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. 遥感图像处理团队
AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction

文献类型：期刊论文

作者Fang, Shen2,3; Zhang, Chunxia1,2; Xiang, Shiming3; Pan, Chunhong3
刊名IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS
出版日期2022-12-16
页码15
关键词Deep learning neural architecture search graph convolution meta-learning traffic flow prediction
ISSN号1524-9050
DOI10.1109/TITS.2022.3225553
通讯作者Xiang, Shiming(smxiang@nlpr.ia.ac.cn)
英文摘要Recently the research of traffic flow prediction with deep learning framework has be largely developed, whereas most current methods are still faced with the following shortcomings. For spatial feature extraction, studies have shown that both local and non-local correlations exist on traffic networks. Considering the temporal dependencies, short-term impending and longer periodic components are two most critical patterns of traffic data, which further provide different information for the prediction task. Furthermore, multi-source heterogeneous external data, which naturally holds semantic gap with traffic data, also have impact on traffic flow. To solve the above problems, this paper proposes an AutoMSNet (Multi-Source Spatio-Temporal Network via Automatic neural architecture search). The AutoMSNet is composed of an encoder-decoder structure. The encoder takes neighboring data as inputs, while the decoder captures long-term periodic patterns. Thus, different functions of two temporal features are simultaneously extracted. Moreover, a neural architecture search space is designed for spatial feature extraction. Through architecture search technique, graph convolutions with different receptive fields are automatically selected and combined to form an optimal module structure. Therefore, both local and non-local spatial features can be adaptively captured. Besides, a meta learning feature fusion strategy is proposed to integrate external data, which can alleviate the semantic gap between different data sources. Extensive experiments on three real-world traffic datasets evaluate the superiority of the proposed model.
WOS关键词KALMAN FILTER ; DEEP
资助项目National Key Research and Development Program of China[2018AAA0100400] ; National Natural Science Foundation of China[91646207] ; National Natural Science Foundation of China[62072039] ; National Natural Science Foundation of China[62076242]
WOS研究方向Engineering ; Transportation
语种英语
WOS记录号WOS:000903350700001
出版者IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
资助机构National Key Research and Development Program of China ; National Natural Science Foundation of China
源URL[http://ir.ia.ac.cn/handle/173211/51021]  
专题自动化研究所_模式识别国家重点实验室_遥感图像处理团队
通讯作者Xiang, Shiming
作者单位1.Beijing Inst Technol, Sch Comp Sci & Technol, Beijing 100081, Peoples R China
2.Univ Chinese Acad Sci, Sch Artificial Intelligence, Beijing 101408, Peoples R China
3.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714		 Fang, Shen,Zhang, Chunxia,Xiang, Shiming,et al. AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction[J]. IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,2022:15.
APA Fang, Shen,Zhang, Chunxia,Xiang, Shiming,&Pan, Chunhong.(2022).AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction.IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS,15.
MLA Fang, Shen,et al."AutoMSNet: Multi-Source Spatio-Temporal Network via Automatic Neural Architecture Search for Traffic Flow Prediction".IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS (2022):15.

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。