scholarly journals Short-Term Traffic Flow Prediction Based on Sparse Regression and Spatio-Temporal Data Fusion

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 142111-142119
Author(s):  
Zengwei Zheng ◽  
Lifei Shi ◽  
Lin Sun ◽  
Junjie Du
Keyword(s):  
Data Fusion ◽  
Traffic Flow ◽  
Temporal Data ◽  
Short Term ◽  
Sparse Regression ◽  
Traffic Flow Prediction ◽  
Flow Prediction ◽  
Spatio Temporal

A Unified Spatio-Temporal Model for Short-Term Traffic Flow Prediction

2019 ◽  
Vol 20 (9) ◽  
pp. 3212-3223 ◽  
Author(s):  
Peibo Duan ◽  
Guoqiang Mao ◽  
Weifa Liang ◽  
Degan Zhang
Keyword(s):  
Traffic Flow ◽  
Short Term ◽  
Traffic Flow Prediction ◽  
Flow Prediction ◽  
Temporal Model ◽  
Spatio Temporal

scholarly journals Cross-Attention Fusion Based Spatial-Temporal Multi-Graph Convolutional Network for Traffic Flow Prediction

Sensors ◽  
2021 ◽  
Vol 21 (24) ◽  
pp. 8468
Author(s):  
Kun Yu ◽  
Xizhong Qin ◽  
Zhenhong Jia ◽  
Yan Du ◽  
Mengmeng Lin
Keyword(s):  
Traffic Flow ◽  
Prediction Errors ◽  
Temporal Data ◽  
Convolutional Network ◽  
Smart Transportation ◽  
Traffic Flow Prediction ◽  
Flow Prediction ◽  
Spatio Temporal ◽  
Regional Similarity ◽  
The Impact

Accurate traffic flow prediction is essential to building a smart transportation city. Existing research mainly uses a given single-graph structure as a model, only considers local and static spatial dependencies, and ignores the impact of dynamic spatio-temporal data diversity. To fully capture the characteristics of spatio-temporal data diversity, this paper proposes a cross-Attention Fusion Based Spatial-Temporal Multi-Graph Convolutional Network (CAFMGCN) model for traffic flow prediction. First, introduce GCN to model the historical traffic data’s three-time attributes (current, daily, and weekly) to extract time features. Second, consider the relationship between distance and traffic flow, constructing adjacency, connectivity, and regional similarity graphs to capture dynamic spatial topology information. To make full use of global information, a cross-attention mechanism is introduced to fuse temporal and spatial features separately to reduce prediction errors. Finally, the CAFMGCN model is evaluated, and the experimental results show that the prediction of this model is more accurate and effective than the baseline of other models.

Short-term traffic flow prediction based on spatio-temporal analysis and CNN deep learning

2019 ◽  
Vol 15 (2) ◽  
pp. 1688-1711 ◽  
Author(s):  
Weibin Zhang ◽  
Yinghao Yu ◽  
Yong Qi ◽  
Feng Shu ◽  
Yinhai Wang
Keyword(s):  
Deep Learning ◽  
Traffic Flow ◽  
Temporal Analysis ◽  
Short Term ◽  
Traffic Flow Prediction ◽  
Flow Prediction ◽  
Spatio Temporal
Sign in / Sign up

Export Citation Format

Share Document