Prediction Model for Ship Traffic Flow Considering Periodic Fluctuation Factors
Download as PDF
DOI: 10.23977/cii2019.19
Author(s)
Zhenguo Ding, Shukui Zhang
Corresponding Author
Zhenguo Ding
ABSTRACT
In order to improve prediction accuracy of ship traffic flow, an improved linear growth model is developed to predict ship traffic flow, by taking into all periodic fluctuation factors, such as seasonal changes, climate impact, and so on, then the Bayesian estimation and prediction are used to solve the new model, and ship traffic flow is predicted using the historical data of ship traffic flow. A case is carried out to compare the prediction effect of the models, and results show that, compared with the linear growth model, the prediction results with the improved model are more in line with the actual situation of ship traffic flow; besides, the mean absolute error of monthly ship flow decrease 3.56%, and the standard deviation decrease 3.79%.
KEYWORDS
In order to improve prediction accuracy of ship traffic flow, an improved linear growth model is developed to predict ship traffic flow, by taking into all periodic fluctuation factors, such as seasonal changes, climate impact, and so on, then the Bayesian estimation and prediction are used to solve the new model, and ship traffic flow is predicted using the historical data of ship traffic flow A case is carried out to compare the prediction effect of the models, and results show that, compared