基于多周期组件时空神经网络的路网通行速度预测

交通运输系统工程与信息 ›› 2021, Vol. 21 ›› Issue (3): 112-119.

基于多周期组件时空神经网络的路网通行速度预测

杨建喜^a，郁超顺^b，李韧^*a，杜利芳^b，蒋仕新^a，王笛^a

重庆交通大学，a. 信息科学与工程学院；b. 交通运输学院，重庆 400074

收稿日期:2021-02-28 修回日期:2021-04-06 出版日期:2021-06-25 发布日期:2021-06-25
作者简介:杨建喜(1977- )，男，宁夏青铜峡人，教授。
基金资助:
国家自然科学基金/National Natural Science Foundation of China（62003063）；重庆市自然科学基金/Natural Science Foundation of Chongqing, China (cstc2020jcyj-msxmX0047)；重庆市教委科学技术研究项目/ Science and Technology Research Program of Chongqing Municipal Education Commission (KJZD-M202000702)。

Traffic Network Speed Prediction via Multi-periodic-component Spatial-temporal Neural Network

YANG Jian-xi^a , YU Chao-shun^b , LI Ren^*a, DU Li-fang^b , JIANG Shi-xin^a , WANG Di^a

a. School of Information Science and Engineering; b. School of Traffic and Transportation, Chongqing Jiaotong University, Chongqing 400074, China

Received:2021-02-28 Revised:2021-04-06 Online:2021-06-25 Published:2021-06-25

摘要/Abstract

摘要：

针对当前路网通行速度预测方法存在的中长周期预测准确性和稳定性不足、自适应路网拓扑空间关系建模能力有待进一步提升等问题，以多尺度卷积算子及门控循环单元为核心单元，提出一种面向路网通行速度预测任务的多周期组件时空神经网络模型。首先，根据路网交通感知数据的周期特性，将其规约为周、日和近期这3种不同粒度的时间-空间-特征三维矩阵，并输入至3个共享网络结构的周期组件。其次，在每部分组件中，利用多尺度卷积核捕获多因素非线性相关性与不同空间视野大小的路网节点空间相关性。然后，对每个路网节点的时序特征使用门控循环单元提取交通数据长时依赖关系，引入残差学习框架，提高网络训练效率并防止梯度弥散。最后，自适应加权融合通过预测卷积层的每部分周期组件预测结果生成预测时段内路网交通通行速度。为验证所提方法的有效性，基于两个公开的交通状态数据集进行实验分析，并选取当前主流的深度神经网络模型作为对比基线模型。结果表明，所提方法在可接受的执行时间内，在两个数据集上平均绝对误差、平均平方误差和平均绝对百分比误差分别为 2.55、3.94 和 10.75%，1.57、3.52和3.44%，在预测准确性与中长时多步预测稳定性方面均优于其他基准方法。

关键词: 智能交通, 多周期组件时空神经网络, 卷积神经网络, 通行速度预测, 门控循环单元

Abstract:

To overcome the drawbacks of current traffic network speed prediction methods, such as the lack of accuracy and stability for medium and long period prediction, as well as the low capability of self- adaptive traffic network topological modeling, this paper proposes a traffic network speed prediction approach via a novel multi- periodiccomponent spatial-temporal neural network which takes multi-scale convolutional operators and gated recurrent units as its building blocks. Firstly, according to the periodic characteristic of traffic network speed, the raw data is transformed into a three-dimensional matrix corresponded to the weekly period, daily period, and recent period before inputting to the period component of the proposed model. Secondly, the multi-scale convolutional kernels are used to capture the spatial correlation between the multi- factor nonlinear correlation and the traffic network nodes with a different spatial field of view in each period component. And then, the gated recurrent units are employed to extract the long-term dependency of traffic data. The residual learning framework is also utilized to improve the training efficiency and prevent gradient dispersion. Finally, the traffic speed prediction results related to each period component via the prediction convolutional unit are adaptively weighted and fused. In order to verify the effectiveness of the proposed model, two public datasets are used for experimental analysis, while the mainstream deep neural network models related to the task are compared. The experimental results show that the average absolute error, the average square error and the average absolute percentage error of the proposed model are 2.55, 3.94 and 10.75%, 1.57, 3.52 and 3.44%, respectively. The proposed model outperforms other baseline models in terms of prediction accuracy and long- term prediction stability.

Key words: intelligent transportation, multi-periodic-component spatial-temporal neural networks, convolutional neural network, traffic network speed prediction, gated recurrent unit

中图分类号:

U495

杨建喜，郁超顺，李韧，杜利芳，蒋仕新，王笛. 基于多周期组件时空神经网络的路网通行速度预测[J]. 交通运输系统工程与信息, 2021, 21(3): 112-119.

