Forecast of Seaport Cargo Volume Based on Artificial Neural Network Model

In this paper two artificial neural network models were explored to predict future cargo volume of Dalian seaport. Factors affecting cargo volume were carefully identified, categorized as input and output variables and then entered into the forecast models that generated a projection of the cargo volume. First the author used time series methods predicting the future results of the input variables. Then the author utilized a radial base function neural network as the basic model. Finally, the author combined this radial base neural network and a linear function to be a generalized regression neural network, which generated the results of the cargo volume. The results indicate that the Dalian seaport cargo volume will increase in the near future and local economics that depends heavily on sea transportation will improve rapidly.

• Record URL:
  https://doi.org/10.1061/41139(387)499
• Availability:
  • Find a library where document is available. Order URL: http://worldcat.org/isbn/9780784411391
• Supplemental Notes:
  • © 2010 American Society of Civil Engineers.
• Corporate Authors:

  American Society of Civil Engineers

  1801 Alexander Bell Drive
  Reston, VA  United States  20191-4400
• Authors:
  • Lu, Yubo
• Conference:
  • International Conference of Logistics Engineering and Management (ICLEM) 2010
  • Location: Chengdu , China
  • Date: 2010-10-8 to 2010-10-10
• Publication Date: 2010-9

Language

• English

Media Info

• Media Type: Web
• Features: References;
• Pagination: pp 3577-3583
• Monograph Title: ICLEM 2010: Logistics For Sustained Economic Development: Infrastructure, Information, Integration

Subject/Index Terms

• TRT Terms: Cargo ships; Forecasting; Freight transportation; Logistics; Neural networks; Seaports; Time series analysis; Traffic volume
• Geographic Terms: Dalian (China)
• Subject Areas: Freight Transportation; Marine Transportation; Planning and Forecasting; I72: Traffic and Transport Planning;

Filing Info

• Accession Number: 01525656
• Record Type: Publication
• ISBN: 9780784411391
• Files: TRIS, ASCE
• Created Date: May 28 2014 3:21PM