A space-time delay neural network model for travel time prediction Academic Article

abstract

• 2016 Elsevier Ltd. All rights reserved. Research on space-time modelling and forecasting has focused on integrating space-time autocorrelation into statistical models to increase the accuracy of forecasting. These models include space-time autoregressive integrated moving average (STARIMA) and its various extensions. However, they are inadequate for the cases when the correlation between data is dynamic and heterogeneous, such as traffic network data. The aim of the paper is to integrate spatial and temporal autocorrelations of road traffic network by developing a novel space-time delay neural network (STDNN) model that capture the autocorrelation locally and dynamically. Validation of the space-time delay neural network is carried out using real data from London road traffic network with 22 links by comparing benchmark models such as Nave, ARIMA, and STARIMA models. Study results show that STDNN outperforms the Nave, ARIMA, and STARIMA models in prediction accuracy and has considerable advantages in travel time prediction.

authors

• Tsapakis, Ioannis

published proceedings

• ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE

author list (cited authors)

• Wang, J., Tsapakis, I., & Zhong, C.

citation count

• 47

complete list of authors

• Wang, Jiaqiu||Tsapakis, Ioannis||Zhong, Chen

publication date

• June 2016

publisher

• Elsevier  Publisher

published in

• Engineering Applications of Artificial Intelligence  Journal

keywords

• London Road Traffic Network
• Space-time Autocorrelation
• Space-time Delay Neural Network
• Travel Time Prediction

Digital Object Identifier (DOI)

• 10.1016/j.engappai.2016.02.012

start page

• 145

end page

• 160

volume

• 52

URL

• http://dx.doi.org/10.1016/j.engappai.2016.02.012