YANG Jian-xi,YU Chao-shun,LI Ren, DU Li-fang,JIANG Shi-xin,WANG Di. Traffic Network Speed Prediction via Multi-periodic-component Spatial-temporal Neural Network[J]. Journal of Transportation Systems Engineering and Information Technology, 2021, 21(3): 112-119.

导出引用管理器 EndNote|Ris|BibTeX

链接本文: http://www.tseit.org.cn/CN/abstract/abstract30250.shtml

http://www.tseit.org.cn/CN/Y2021/V21/I3/112

参考文献

[1] 陆化普, 孙智源, 屈闻聪. 大数据及其在城市智能交通系统中的应用综述[J]. 交通运输系统工程与信息, 2015, 15(5): 45-52. [LU H P, SUN Z Y, QU W C. Big data and its applications in urban intelligent transportation system[J]. Journal of Transportation Systems Engineering and Information Technology, 2015, 15(5): 45-52. ]

[2] VLAHOGIANNI E I, KARLAFTIS M G, GOLIAS J C. Short- term traffic forecasting: Where we are and where we're going[J]. Transportation Research Part C: Emerging Technologies, 2014, 43: 3-19.

[3] 刘小明, 田玉林, 唐少虎, 等. 基于时延特性建模的多断面短时交通流预测[J]. 交通运输系统工程与信息, 2020, 20(3): 54-60. [LIU X M, TIAN Y L, TANG S H, et al. Short- term traffic flow prediction of multisections based on time-delay modeling[J]. Journal of Transportation Systems Engineering and Information Technology, 2020, 20(3): 54-60.]

[4] LIU Y, ZHENG H, FENG X, et al. Short-term traffic flow prediction with Conv-LSTM[C]//2017 9th International Conference on Wireless Communications and Signal Processing (WCSP), IEEE, 2017: 1-6.

[5] 冯宁, 郭晟楠, 宋超, 等. 面向交通流量预测的多组件时空图卷积网络[J]. 软件学报, 2019, 30(3): 759-769. [FENG N, GUO S N, SONG C, et al. Multi- component spatial-temporal graph convolution networks for traffic flow forecasting[J]. Journal of Software, 2019, 30(3): 759- 769. ]

[6] GUO S, LIN Y, FENG N, et al. Attention based spatialtemporal graph convolutional networks for traffic flow forecasting[C]//Proceedings of the AAAI Conference on Artificial Intelligence, 2019, 33(1): 922-929.

[7] 胡启洲, 孙煦. 基于多维联系数的城市路网交通拥堵态势监控模型[J]. 中国公路学报, 2013, 26(6): 143- 149. [HU Q Z, SUN X. Model for traffic congestion state monitor in urban road network based on multi-dimension connection number[J]. China Journal of Highway and Transport, 2013, 26(6): 143-149. ]

[8] MA X, TAO Z, WANG Y, et al. Long short-term memory neural network for traffic speed prediction using remote microwave sensor data[J]. Transportation Research Part C: Emerging Technologies, 2015, 54: 187-197.

[9] MA X, DAI Z, HE Z, et al. Learning traffic as images: Adeep convolutional neural network for large-scale transportation network speed prediction[J]. Sensors, 2017, 17(4): 81.

[10] LIU Q, WANG B, ZHU Y. Short- term traffic speed forecasting based on attention convolutional neural network for arterials[J]. Computer-Aided Civil and Infrastructure Engineering, 2018, 33(11): 999-1016.

[11] ZHAO L, SONG Y, ZHANG C, et al. T-gcn: A temporal graph convolutional network for traffic prediction[J]. IEEE Transactions on Intelligent Transportation Systems, 2019, 21(9): 3848-3858.

[12] HE K, ZHANG X, REN S, et al. Deep residual learning for image recognition[C]//Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016: 770-778.

[13] ZHAO R, WANG D, YAN R, et al. Machine health monitoring using local feature-based gated recurrent unit networks[J]. IEEE Transactions on Industrial Electronics, 2017, 65(2): 1539-1548.

[14] 滴滴出行科技有限公司. 滴滴出行“盖亚”数据开放计划 [EB/OL]. (2019- 10- 19) [2021- 01- 24]. https://gaia. didichuxing.com. [Didi Technology Co, Ltd. Data source: Didi Chuxing GAIA initiative[EB/OL]. (2019- 10- 19) [2021-01-24]. https://gaia.didichuxing.com.]

[15] CHEN C, PETTY K, SKABARDONIS A, et al. Freeway performance measurement system: Mining loop detector data[J]. Transportation Research Record, 2001, 1748(1): 96-102.