Editor/Reviewer loginFrequency : 12 issues per year
Subject : Computer Applications and Technology
ISSN : 2319–8656 (Online)
IJCATR Volume 11 Issue 5
Combined Traffic Flow Prediction Based on Graph Convolution
Wang Ke
10.7753/IJCATR1105.1004
keywords : traffic flow prediction; temporal convolution; spatial convolution
Traffic flow data has strong temporal and spatial correlation. The traffic flow in the previous moment will affect the traffic flow in the next moment, and the traffic flow in the upstream and downstream will affect each other in space. . In order to alleviate traffic congestion and improve the accuracy of traffic flow prediction, this paper proposes a combined traffic flow prediction model C GCN based on graph convolution. product to extract the temporal features of the traffic flow. The experimental results show that the prediction effect of the C- GCN combination prediction model is better.
@artical{w1152022ijcatr11051004,
Title = "Combined Traffic Flow Prediction Based on Graph Convolution",
Journal ="International Journal of Computer Applications Technology and Research(IJCATR)",
Volume = "11",
Issue ="5",
Pages ="170 - 174",
Year = "2022",
Authors ="Wang Ke"}
Research based on deep learning makes prediction results more accurate.
Separately extract temporal and spatial features of traffic flow.
Building a combined model CGCN to predict traffic flow.
Using GCN to extract the spatial features of traffic flow is more effective.