@article{Xie:207231,
      recid = {207231},
      author = {Xie, Yuanchang and Huynh, Nathan},
      title = {Kernel-Based Machine Learning Methods for Modeling Daily  Truck Volume at Seaport Terminals},
      address = {2010-03},
      number = {1430-2016-118676},
      pages = {19},
      year = {2010},
      abstract = {The heavy truck traffic generated by major seaports can  have huge impacts on local and regional transportation  networks. Transportation agencies, port authorities, and  terminal operators have a need to know in advance the truck  traffic in order to accommodate them accordingly. Several  previous studies have developed models for predicting the  daily truck traffic at seaport terminals using terminal  operations data. In this study, two kernel-based supervised  machine learning methods are introduced for the same  purpose: Gaussian Processes (GP) and ε-Support Vector  Machines (ε-SVMs). They are compared against the Multilayer  Feed-forward Neural Networks (MLFNNN) model, which was used  in past studies, to provide a comparison of their relative  performance. The model development is done using the data  from Bayport and Barbours Cut (BCT) container terminals at  the Port of Houston. Truck trips generated by import and  export activities at the two terminals are investigated  separately, generating four sets of data for model testing  and comparison. For all test datasets, the GP and ε-SVMs  models perform equally well and their prediction  performance compares favorably to that of the MLFNN model.  On a practical note, the GP and ε-SVMs models require less  effort in model fitting compared to the MLFNN model. The  strong performance of the GP and ε-SVMs models relative to  the commonly used MLFNN model suggest that they can be  considered as alternative approaches to the MLFNN in other  predictive applications.},
      url = {http://ageconsearch.umn.edu/record/207231},
      doi = {https://doi.org/10.22004/ag.econ.207231},
}