A hierarchical methodology for vessel traffic flow prediction using Bayesian tensor decomposition and similarity grouping

Abstract

Accurate vessel traffic flow (VTF) prediction can enhance navigation safety and economic efficiency. To address the challenge of the inherently complex and dynamic growth of the VTF time series, a new hierarchical methodology for VTF prediction is proposed. Firstly, the original VTF data is reconfigured as a three-dimensional tensor by a modified Bayesian Gaussian CANDECOMP/PARAFAC (BGCP) tensor decomposition model. Secondly, the VTF matrix (hour ✕ day) of each week is decomposed into high- and low-frequency matrices using a Bidimensional Empirical Mode Decomposition (BEMD) model to address the non-stationary signals affecting prediction results. Thirdly, the self-similarities between VTF matrices of each week within the high-frequency tensor are utilised to rearrange the matrices as different one-dimensional time series to solve the weak mathematical regularity in the high-frequency matrix. Then, a Dynamic Time Warping (DTW) model is employed to identify grouped segments with high similarities to generate more suitable high-frequency tensors. The experimental results verify that the proposed methodology outperforms the state-of-the-art VTF prediction methods using real Automatic Identification System (AIS) datasets collected from two areas. The methodology can potentially optimise relation operations and manage vessel traffic, benefiting stakeholders such as port authorities, ship operators, and freight forwarders.