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
Long memory is important: A test study on deep-learning based car-following model

文献类型：期刊论文

作者Wang, Xiao1; Jiang, Rui2; Li, Li3; Lin, Yi-Lun4; Wang, Fei-Yue4
刊名PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS
出版日期2019-01-15
卷号514页码:786-795
ISSN号0378-4371
关键词Car-following Long memory Hysteresis Deep learning
DOI10.1016/j.physa.2018.09.136
通讯作者Jiang, Rui(jiangrui@bjtu.edu.cn) ; Li, Li(li-li@tsinghua.edu.cn)
英文摘要Whether long memory effect plays an important role in car-following models remains unsolved. In this paper, we study the possible relationship between long memory effect and hysteresis phenomena observed in practice. Especially, we have compared the performance of different deep learning based car-following models that take various time-scale historical information as inputs. Test show that hysteresis phenomena can be correctly simulated only by car-following models with long memory. So, we argue that car-following models should embed long memory effect appropriately. (C) 2018 Elsevier B.V. All rights reserved.
WOS关键词CONGESTED TRAFFIC STATES ; PHASE-TRANSITIONS ; NEURAL-NETWORKS ; FLOW ; CALIBRATION ; HYSTERESIS ; STABILITY ; ALGORITHM ; DIAGRAM ; DELAY
资助项目National Natural Science Foundation of China[61790565] ; Beijing Municipal Science and Technology Commission Program, China[D171100000317002] ; Beijing Municipal Commission of Transport, China[ZC179074Z] ; Natural Science Foundation of Beijing Municipality, China[9172013]
WOS研究方向Physics
语种英语
出版者ELSEVIER SCIENCE BV
WOS记录号WOS:000450137000070
资助机构National Natural Science Foundation of China ; Beijing Municipal Science and Technology Commission Program, China ; Beijing Municipal Commission of Transport, China ; Natural Science Foundation of Beijing Municipality, China
源URL[http://ir.ia.ac.cn/handle/173211/22587]  
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
自动化研究所_复杂系统管理与控制国家重点实验室
通讯作者Jiang, Rui; Li, Li
作者单位1.Xi An Jiao Tong Univ, Dept Comp Sci & Technol, Xian 710049, Shaanxi, Peoples R China
2.Tsinghua Univ, Dept Automat, Beijing 100084, Peoples R China
3.Beijing Jiaotong Univ, Sch Traff & Transportat, Beijing 100044, Peoples R China
4.Chinese Acad Sci, State Key Lab Management & Control Complex Syst, Inst Automat, Beijing 100080, Peoples R China
推荐引用方式
GB/T 7714		 Wang, Xiao,Jiang, Rui,Li, Li,et al. Long memory is important: A test study on deep-learning based car-following model[J]. PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS,2019,514:786-795.
APA Wang, Xiao,Jiang, Rui,Li, Li,Lin, Yi-Lun,&Wang, Fei-Yue.(2019).Long memory is important: A test study on deep-learning based car-following model.PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS,514,786-795.
MLA Wang, Xiao,et al."Long memory is important: A test study on deep-learning based car-following model".PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS 514(2019):786-795.

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。