This paper presents a new class of models for predicting vehicle traffic delay in ferry terminals. Ferry service plays an important role in many cities adjacent to navigable bodies of water. Transportation agencies, port authorities, and drivers can benefit from a reliable method for ferry traffic delay prediction, which can support improved ferry service scheduling, land-based transit and ferry coordination, and proactive trip planning. In this study, vehicle traffic delay within a ferry terminal is considered to be comprised of both periodic and dynamic components. Frequency analysis is applied to confirm the presence of a consistent periodic trend. A combination method is adopted to fit the dynamic component, which assembles artificial neural network, support vector machine, and ARIMA model in a Bayesian framework. The results presented indicate that, by aggregating the output of multiple models, this model ensemble approach can lead to greater predictive accuracy in modelling ferry traffic delay.
Vehicle traffic delay prediction in ferry terminal based on Bayesian multiple models combination method
Transportmetrica A: Transport Science ; 13 , 5 ; 467-490
2017-05-28
24 pages
Article (Journal)
Electronic Resource
English
Springer Verlag | 2022
|Hybrid short-term prediction of traffic volume at ferry terminal based on data fusion
IET | 2016
|Hybrid short‐term prediction of traffic volume at ferry terminal based on data fusion
Wiley | 2016
|Finnhansa -- Ferry for passenger, vehicle and container traffic
Engineering Index Backfile | 1966
Dover car ferry terminal -- New facilities for increased traffic
Engineering Index Backfile | 1965
|