Open AccessShort‐term forecasting of available parking space using wavelet neural network model
Author(s) -
Ji Yanjie,
Tang Dounan,
Blythe Phil,
Guo Weihong,
Wang Wei
Publication year - 2015
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.2013.0184
Subject(s) - mean squared error , artificial neural network , robustness (evolution) , computer science , term (time) , data mining , machine learning , statistics , mathematics , biochemistry , chemistry , physics , quantum mechanics , gene
The technique to forecast available parking spaces (APSs) is the foundation theory of parking guidance information systems (PGISs). This study utilises data collected on parking availability at several off‐street parking garages in Newcastle upon Tyne, England, to investigate the changing characteristics of APS. Using these baseline data the research reported here aims to build up a short‐term APS forecasting model and applies the wavelet neural network (WNN) method to the PGIS problem. After selecting optimal preferences, including training set size, delay time and embedding dimension, the APS short‐term forecasting model based on WNN is built and tested using the real‐world dataset. By experimental tests conducted using the same dataset, WNN's prediction performance is compared with the largest Lyapunov exponents (LEs) method in the aspects of accuracy, efficiency and robustness. It is found that WNN prevails through a more efficient structure and employs, barely half of the computational cost compared to the largest LEs method, which could be significant if applied to real‐time operation. Moreover, WNN enjoys a more accurate performance, for its prediction average mean square error (MSE) is 6.4 ± 3.1 (in a parking building with 492 parking lots) for workdays and 8.5 ± 6.2 for weekends, compared to the MSE of largest LEs method, 18.7 and 29.0, respectively.