Attention based simplified deep residual network for citywide crowd flows prediction

作     者：Genan DAI Xiaoyang HU Youming GE Zhiqing NING Yubao LIU Genan DAI;Xiaoyang HU;Youming GE;Zhiqing NING;Yubao LIU

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.