Journal of Computer Applications ›› 2021, Vol. 41 ›› Issue (3): 875-880.DOI: 10.11772/j.issn.1001-9081.2020060467

Special Issue: 前沿与综合应用

• Frontier and comprehensive applications • Previous Articles     Next Articles

LSTM and artificial neural network for urban bus travel time prediction based on spatiotemporal eigenvectors

ZHANG Xinhuan1, LIU Hongjie2, SHI Junqing1, MAO Chengyuan1, MENG Guolian1   

  1. 1. Road and Traffic Engineering Research Center, Zhejiang Normal University, Jinhua Zhejiang 321004, China;
    2. School of Electronic and Information Engineering, Xi'an Jiaotong University, Xi'an Shaanxi 710049, China
  • Received:2020-06-18 Revised:2020-10-12 Online:2021-03-10 Published:2020-12-17
  • Supported by:
    This work is partially supported by Project of the Zhejiang Provincial Educational Committee (Y201738488), the Zhejiang Provincial Natural Science Foundation (LY18G010009, LY18G030021), the Scientific Research Start Foundation for the Returned Scholars, Ministry of Education of China (ZC304012027).

基于时空特征向量的长短期记忆人工神经网络的城市公交旅行时间预测

张欣环1, 刘宏杰2, 施俊庆1, 毛程远1, 孟国连1   

  1. 1. 浙江师范大学 道路与交通工程研究中心, 浙江 金华 321004;
    2. 西安交通大学 电子信息工程学院, 西安 710049
  • 通讯作者: 刘宏杰
  • 作者简介:张欣环(1977-),女,陕西乾县人,讲师,博士,主要研究方向:城市公共交通系统评价与优化、网联自动车路系统;刘宏杰(1988-),男,陕西渭南人,博士研究生,主要研究方向:智慧交通、人工智能、机器学习、网联自动车路系统;施俊庆(1985-),男,浙江永康人,副教授,博士,主要研究方向:智能交通、交通流理论、网联自动车路系统;毛程远(1982-),男,浙江杭州人,讲师,博士,主要研究方向:城市交通规划与管理、交通流理论;孟国连(1986-),女,山东潍坊人,实验师,博士研究生,主要研究方向:城市交通规划与管理、交通流理论。
  • 基金资助:
    浙江省教育厅项目(Y201738488);浙江省自然科学基金资助项目(LY18G010009,LY18G030021);教育部留学回国人员科研启动基金资助项目(ZC304012027)。

Abstract: Aiming at the problem that "with the increase of the prediction distance, the prediction of travel time becomes more and more difficult", a comprehensive prediction model of Long Short Term Memory (LSTM) and Artificial Neural Network (ANN) based on spatiotemporal eigenvectors was proposed. Firstly, 24 hours were segmented into 288 time slices to generate time eigenvectors. Secondly, the LSTM time window model was established based on the time slices. This model was able to solve the window movement problem of long-time prediction. Thirdly, the bus line was divided into multiple space slices and the average velocity of the current space slice was used as the instantaneous velocity. At the same time, the predicted time of each space slice would be used as the spatial eigenvector and sent to the new hybrid neural network model named LSTM-A (Long Short Term Memory Artificial neural network). This model combined with the advantages of the two prediction models and solved the problem of bus travel time prediction. Finally, based on the experimental dataset, experiments and tests were carried out:the prediction problem between bus stations was divided into sub-problems of line slice prediction, and the concept of real-time calculation was introduced to each related sub-problem, so as to avoid the prediction error caused by complex road conditions. Experimental results show that the proposed algorithm is superior to single neural network models in both accuracy and applicability. In conclusion, the proposed new hybrid neural network model LSTM-A can realize the long-distance arrival time prediction from the dimension of time feature and the short-distance arrival time prediction from the dimension of spatial feature, thus effectively solving the problem of urban bus travel time prediction and avoiding the remote dependency and error accumulation of buses.

Key words: urban traffic, Long Short-Term Memory (LSTM) network, Artificial Neural Network (ANN), Long Short-Term Memory Artificial neural network (LSTM-A), travel time prediction

摘要: 针对“随着预测距离的增加,旅行时间预测的难度加大”的问题,提出了一种基于时空特征向量的长短期记忆(LSTM)和人工神经网络(ANN)的综合预测模型。首先,将24 h切分为288个时间切片,以生成时间特征向量;然后,基于时间切片建立LSTM时间窗口模型,该模型可解决长期预测的窗口移动问题;其次,将公交线路切分为多个空间切片,并使用当前空间切片的共同平均速度作为瞬时速度,同时将每个空间切片的预测时间用作空间特征向量,并将其发送到新型的混合神经网络模型LSTM-A中,该模型结合两种预测模型的优点并解决了公交旅行时间预测问题;最后,基于实验数据集进行了实验和测试:将公交站点间的预测问题划分为线路切片预测子问题,并针对每个相关的子问题引入了实时计算的概念,从而避免了复杂路况带来的预测误差。实验结果表明,所提算法在准确性、适用性方面均优于单个神经网络模型。综上,所提的新型混合神经网络模型LSTM-A能从时间特征的维度实现长距离到站预测、从空间特征的维度实现短距离到站预测,从而有效地解决了城市公交旅行时间预测问题,避免了公交车辆的远程依赖和错误积累。

关键词: 城市交通, 长短期记忆网络, 人工神经网络, 长短期记忆人工神经网络, 旅行时间预测

CLC Number: