Network-Scale Traffic Modeling and Forecasting with Graphical Lasso and Neural Networks
Network-Scale Traffic Modeling and Forecasting with Graphical Lasso and Neural Networks
复制标题
DOI：
10.1061/(asce)te.1943-5436.0000435
复制
发表时间：
2012-11-01
影响因子：
--
通讯作者：
Gao, Ya
中科院分区：
文献类型：
--
作者：
Sun, Shiliang;Huang, Rongqing;Gao, Ya
交通流量预测，尤其是短期情况下的交通流量预测，是智能交通系统（ITS）中的一个重要课题。本文研究短期交通流的网络规模建模和预测。首先，提出了交通流预测的单链路和多链路模型的概念。其次，将两个模型与单任务学习（STL）和多任务学习（MTL）相结合，构建了四个预测模型。多链路模型与多任务学习的结合不仅提高了实验效率，而且提高了预测精度。此外，还提出了一种新的多链接、单任务方法，将图形套索（GL）与神经网络（NN）相结合。 GL 提供了解决涉及大量变量的问题的通用方法。使用 L1 正则化，GL 利用稀疏逆协方差矩阵构建稀疏图形模型。高斯过程回归（GPR）是贝叶斯机器学习中的经典回归算法。尽管探地雷达的研究非常广泛，但探地雷达在交通流预测中的应用却很少。本文将探地雷达应用于交通流预测，显示了其潜力。通过充分的实验，对所有提出的方法进行比较，并做出总体评估。 DOI：10.1061/(ASCE)TE.1943-5436.0000435。 (C) 2012 年美国土木工程师学会。
Traffic flow forecasting, especially the short-term case, is an important topic in intelligent transportation systems (ITS). This paper researches network-scale modeling and forecasting of short-term traffic flows. First, the concepts of single-link and multilink models of traffic flow forecasting are proposed. Secondly, four prediction models are constructed by combining the two models with single-task learning (STL) and multitask learning (MTL). The combination of the multilink model and multitask learning not only improves the experimental efficiency but also improves the prediction accuracy. Moreover, a new multilink, single-task approach that combines graphical lasso (GL) with neural network (NN) is proposed. GL provides a general methodology for solving problems involving lots of variables. Using L1 regularization, GL builds a sparse graphical model, making use of the sparse inverse covariance matrix. Gaussian process regression (GPR) is a classic regression algorithm in Bayesian machine learning. Although there is wide research on GPR, there are few applications of GPR in traffic flow forecasting. In this paper, GPR is applied to traffic flow forecasting, and its potential is shown. Through sufficient experiments, all of the proposed approaches are compared, and an overall assessment is made. DOI: 10.1061/(ASCE)TE.1943-5436.0000435. (C) 2012 American Society of Civil Engineers.