Spatial Origin-Destination Flow Imputation Using Graph Convolutional Networks
文献类型：期刊论文
| 作者 | Yao, Xin2; Gao, Yong2; Zhu, Di2; Manley, Ed3; Wang, Jiaoe1,4; Liu, Yu2 |
| 刊名 | IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
 |
| 出版日期 | 2021-12-01 |
| 卷号 | 22期号:12页码:7474-7484 |
| 关键词 | Spatial databases Gravity Convolution Biological system modeling Data models Predictive models Neural networks Origin-destination flow data imputation spatial interaction network graph embedding graph convolution |
| ISSN号 | 1524-9050 |
| DOI | 10.1109/TITS.2020.3003310 |
| 通讯作者 | Gao, Yong(gaoyong@pku.edu.cn) |
| 英文摘要 | Due to the limitation of data collection techniques and privacy issues, the problem of missing spatial origin-destination flows frequently occurs. Data imputation provides great support for the acquisition of complete flow data, which enables us to better understand regional connections and mobility patterns. However, existing models or approaches neglect the network structure of spatial flows, thus resulting in inappropriate estimates and a low performance. The development of graph neural networks offers a powerful tool to deal with graph-structured data. In this article, we proposed a spatial interaction graph convolutional network model, which combines graph convolution and a mapping function to predict flow data from the perspective of network learning. This model utilizes geographical unit embedding in local spatial networks to improve prediction accuracy. A negative sampling technique is adopted to reduce misestimation. Experiments on Beijing taxi trip data verified the usefulness of our model in spatial flow prediction. We also demonstrated that a biased training sample had a negative impact on the model's performance. More attributes of geographical units, a more proper negative sampling rate and a larger training set can increase the prediction accuracy of flow data. |
| WOS关键词 | INTERACTION PATTERNS ; NEURAL-NETWORKS ; MOBILITY ; MATRICES ; MODELS ; CHINA ; URBAN ; COMMUNITIES ; INFERENCE |
| 资助项目 | National Natural Science Foundation of China[41971331] ; National Natural Science Foundation of China[41830645] ; National Natural Science Foundation of China[41625003] ; National Natural Science Foundation of China[41771425] ; National Key Research and Development Program of China[2017YFB0503602] ; Smart Guangzhou Spatio-Temporal Information Cloud Platform Construction[GZIT2016-A5-147] |
| WOS研究方向 | Engineering ; Transportation |
| 语种 | 英语 |
| WOS记录号 | WOS:000722718400016 |
| 出版者 | IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC |
| 资助机构 | National Natural Science Foundation of China ; National Key Research and Development Program of China ; Smart Guangzhou Spatio-Temporal Information Cloud Platform Construction |
| 源URL | [http://ir.igsnrr.ac.cn/handle/311030/168099]  |
| 专题 | 中国科学院地理科学与资源研究所 |
| 通讯作者 | Gao, Yong |
| 作者单位 | 1.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, Beijing 100101, Peoples R China 2.Peking Univ, Sch Earth & Space Sci, Inst Remote Sensing & Geog Informat Syst, Beijing 100871, Peoples R China 3.Univ Leeds, Sch Geog, Leeds LS2 9JT, W Yorkshire, England 4.Univ Chinese Acad Sci, Coll Resources & Environm, Beijing 100049, Peoples R China |
| 推荐引用方式 GB/T 7714 | Yao, Xin,Gao, Yong,Zhu, Di,et al. Spatial Origin-Destination Flow Imputation Using Graph Convolutional Networks[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2021,22(12):7474-7484. |
| APA | Yao, Xin,Gao, Yong,Zhu, Di,Manley, Ed,Wang, Jiaoe,&Liu, Yu.(2021).Spatial Origin-Destination Flow Imputation Using Graph Convolutional Networks.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,22(12),7474-7484. |
| MLA | Yao, Xin,et al."Spatial Origin-Destination Flow Imputation Using Graph Convolutional Networks".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 22.12(2021):7474-7484. |
入库方式： OAI收割
来源：地理科学与资源研究所
浏览0
下载0
收藏0
其他版本
除非特别说明，本系统中所有内容都受版权保护，并保留所有权利。