structure to capture the spatio-temporal heterogeneity relationship of long sequences. The gated decomposition recurrent module decomposes the time series into the period and trend terms, which are modelled by convolutional gated recurrent unit (ConvGRU) and then fused with features, respectively, and output after graph convolution. Finally, multi-step prediction of future traffic flow is performed in the form of encoder-decoder. Experimental evaluations are conducted on two real traffic datasets, and the results demonstrate the effectiveness of the proposed model.http://dx.doi.org/10.1155/2022/7682274 |
| spellingShingle | Shanchun Zhao Xu Li An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction Journal of Advanced Transportation |
| title | An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction |
| title_full | An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction |
| title_fullStr | An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction |
| title_full_unstemmed | An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction |
| title_short | An Attention Encoder-Decoder Dual Graph Convolutional Network with Time Series Correlation for Multi-Step Traffic Flow Prediction |
| title_sort | attention encoder decoder dual graph convolutional network with time series correlation for multi step traffic flow prediction |
| url | http://dx.doi.org/10.1155/2022/7682274 |
| work_keys_str_mv | AT shanchunzhao anattentionencoderdecoderdualgraphconvolutionalnetworkwithtimeseriescorrelationformultisteptrafficflowprediction AT xuli anattentionencoderdecoderdualgraphconvolutionalnetworkwithtimeseriescorrelationformultisteptrafficflowprediction AT shanchunzhao attentionencoderdecoderdualgraphconvolutionalnetworkwithtimeseriescorrelationformultisteptrafficflowprediction AT xuli attentionencoderdecoderdualgraphconvolutionalnetworkwithtimeseriescorrelationformultisteptrafficflowprediction |