Attention based simplified deep residual network for citywide crowd flows prediction
作者机构:School of Data and Computer ScienceSun Yat-Sen UniversityGuangzhou510006China Guangdong Key Laboratory of Big Data Analysis and ProcessingGuangzhou510006China
出 版 物:《Frontiers of Computer Science》 (中国计算机科学前沿(英文版))
年 卷 期:2021年第15卷第2期
页 面:51-62页
核心收录:
学科分类:0810[工学-信息与通信工程] 0808[工学-电气工程] 081203[工学-计算机应用技术] 08[工学] 0835[工学-软件工程] 0701[理学-数学] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:This work was supported by the National Nature Science Foundation of China(NSFC Grant Nos.61572537 U1501252)
主 题:crowd flows prediction spatio-temporal data mining attention
摘 要:Crowd flows prediction is an important problem of urban computing whose goal is to predict the number of incoming and outgoing people of regions in the *** practice,emergency applications often require less training ***,there is a little work on how to obtain good prediction performance with less training *** this paper,we propose a simplified deep residual network for our *** using the simplified deep residual network,we can obtain not only less training time but also competitive prediction performance compared with the existing similar ***,we adopt the spatio-temporal attention mechanism to further improve the simplified deep residual network with reasonable additional time *** on the real datasets,we construct a series of experiments compared with the existing *** experimental results confirm the efficiency of our proposed methods.