基于混合卷积-递归神经网络的共享单车出入流预测  

Prediction of Shared Bicycle Inflow and Outflow Based on Conv3D-GRU Neural Network

作　　者：贾现广[1] 刘欢 冯超琴 吕英英[2] JIA Xian-guang;LIU Huan;FENG Chao-qin;LÜYing-ying(School of Traffic Engineering,Kunming University of Science and Technology,Kunming 650500,China;School of Information Engineering and Automation,Kunming University of Science and Technology,Kunming 650500,China)

机构地区：[1]昆明理工大学交通工程学院,昆明650500 [2]昆明理工大学信息工程与自动化学院,昆明650500

出　　处：《科学技术与工程》2025年第5期2127-2134,共8页Science Technology and Engineering

基　　金：国家自然科学基金(71961012)。

摘　　要：准确预测共享单车流量有助于优化共享单车的供需平衡,提高城市居民的出行便利性。为解决共享单车预测准确性不高以及时空特性捕捉不充分的问题,提出了一种混合卷积-递归神经网络(hybrid convolutional-recurrent neural network)Conv3D-GRU模型,采用芝加哥2022全年共享单车数据进行实验,并与三维卷积神经网络3D-CNN(3D convolutional neural network)模型和卷积长短期记忆网络(Convolutional long short-term memory,ConvLSTM)的预测结果进行比较,使用均方根误差(root mean squared error,RMSE)、平均绝对误差(mean absolute error,MAE)、决定系数R^(2)评估模型性能。实验结果表明,Conv3D-GRU相较于3D-CNN和ConvLSTM模型,在RMSE、MAE以及R^(2)上分别提高了3.25%、4.90%、1.14%和11.94%、13.70%、2.46%,可见Conv3D-GRU模型的预测误差小,预测精度高,能够有效和可靠地适用于共享单车出入流的预测。Accurately predicting bike-sharing flow is essential for optimizing the supply-demand balance of shared bikes and enhancing urban residents'travel convenience.To address the issues of low prediction accuracy and insufficient capture of spatiotemporal characteristics in bike-sharing flow prediction,a hybrid convolutional-recurrent neural network(Conv3D-GRU)model was proposed.Using Chicago's 2022 full-year bike-sharing data,experiments were conducted,and the results were compared with those of the 3D convolutional neural network(3D-CNN)model and the convolutional long short-term memory(ConvLSTM)model.The model performance was evaluated using root mean squared error(RMSE),mean absolute error(MAE),and the coefficient of determination(R^(2)).Experimental results show that compared with the 3D-CNN and ConvLSTM models,Conv3D-GRU is improved by 3.25%,4.90%,1.14%and 11.94%,13.70%and 2.46%on RMSE,MAE and R^(2),respectively.This demonstrates that the Conv3D-GRU model has lower prediction errors and higher prediction accuracy,making it an effective and reliable approach for forecasting bike-sharing inflow and outflow.

关 键 词：城市交通 出入流预测 Conv3D-GRU 共享单车 时空特性 

分 类 号：U484[交通运输工程—载运工具运用工程]