中国科学院机构知识库网格
Chinese Academy of Sciences Institutional Repositories Grid
首页 机构 成果 学者
  
  1. CAS IR Grid
  2. 自动化研究所
  3. 中国科学院自动化研究所
  4. 多模态人工智能系统全国重点实验室
  5. 先进控制与自动化团队
Traffic Flow Imputation Using Parallel Data and Generative Adversarial Networks

文献类型：期刊论文

作者Chen, Yuanyuan2,3; Lv, Yisheng1,2; Wang, Fei-Yue1,2
刊名IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版日期2020-04-01
卷号21期号:4页码:1624-1630
关键词Generators Data models Gallium nitride Generative adversarial networks Training Loss measurement Biological system modeling Parallel data generative adversarial networks traffic flow imputation data augmentation deep learning
ISSN号1524-9050
DOI10.1109/TITS.2019.2910295
通讯作者Lv, Yisheng(yisheng.lv@ia.ac.cn)
英文摘要Traffic data imputation is critical for both research and applications of intelligent transportation systems. To develop traffic data imputation models with high accuracy, traffic data must be large and diverse, which is costly. An alternative is to use synthetic traffic data, which is cheap and easy-access. In this paper, we propose a novel approach using parallel data and generative adversarial networks (GANs) to enhance traffic data imputation. Parallel data is a recently proposed method of using synthetic and real data for data mining and data-driven process, in which we apply GANs to generate synthetic traffic data. As it is difficult for the standard GAN algorithm to generate time-dependent traffic flow data, we made twofold modifications: 1) using the real data or the corrupted ones instead of random vectors as latent codes to generator within GANs and 2) introducing a representation loss to measure discrepancy between the synthetic data and the real data. The experimental results on a real traffic dataset demonstrate that our method can significantly improve the performance of traffic data imputation.
WOS关键词INTELLIGENT TRANSPORTATION SYSTEMS ; PREDICTION
资助项目National Natural Science Foundation of China[61533019] ; National Natural Science Foundation of China[61876011] ; National Natural Science Foundation of China[U1811463]
WOS研究方向Engineering ; Transportation
语种英语
WOS记录号WOS:000523478400024
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/38865]  
专题自动化研究所_复杂系统管理与控制国家重点实验室_先进控制与自动化团队
通讯作者Lv, Yisheng
作者单位1.Qingdao Acad Intelligent Ind, Shandong 266109, Peoples R China
2.Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
3.Univ Chinese Acad Sci, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Chen, Yuanyuan,Lv, Yisheng,Wang, Fei-Yue. Traffic Flow Imputation Using Parallel Data and Generative Adversarial Networks[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2020,21(4):1624-1630.
APA Chen, Yuanyuan,Lv, Yisheng,&Wang, Fei-Yue.(2020).Traffic Flow Imputation Using Parallel Data and Generative Adversarial Networks.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,21(4),1624-1630.
MLA Chen, Yuanyuan,et al."Traffic Flow Imputation Using Parallel Data and Generative Adversarial Networks".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 21.4(2020):1624-1630.

入库方式： OAI收割

来源：自动化研究所

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。