面向分布式EMDN-GRU模型的乘客等待时间预测  

Passenger Waiting Time Prediction for Distributed EMDN-GRU Model

作　　者：白宇 郑永玲 蒋顺英 杨楠 BAI Yu;ZHENG Yongling;JIANG Shunying;YANG Nan(School of Data Science and Information Engineering,Guizhou Minzu University,Guiyang 550025,China)

机构地区：[1]贵州民族大学数据科学与信息工程学院,贵州贵阳550025

出　　处：《现代信息科技》2020年第21期59-65,70,共8页Modern Information Technology

摘　　要：面对移动轨迹大数据难以使用传统数据处理平台进行处理,乘客等待时间难以预测,以及GPS数据无法明确给出车辆行驶方向的问题。文章提出一种基于Spark的坐标轴车辆方向判别法,并建立了EMDN-GRU模型对乘客等待时间进行预测,并且与LSTM、GRU、EMD-LSTM与EMD-GRU进行比较。案例研究表明:EMDN-GRU模型明显优于比较模型,其中MAPE最少提高了8.183%,最大提高了25.729%;在乘客等待时间预测方面具有良好的效果。Facing with the problems that it is difficult to use traditional data processing platforms to process big data of moving trajectories,it is difficult to predict the waiting time of passengers,and GPS data cannot clearly give the vehicle driving direction.The article proposes a method for judging the vehicle direction of the coordinate axis based on Spark,and establishes the EMDN-GRU model to predict passenger waiting time,and compares it with LSTM,GRU,EMD-LSTM and EMD-GRU.The case study shows that the EMDN-GRU model is significantly better than the comparison model.The MAPE is increased by at least 8.183%and the largest by 25.729%;it has a good effect on passenger waiting time prediction.

关 键 词：等待时间 EMD算法 GRU SPARK 车辆方向 

分 类 号：O211.61[理学—概率论与数理统计] TP301.6[理学—数学]