Feature selection-based approach for urban short-term travel speed prediction
Feature selection-based approach for urban short-term travel speed prediction
复制标题
基于特征选择的城市短期出行速度预测方法
DOI：
10.1049/iet-its.2017.0059
复制
发表时间：
2018-01
影响因子：
2.7
通讯作者：
Huang Helai
中科院分区：
文献类型：
--
作者：
Zheng Liang;Zhu Chuang;Zhu Ning;He Tian;Dong Ni;Huang Helai
本研究提出了一种基于特征选择的方法来识别与目标链路相关的合理时空流量模式，以提高在线预测的性能。该预测任务由两步组成：首先，提出基于混合智能算法的特征选择器（FS）来优化原始状态向量，在离线过程中经验设计状态向量，并利用优化后的状态向量进行在线预测；利用长沙市某城市路网出租车全球定位系统数据，采用三种非参数算法进行了数值实验。结果表明：(1)在优化状态向量下，预测精度提高或基本保持不变；（ii）最简单状态向量的k近邻（KNN）预测性能提高最大；（iii）虽然e-支持向量回归的性能改进受到优化状态向量的限制，但它总是优于反向传播神经网络和KNN；（iv）在相对较长的预测范围内，具有优化状态向量的三种非参数方法优于自回归综合移动平均。综上所述，该方法能够在显著降低模型复杂度的情况下提高或保证预测性能，是一种很有前途的短期交通预测方法。
This study proposes a feature selection-based approach to identify reasonable spatial-temporal traffic patterns related to the target link, in order to improve the online-prediction performance. The prediction task is composed of two steps: one hybrid intelligent algorithm-based feature selector (FS) is proposed to optimise original state vectors, which are designed empirically during the offline process and optimised state vectors are employed to carry out the online prediction. Numerical experiments by three non-parametric algorithms are conducted with taxis' global positioning system data in an urban road network of Changsha, China. It is concluded that: (i) under optimised state vectors, the prediction accuracies improve or almost maintain the same; (ii) K-nearest neighbour (KNN) with the simplest state vectors obtains the greatest improvement of prediction performance; (iii) although the performance improvement of e-support vector regression is limited with optimised state vectors, it always outperforms backward-propagation neural network and KNN; and (iv) three non-parametric approaches with optimised state vectors outperform auto-regressive integrated moving average in relatively longer prediction horizons. In conclusion, such FS-based approach is able to improve or guarantee the prediction performance under the remarkably reduced model complexity, and is a promising methodology for short-term traffic prediction.
登录
查看更多内容
DOI：
10.1201/b10345-5
发表时间：
2010-11
期刊：
Encyclopedia of Autism Spectrum Disorders
影响因子：
--
作者：
Kim-Anh Lê Cao;Z. Welham
通讯作者：
Kim-Anh Lê Cao;Z. Welham
DOI：
10.1016/j.trc.2014.01.005
发表时间：
2014-06-01
影响因子：
8.3
作者：
Vlahogianni, Eleni I.;Karlaftis, Matthew G.;Golias, John C.
通讯作者：
Golias, John C.
影响因子：
9.6
作者：
Yao Baozhen;Chen Chao;Cao Qingda;Jin Lu;Zhang Mingheng;Zhu Hanbing;Yu Bin
通讯作者：
Yu Bin
影响因子：
--
作者：
S. Yun;S. Namkoong;J. Rho;S.-W. Shin;J.-U. Choi
通讯作者：
S. Yun;S. Namkoong;J. Rho;S.-W. Shin;J.-U. Choi
影响因子：
--
作者：
SHANNON, CE
通讯作者：
SHANNON, CE