Vessel traffic flow analysis and prediction by an improved PSO-BP mechanism based on AIS data

Abstract

Vessel traffic flow forecasting is indispensable for the development of national shipping industry and the coordinated development of regional economy. In this paper, an improved PSO-BP (particle swarm optimization-back propagation) prediction model is established for the prediction of the total vessel traffic flow in a designated port area. The presented prediction model is referred to as SAPSO-BP neural network which utilizes the SAPSO (self-adaptive particle swarm optimization) algorithm to adjust the structure parameters of BP neural network. Facilitated by the establishment of foundation networks and satellite communication of Automatic Identification System (AIS) receivers, the detailed information of vessel is becoming increasingly obtainable. Therefore, a large number of real-observed vessel traffic flow data based on AIS records of Port area of Los Angeles (LA) has been chosen as the testing database to validate the effectiveness of the SAPSO-BP prediction model in vessel traffic flow forecasting. The grey correlation analysis (GCA) is employed to confirm the input dimension of the prediction model. Finally, simulation results demonstrate that the presented prediction approach can achieve vessel traffic flow trend predictions with reasonable, satisfactory convergence and stability.