https://scholars.lib.ntu.edu.tw/handle/123456789/607479
標題: | Multivariate and Propagation Graph Attention Network for Spatialoral Prediction with Outdoor Cellular Traffic | 作者: | Lin C.-Y Su H.-T Tung S.-L WINSTON HSU |
關鍵字: | graph attention network;multivariate spatialoral prediction;outdoor cellular traffic;Backpropagation;Traffic control;Cellulars;Critical problems;Device costs;Graph attention network;Intelligent transportation;Large-scales;Multivariate spatialoral prediction;Outdoor cellular traffic;Propagation graph;Traffic data;Forecasting | 公開日期: | 2021 | 起(迄)頁: | 3248-3252 | 來源出版物: | International Conference on Information and Knowledge Management, Proceedings | 摘要: | Spatialoral prediction is a critical problem for intelligent transportation, which is helpful for tasks such as traffic control and accident prevention. Previous studies rely on large-scale traffic data collected from sensors. However, it is unlikely to deploy sensors in all regions due to the device and maintenance costs. This paper addresses the problem via outdoor cellular traffic distilled from over two billion records per day in a telecom company, because outdoor cellular traffic induced by user mobility is highly related to transportation traffic. We study road intersections in urban and aim to predict future outdoor cellular traffic of all intersections given historic outdoor cellular traffic. Furthermore, we propose a new model for multivariate spatialoral prediction, mainly consisting of two extending graph attention networks (GAT). First GAT is used to explore correlations among multivariate cellular traffic. Another GAT leverages the attention mechanism into graph propagation to increase the efficiency of capturing spatial dependency. Experiments show that the proposed model significantly outperforms the state-of-the-art methods on our dataset. ? 2021 ACM. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85119209122&doi=10.1145%2f3459637.3482152&partnerID=40&md5=f23efd9a2bc104a5dd418c4df4df2ec9 https://scholars.lib.ntu.edu.tw/handle/123456789/607479 |
DOI: | 10.1145/3459637.3482152 | SDG/關鍵字: | Backpropagation; Traffic control; Cellulars; Critical problems; Device costs; Graph attention network; Intelligent transportation; Large-scales; Multivariate spatialoral prediction; Outdoor cellular traffic; Propagation graph; Traffic data; Forecasting |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。