A deep learning based multitask model for network-wide traffic speed prediction
A deep learning based multitask model for network-wide traffic speed prediction
复制标题
DOI：
10.1016/j.neucom.2018.10.097
复制
发表时间：
2020-07
期刊：
影响因子：
6
通讯作者：
Kunpeng Zhang;Liang Zheng;Zijian Liu;Ning Jia
中科院分区：
文献类型：
--
作者：
Kunpeng Zhang;Liang Zheng;Zijian Liu;Ning Jia
本文提出了一种基于深度学习的多任务学习（MTL）模型来预测全网流量速度，并介绍了两种提高预测性能的方法。利用非线性格兰杰因果分析来检测各个环节之间的时空因果关系，从而为MTL模型选择信息量最大的特征。采用贝叶斯优化来以有限的计算成本调整 MTL 模型的超参数。利用出租车GPS数据在长沙市城市路网中进行了数值实验，得出以下结论。基于深度学习的MTL模型优于四种基于深度学习的单任务学习（STL）模型（即门控循环单元网络、长短期记忆网络、卷积门控循环单元网络和时域卷积网络）和其他三种经典模型（即支持向量机、k近邻和进化模糊神经网络）。非线性格兰杰因果关系检验为 MTL 模型从全网链路中选择信息特征提供了可靠的指导。与其他两种优化方法（即网格搜索和随机搜索）相比，贝叶斯优化在预算计算成本下的预测精度方面为 MTL 模型带来了更好的调整性能。综上所述，基于深度学习的 MTL 模型具有非线性 Granger 因果关系分析和贝叶斯优化，有望为大规模网络提供准确、高效的交通速度预测。
This paper proposes a deep learning based multitask learning (MTL) model to predict network-wide traffic speed, and introduces two methods to improve the prediction performance. The nonlinear Granger causality analysis is used to detect the spatiotemporal causal relationship among various links so as to select the most informative features for the MTL model. Bayesian optimization is employed to tune the hyperparameters of the MTL model with limited computational costs. Numerical experiments are carried out with taxis’ GPS data in an urban road network of Changsha, China, and some conclusions are drawn as follows. The deep learning based MTL model outperforms four deep learning based single task learning (STL) models (i.e., Gated Recurrent Units network, Long Short-term Memory network, Convolutional Gated Recurrent Units network and Temporal Convolutional Network) and three other classic models (i.e., Support Vector Machine,k-Nearest Neighbors and Evolving Fuzzy Neural Network). The nonlinear Granger causality test provides a reliable guide to select the informative features from network-wide links for the MTL model. Compared with two other optimization approaches (i.e., grid search and random search), Bayesian optimization yields a better tuning performance for the MTL model in the prediction accuracy under the budgeted computation cost. In summary, the deep learning based MTL model with nonlinear Granger causality analysis and Bayesian optimization promises the accurate and efficient traffic speed prediction for a large-scale network.