
Feature selection‐based approach for urban short‐term travel speed prediction
Author(s) -
Zheng Liang,
Zhu Chuang,
Zhu Ning,
He Tian,
Dong Ni,
Huang Helai
Publication year - 2018
Publication title -
iet intelligent transport systems
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.579
H-Index - 45
eISSN - 1751-9578
pISSN - 1751-956X
DOI - 10.1049/iet-its.2017.0059
Subject(s) - computer science , artificial neural network , feature selection , data mining , support vector machine , feature (linguistics) , feature vector , parametric statistics , term (time) , artificial intelligence , process (computing) , machine learning , pattern recognition (psychology) , mathematics , philosophy , statistics , linguistics , physics , quantum mechanics , operating system
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 ɛ‐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.