T1 A Clustering-Based Hybrid Support Vector Regression Model to Predict Container Volume at Seaport Sanitary Facilities
A1 Ruiz Aguilar, Juan Jesús
A1 Moscoso López, José Antonio
A1 Urda Muñoz, Daniel
A1 González Enrique, Francisco Javier
A1 Turias Domínguez, Ignacio J.
K1 Maritime transport
K1 Container forecasting
K1 Support vector regression
K1 Self-organizing maps
K1 Machine learning
K1 Hybrid models
K1 Informática
K1 Computer science
AB An accurate prediction of freight volume at the sanitary facilities of seaports is a key factorto improve planning operations and resource allocation. This study proposes a hybrid approachto forecast container volume at the sanitary facilities of a seaport. The methodology consists of athree-step procedure, combining the strengths of linear and non-linear models and the capabilityof a clustering technique. First, a self-organizing map (SOM) is used to decompose the time seriesinto smaller clusters easier to predict. Second, a seasonal autoregressive integrated moving averages(SARIMA) model is applied in each cluster in order to obtain predicted values and residuals ofeach cluster. These values are finally used as inputs of a support vector regression (SVR) modeltogether with the historical data of the cluster. The final prediction result integrates the predictionresults of each cluster. The experimental results showed that the proposed model provided accurateprediction results and outperforms the rest of the models tested. The proposed model can be used asan automatic decision-making tool by seaport management due to its capacity to plan resources inadvance, avoiding congestion and time delays.
PB MDPI
YR 2020
FD 2020-11
LK http://hdl.handle.net/10259/7250
UL http://hdl.handle.net/10259/7250
LA eng
NO This research was funded by MICINN (Ministerio de Ciencia e Innovación-Spain), grant number RTI2018-098160-B-I00.
DS Repositorio Institucional de la Universidad de Burgos
RD 07-may-2024