Extracting Shipping Route Patterns by Trajectory Clustering Model Based on Automatic Identification System Data

Abstract

Shipping route analysis is essential for vessel traffic management and relies on professional technical facilities for collecting and recording specific information about vessel behaviors. The recent Automatic Identification System (AIS) onboard has been made available to provide ship-related information for the research. However, the complexity and large quantity of AIS data overload traditional surveillance operations and increase the difficulty of vessel traffic analysis. An unsupervised approach is urgently desired to effectively convert the raw AIS data to regular shipping route patterns. In this paper, we proposed a trajectory clustering model based on AIS data to analyze the shipping routes. The whole model consists of four parts: Data preprocessing, structure similarity measurement, clustering, and representative trajectory extraction. Our model comprehensively considered the geospatial information and contextual features of ship trajectory. The revised density-based clustering algorithm could automatically classify different shipping routes with trajectory features without prior knowledge. The experimental evaluation showed the effectiveness of the proposed model by real AIS data from Port of Tianjin. The results contribute to the further understanding of shipping route patterns and assists maritime authorities and the officers in stable and sustainable vessel traffic management.

Research on Ship Trajectory Extraction Based on Multi-Attribute DBSCAN Optimisation Algorithm

“…It allows experimental verification through specific waters. The results show that the model is effective, and helps to further understand the route model [10].…”

Modeling Vessel Behaviours by Clustering AIS Data Using Optimized DBSCAN

“…For future work, the research could be evaluated by comparing it against the applications on marine transportation modeling. Direct comparison on clustering points in trajectories to define stages has been done in [5,53]. Indirect comparison on clustering trajectories has been done in [30,31].…”

Dual Supervised Autoencoder Based Trajectory Classification Using Enhanced Spatio-Temporal Information

“…where L r1 and L r2 are MSE loss functions (see (11)) of RP autoencoder and FS autoencoder respectively, and α, β, γ are used to weigh these three loss functions, which are referred to as "loss weights" in the rest of this paper. Furthermore, if we denote the parameters (weights and bias) of FS encoder and RP encoder as η and σ respectively, the gradient of the loss function L with respect to η and σ can be expressed as:…”