关键词: 智能交通, 数据修复, 图自编码器, 生成对抗网络, 时空特征, 深度学习

Abstract:  The completeness of the traffic and road network data affects the operation of the intelligent transportation systems. This paper proposes a method based on graph autoencoder-generative adversarial network to repair the missing data in the road network. First, the spatiotemporal features of the missing road network data are extracted through the denoising graph variational autoencoder which captures the original road network information to the greatest extent. Then, based on the spatial-temporal features, the study uses the generative adversarial network to generate repaired road network data, adds reconstruction Loss, and optimizes the objective function of the generation of the confrontation network. The effective interpolation of missing data is then realized. This study uses the Seattle (Seattle) and California (PEMS04) road network speed datasets to conduct comparative experiments on data restoration with different missing types and missing rates. When the random missing rate is between 10% and 70% , the mean absolute error(MAE) index of the Seattle dataset is between 2.38 and 3.25. The MAE index of the PEMS04 data set is between 1.46 and 2.38. When the aggregated missing rate is between 10% and 70%, the MAE index of the Seattle data set is between 2.51 and 2.82. The MAE index of the PEMS04 data set is between 1.52 and 1.54. The comparison results show that the proposed road network data restoration methods perform better than the backpropagation network(BP), denoising stacked auto-encoder(DSAE), bayesian gaussian Candecomp/Parafac(BGCP) and other models involved in the comparison analy

Key words: intelligent transportation, data repair, graph auto-encoder, generative adversarial network, potential spatiotemporal features, deep learning