An efficient realization of deep learning for traffic data imputation
Duan, Yanjie; Lv, Yisheng; Liu, Yu-Liang; Wang, Fei-Yue
发表期刊TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES
2016-11-01
卷号72页码:168-181
文章类型Article
摘要Traffic data provide the basis for both research and applications in transportation control, management, and evaluation, but real-world traffic data collected from loop detectors or other sensors often contain corrupted or missing data points which need to be imputed for traffic analysis. For this end, here we propose a deep learning model named denoising stacked autoencoders for traffic data imputation. We tested and evaluated the model performance with consideration of both temporal and spatial factors. Through these experiments and evaluation results, we developed an algorithm for efficient realization of deep learning for traffic data imputation by training the model hierarchically using the full set of data from all vehicle detector stations. Using data provided by Caltrans PeMS, we have shown that the mean absolute error of the proposed realization is under 10 veh/5-min, a better performance compared with other popular models: the history model, ARIMA model and BP neural network model. We further investigated why the deep leaning model works well for traffic data imputation by visualizing the features extracted by the first hidden layer. Clearly, this work has demonstrated the effectiveness as well as efficiency of deep learning in the field of traffic data imputation and analysis. (C) 2016 Elsevier Ltd. All rights reserved.
关键词Traffic Data Imputation Deep Learning Missing Data
WOS标题词Science & Technology ; Technology
DOI10.1016/j.trc.2016.09.015
关键词[WOS]TRAVEL-TIME PREDICTION ; MISSING DATA ; NEURAL-NETWORKS ; VOLUME DATA ; SYSTEMS ; SIMULATION ; MANAGEMENT ; MODELS ; ISSUES ; VALUES
收录类别SCI
语种英语
项目资助者National Natural Science Foundation of China(61233001 ; Early Career Development Award of SKLMCCS ; 61203166 ; 71232006 ; 61533019)
WOS研究方向Transportation
WOS类目Transportation Science & Technology
WOS记录号WOS:000388047100012
引用统计
被引频次:193[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/13346
专题复杂系统管理与控制国家重点实验室_平行智能技术与系统团队
作者单位Chinese Acad Sci, Inst Automat, State Key Lab Management & Control Complex Syst, Beijing 100190, Peoples R China
第一作者单位中国科学院自动化研究所
推荐引用方式
GB/T 7714
Duan, Yanjie,Lv, Yisheng,Liu, Yu-Liang,et al. An efficient realization of deep learning for traffic data imputation[J]. TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES,2016,72:168-181.
APA Duan, Yanjie,Lv, Yisheng,Liu, Yu-Liang,&Wang, Fei-Yue.(2016).An efficient realization of deep learning for traffic data imputation.TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES,72,168-181.
MLA Duan, Yanjie,et al."An efficient realization of deep learning for traffic data imputation".TRANSPORTATION RESEARCH PART C-EMERGING TECHNOLOGIES 72(2016):168-181.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
An efficient realiza(824KB)期刊论文出版稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Duan, Yanjie]的文章
[Lv, Yisheng]的文章
[Liu, Yu-Liang]的文章
百度学术
百度学术中相似的文章
[Duan, Yanjie]的文章
[Lv, Yisheng]的文章
[Liu, Yu-Liang]的文章
必应学术
必应学术中相似的文章
[Duan, Yanjie]的文章
[Lv, Yisheng]的文章
[Liu, Yu-Liang]的文章
相关权益政策
暂无数据
收藏/分享
文件名: An efficient realization of deep learning for traffic data imputation.pdf
格式: Adobe PDF
此文件暂不支持浏览
所有评论 (0)
暂无评论
 

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。