Analysis of Different Graph Convolutional Network Prediction Models with Spatial Dependence Evaluation

Autor:	Weike Lu, Hao Huang, Qipeng Yan, Lan Liu, Yuting Chen, Jiannan Mao
Rok vydání:	2021
Předmět:	Sequence Computer science Feature extraction Graph (abstract data type) Adjacency matrix Spatial dependence Residual Algorithm Maximal information coefficient Convolutional neural network
Zdroj:	ITSC
DOI:	10.1109/itsc48978.2021.9564626
Popis:	Over the past few years, the graph-based Graph Convolutional Network (GCN) models have been introduced to handle the spatial-temporal attributes in short-term traffic prediction. Aiming at filling the gap of lacking comparisons of different graph-based models, this study analyses the performances of different graph-based convolutional neural networks. A modified sequence to sequence structure with attention mechanism and the residual module is applied as the backbone of the prediction model, and the input to the graph-based models is the Maximal Information Coefficient (MIC) adjacency matrix. The results confirm the effectiveness of the proposed prediction framework and shed light on choosing the most acceptable graph-based convolutional neural networks for short-term traffic predictions.
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=doi_________::be584a9e4cd48eb8e7999df19f2a1364 https://doi.org/10.1109/itsc48978.2021.9564626 Zobrazit plný text záznamu