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. 地理科学与资源研究所
  3. 中国科学院地理科学与资源研究所
Prediction of human activity intensity using the interactions in physical and social spaces through graph convolutional networks

文献类型：期刊论文

作者Li, Mingxiao1,2,6,7; Gao, Song2; Lu, Feng3,5,7; Liu, Kang4,7; Zhang, Hengcai7; Tu, Wei1,6
刊名INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE
出版日期2021-04-21
页码28
ISSN号1365-8816
关键词Human activity intensity prediction graph convolutional networks social interaction mobile phone data human mobility
DOI10.1080/13658816.2021.1912347
通讯作者Gao, Song(song.gao@wisc.edu) ; Tu, Wei(tuwei@szu.edu.cn)
英文摘要Dynamic human activity intensity information is of great importance in many location-based applications. However, two limitations remain in the prediction of human activity intensity. First, it is hard to learn the spatial interaction patterns across scales for predicting human activities. Second, social interaction can help model the activity intensity variation but is rarely considered in the existing literature. To mitigate these limitations, we proposed a novel dynamic activity intensity prediction method with deep learning on graphs using the interactions in both physical and social spaces. In this method, the physical interactions and social interactions between spatial units were integrated into a fused graph convolutional network to model multi-type spatial interaction patterns. The future activity intensity variation was predicted by combining the spatial interaction pattern and the temporal pattern of activity intensity series. The method was verified with a country-scale anonymized mobile phone dataset. The results demonstrated that our proposed deep learning method with combining graph convolutional networks and recurrent neural networks outperformed other baseline approaches. This method enables dynamic human activity intensity prediction from a more spatially and socially integrated perspective, which helps improve the performance of modeling human dynamics.
资助项目National Key Research and Development Program[2016YFB0502104] ; Guangdong Province Basic and Applied Basic Research Fund Project[2020A1515111166] ; State Key Laboratory of Resources and Environmental Information System ; National Natural Science Foundation of China[41771436] ; National Natural Science Foundation of China[41901391] ; National Natural Science Foundation of China[42071360] ; Shenzhen Basic Research Program[JCYJ20190807163001783] ; National Science Foundation of United States[1940091] ; Wisconsin Alumni Research Foundation
WOS研究方向Computer Science ; Geography ; Physical Geography ; Information Science & Library Science
语种英语
出版者TAYLOR & FRANCIS LTD
WOS记录号WOS:000641781900001
资助机构National Key Research and Development Program ; Guangdong Province Basic and Applied Basic Research Fund Project ; State Key Laboratory of Resources and Environmental Information System ; National Natural Science Foundation of China ; Shenzhen Basic Research Program ; National Science Foundation of United States ; Wisconsin Alumni Research Foundation
源URL[http://ir.igsnrr.ac.cn/handle/311030/161708]  
专题中国科学院地理科学与资源研究所
通讯作者Gao, Song; Tu, Wei
作者单位1.Shenzhen Univ, Res Inst Smart Cities, Shenzhen, Peoples R China
2.Univ Wisconsin, Dept Geog, Geospatial Data Sci Lab, Madison, WI 53706 USA
3.Fuzhou Univ, Acad Digital China, Fuzhou, Peoples R China
4.Chinese Acad Sci, Shenzhen Inst Adv Technol, Shenzhen, Peoples R China
5.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing, Peoples R China
6.Shenzhen Univ, Shenzhen Key Lab Spatial Informat Smart Sensing &, Guangdong Lab Artificial Intelligence & Digital E, Guangdong Key Lab Urban Informat, Shenzhen, Peoples R China
7.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing, Peoples R China
推荐引用方式
GB/T 7714		 Li, Mingxiao,Gao, Song,Lu, Feng,et al. Prediction of human activity intensity using the interactions in physical and social spaces through graph convolutional networks[J]. INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,2021:28.
APA Li, Mingxiao,Gao, Song,Lu, Feng,Liu, Kang,Zhang, Hengcai,&Tu, Wei.(2021).Prediction of human activity intensity using the interactions in physical and social spaces through graph convolutional networks.INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE,28.
MLA Li, Mingxiao,et al."Prediction of human activity intensity using the interactions in physical and social spaces through graph convolutional networks".INTERNATIONAL JOURNAL OF GEOGRAPHICAL INFORMATION SCIENCE (2021):28.

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。