A distributed EEMDN-SABiGRU model on Spark for passenger hotspot prediction

作     者：Dawen XIA Jian GENG Ruixi HUANG Bingqi SHEN Yang HU Yantao LI Huaqing LI Dawen XIA;Jian GENG;Ruixi HUANG;Bingqi SHEN;Yang HU;Yantao LI;Huaqing LI

作者机构：College of Data Science and Information EngineeringGuizhou Minzu UniversityGuiyang 550025China Department of Automotive EngineeringGuizhou Traffic Technician and Transportation CollegeGuiyang 550008China College of Computer ScienceChongqing UniversityChongqing 400044China College of Electronic and Information EngineeringSouthwest UniversityChongqing 400715China 

出 版 物：《信息与电子工程前沿:英文版》 (Frontiers of Information Technology & Electronic Engineering)

年 卷 期：2023年第24卷第9期

页      面：1316-1331页

核心收录：

学科分类：0402[教育学-心理学(可授教育学、理学学位）] 0303[法学-社会学] 08[工学] 081203[工学-计算机应用技术] 0714[理学-统计学（可授理学、经济学学位）] 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：Project supported by the National Natural Science Foundation of China(Nos.62162012,62173278,and 62072061) the Science and Technology Support Program of Guizhou Province,China(No.QKHZC2021YB531) the Natural Science Research Project of Department of Education of Guizhou Province,China(Nos.QJJ2022015 and QJJ2022047) the Science and Technology Foundation of Guizhou Province,China(Nos.QKHJCZK2022YB195,QKHJCZK2022YB197,and QKHJCZK2023YB143) the Scientific Research Platform Project of Guizhou Minzu University,China(No.GZMUSYS202104) the 7^(th) Batch High-Level Innovative Talent Project of Guizhou Province,China。 

主　　题：Passenger hotspot prediction Ensemble empirical mode decomposition(EEMD) Spatial attention mechanism Bi-directional gated recurrent unit(BiGRU) GPS trajectory Spark 

摘      要：To address the imbalance problem between supply and demand for taxis and passengers,this paper proposes a distributed ensemble empirical mode decomposition with normalization of spatial attention mechanism based bi-directional gated recurrent unit(EEMDN-SABiGRU)model on Spark for accurate passenger hotspot prediction.It focuses on reducing blind cruising costs,improving carrying efficiency,and maximizing incomes.Specifically,the EEMDN method is put forward to process the passenger hotspot data in the grid to solve the problems of non-smooth sequences and the degradation of prediction accuracy caused by excessive numerical differences,while dealing with the eigenmodal EMD.Next,a spatial attention mechanism is constructed to capture the characteristics of passenger hotspots in each grid,taking passenger boarding and alighting hotspots as weights and emphasizing the spatial regularity of passengers in the grid.Furthermore,the bi-directional GRU algorithm is merged to deal with the problem that GRU can obtain only the forward information but ignores the backward information,to improve the accuracy of feature extraction.Finally,the accurate prediction of passenger hotspots is achieved based on the EEMDN-SABiGRU model using real-world taxi GPS trajectory data in the Spark parallel computing framework.The experimental results demonstrate that based on the four datasets in the 00-grid,compared with LSTM,EMDLSTM,EEMD-LSTM,GRU,EMD-GRU,EEMD-GRU,EMDN-GRU,CNN,and BP,the mean absolute percentage error,mean absolute error,root mean square error,and maximum error values of EEMDN-SABiGRU decrease by at least 43.18%,44.91%,55.04%,and 39.33%,respectively.