Container throughput time series forecasting using a hybrid approach
- Author
- Xi Zha, Yi Chai, Frank Witlox (UGent) and Le Ma
- Organization
- Abstract
- This paper proposed a novel two-stage hybrid container throughput forecasting model. Time series in reality exhibits both linear and nonlinear characteristics and individual models are not able to describe the two features simultaneously. Therefore, we combine linear model SARIMA (seasonal autoregressive integrated moving average) and nonlinear model ANN (artificial neural network). In order to break through the limitations of traditional hybrid models, based on the identified parameters of SARIMA in first stage, the structures of several ANN in second stage could be decided. Finally, we validate the proposed hybrid model 5 performs best with case study in Shanghai port.
- Keywords
- Port throughput forecasting, SARIMA, ANN, Hybrid models
Downloads
-
(...).pdf
- full text (Published version)
- |
- UGent only
- |
- |
- 398.35 KB
Citation
Please use this url to cite or link to this publication: http://hdl.handle.net/1854/LU-01M1EKNYHES11PDPF4XA3964YR
- MLA
- Zha, Xi, et al. “Container Throughput Time Series Forecasting Using a Hybrid Approach.” PROCEEDINGS OF THE 2015 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL 1, edited by Y Jia et al., vol. 359, Springer, 2016, pp. 639–50, doi:10.1007/978-3-662-48386-2_65.
- APA
- Zha, X., Chai, Y., Witlox, F., & Ma, L. (2016). Container throughput time series forecasting using a hybrid approach. In Y. Jia, J. Du, H. Li, & W. Zhang (Eds.), PROCEEDINGS OF THE 2015 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL 1 (Vol. 359, pp. 639–650). https://doi.org/10.1007/978-3-662-48386-2_65
- Chicago author-date
- Zha, Xi, Yi Chai, Frank Witlox, and Le Ma. 2016. “Container Throughput Time Series Forecasting Using a Hybrid Approach.” In PROCEEDINGS OF THE 2015 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL 1, edited by Y Jia, J Du, H Li, and W Zhang, 359:639–50. New York: Springer. https://doi.org/10.1007/978-3-662-48386-2_65.
- Chicago author-date (all authors)
- Zha, Xi, Yi Chai, Frank Witlox, and Le Ma. 2016. “Container Throughput Time Series Forecasting Using a Hybrid Approach.” In PROCEEDINGS OF THE 2015 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL 1, ed by. Y Jia, J Du, H Li, and W Zhang, 359:639–650. New York: Springer. doi:10.1007/978-3-662-48386-2_65.
- Vancouver
- 1.Zha X, Chai Y, Witlox F, Ma L. Container throughput time series forecasting using a hybrid approach. In: Jia Y, Du J, Li H, Zhang W, editors. PROCEEDINGS OF THE 2015 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL 1. New York: Springer; 2016. p. 639–50.
- IEEE
- [1]X. Zha, Y. Chai, F. Witlox, and L. Ma, “Container throughput time series forecasting using a hybrid approach,” in PROCEEDINGS OF THE 2015 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL 1, Yangzhou, PEOPLES R CHINA, 2016, vol. 359, pp. 639–650.
@inproceedings{01M1EKNYHES11PDPF4XA3964YR,
abstract = {{This paper proposed a novel two-stage hybrid container throughput forecasting model. Time series in reality exhibits both linear and nonlinear characteristics and individual models are not able to describe the two features simultaneously. Therefore, we combine linear model SARIMA (seasonal autoregressive integrated moving average) and nonlinear model ANN (artificial neural network). In order to break through the limitations of traditional hybrid models, based on the identified parameters of SARIMA in first stage, the structures of several ANN in second stage could be decided. Finally, we validate the proposed hybrid model 5 performs best with case study in Shanghai port.}},
author = {{Zha, Xi and Chai, Yi and Witlox, Frank and Ma, Le}},
booktitle = {{PROCEEDINGS OF THE 2015 CHINESE INTELLIGENT SYSTEMS CONFERENCE, VOL 1}},
editor = {{Jia, Y and Du, J and Li, H and Zhang, W}},
isbn = {{9783662483848}},
issn = {{1876-1100}},
keywords = {{Port throughput forecasting,SARIMA,ANN,Hybrid models}},
language = {{eng}},
location = {{Yangzhou, PEOPLES R CHINA}},
pages = {{639--650}},
publisher = {{Springer}},
title = {{Container throughput time series forecasting using a hybrid approach}},
url = {{http://doi.org/10.1007/978-3-662-48386-2_65}},
volume = {{359}},
year = {{2016}},
}
- Altmetric
- View in Altmetric
- Web of Science
- Times cited: