.png){kind=icon}
返回
Spatial-Temporal Traffic Prediction With an Interactive Spatial-Enhanced Graph Convolutional Network Model
.png){kind=icon}
PRE
AI
DOI：10.1109/TITS.2024.3467172.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Accurate traffic prediction is crucial for effective traffic control and risk assessment. Traffic data exhibits a distinct nature, characterized by the interplay of swift, sudden short-term variations and enduring, extended long-term trends within specific regions. This intricate intermingling and interaction give rise to diverse spatial propagation patterns. Successful traffic prediction models necessitate mastering multi-scale temporal and dynamic spatial correlations, as well as their intricate interrelationships. In this study, we present a novel spatial-temporal traffic prediction framework named Interactive Spatial-Enhanced Graph Convolution Network (ISGCN). Our key innovation lies in the introduction of a novel dynamic graph convolution module, which not only captures overarching spatial correlations but also unveils the concealed evolution of dynamic spatial correlations over time. By seamlessly integrating the graph convolutional module with temporal sample convolution and interaction blocks, we adeptly bridge multi-scale temporal correlations with the acquired dynamic spatial correlations. Additionally, we harness diverse temporal granularities data to comprehensively capture global temporal correlations. Experiments conducted on four real-world traffic datasets illustrate that ISGCN outperforms diverse types of state-of-the-art baseline models.
Keyword:
Correlation
Roads
Predictive models
Feature extraction
Convolution
Time series analysis
Data models
Accuracy
Vehicle dynamics
Spatiotemporal phenomena
Traffic prediction
graph convolutional network
multi-scale temporal correlations
dynamic spatial correlations
期刊
IF:
8.4
论文数:
9.7K
被引数:
6.3W
机构
引用论文
.png){kind=icon}
Dynamic spatiotemporal interactive graph neural network for multivariate time series forecasting用于多元时间序列预测的动态时空交互图神经网络
PREAI
分享收藏Multi-Source Information Fusion Graph Convolution Network for traffic flow prediction面向交通流预测的多源信息融合图卷积网络
PREAI
分享收藏A novel reinforced dynamic graph convolutional network model with data imputation for network-wide traffic flow prediction一种具有数据插补的新型增强型动态图卷积网络模型，用于网络范围内的交通流预测
PREAI
分享收藏Automated Dilated Spatio-Temporal Synchronous Graph Modeling for Traffic Prediction用于交通预测的自动扩展时空同步图建模
OAAI
OAAI分享收藏
查看更多内容