Jinwan Park

Automatic Identification System (AIS) data are widely used for maritime traffic monitoring and near-miss detection. Most detection approaches based on the closest point of approach (CPA) implicitly assume that AIS reports from different vessels are temporally synchronized. However, in real maritime environments, AIS messages are often received at irregular intervals. Despite this, the influence of AIS temporal asynchrony on the reliability of CPA-based near-miss detection has not been systematically investigated. This study investigates how temporal asynchrony in AIS reporting affects CPA-based near-miss detection using real-world AIS encounter data. The distribution of time differences between AIS reports of vessel pairs was analyzed, and detection outcomes were evaluated under multiple temporal synchronization thresholds (DT_MAX) through encounter-level analysis. The results show that AIS report time differences exhibit a long-tailed distribution ranging from several seconds to several minutes. To clarify the evaluation framework, false-negative near-miss events are defined as encounters detected under the baseline condition without temporal filtering and missed under DT_MAX filtering. Detection experiments indicate that stricter temporal synchronization constraints lead to an increase in missed detections. For example, under a moderate CPA threshold (0.5 nm, 30 min), the false-negative rate relative to the baseline condition increases to approximately 36% when DT_MAX = 60 s, but decreases to about 5% when DT_MAX = 240 s. These findings demonstrate that AIS temporal asynchrony is a critical factor affecting the reliability of CPA-based near-miss detection under real-world irregular reporting conditions. The results further indicate that DT_MAX = 240 s provides a practical reference point, maintaining 94.2–95.7% detection reliability depending on the CPA threshold. Incorporating temporal synchronization into AIS-based detection algorithms is therefore essential for improving the reliability of maritime traffic monitoring, navigational decision-support systems, and Maritime Autonomous Surface Ships (MASS).

This study proposes a collision-risk assessment framework that combines an interval type-2 fuzzy inference system with Dempster–Shafer evidence theory to more reliably evaluate vessel collision risk under the uncertainty inherent in AIS-based marine navigation data. The fuzzy system models membership-function uncertainty through a footprint of uncertainty and produces time-indexed basic probability assignments that are subsequently combined through a Dempster–Shafer–based temporal integration process. Robust combination rules are incorporated to mitigate the counterintuitive results often produced by classical evidence combination. Furthermore, Lenart’s time-based criterion and Fujii’s spatial safety domain are unified to construct a three-level risk labeling scheme, overcoming the limitations of conventional binary risk classification. Case studies using real AIS data demonstrate improved predictive accuracy and significantly reduced uncertainty, particularly when using the robust symmetric combination rule. Overall, the proposed framework provides a systematic approach for handling structural uncertainty in maritime environments and supports more reliable collision-risk prediction and safer navigational decision-making.

Accurate forecasting of ship encounter positions is crucial for preventing collisions at sea. This paper presents a framework for predicting a ship’s trajectory using a sparse Gaussian process. The proposed method effectively addresses the limitations of existing full Gaussian processes, specifically the significant storage requirements and time complexity associated with data training. The model is trained using Automatic Identification System (AIS) data on trajectories, with hyperparameters optimized through a genetic algorithm. Experimental analysis demonstrates that the proposed model reduces average time complexity by 61.3 s and improves average prediction error to 9.2 m compared to full Gaussian-process-based models.

Jinwan Park. International Journal of Fuzzy Logic and Intelligent Systems 2021;21:378-90. https://doi.org/10.5391/IJFIS.2021.21.4.378

According to the statistics of maritime accidents, most collision accidents have been caused by human factors. In an encounter situation, the prediction of ship’s trajectory is a good way to notice the intention of the other ship. This paper proposes a methodology for predicting the ship’s trajectory that can be used for an intelligent collision avoidance algorithm at sea. To improve the prediction performance, the density-based spatial clustering of applications with noise (DBSCAN) has been used to recognize the pattern of the ship trajectory. Since the DBSCAN is a clustering algorithm based on the density of data points, it has limitations in clustering the trajectories with nonlinear curves. Thus, we applied the spectral clustering method that can reflect a similarity between individual trajectories. The similarity measured by the longest common subsequence (LCSS) distance. Based on the clustering results, the prediction model of ship trajectory was developed using the bidirectional long short-term memory (Bi-LSTM). Moreover, the performance of the proposed model was compared with that of the long short-term memory (LSTM) model and the gated recurrent unit (GRU) model. The input data was obtained by preprocessing techniques such as filtering, grouping, and interpolation of the automatic identification system (AIS) data. As a result of the experiment, the prediction accuracy of Bi-LSTM was found to be the highest compared to that of LSTM and GRU.

According to the statistics of maritime collision accidents over the last five years (2016–2020), 95% of the total maritime collision accidents are caused by human factors. Machine learning algorithms are an emerging approach in judging the risk of collision among vessels and supporting reliable decision-making prior to any behaviors for collision avoidance. As the result, it can be a good method to reduce errors caused by navigators’ carelessness. This article aims to propose an enhanced machine learning method to estimate ship collision risk and to support more reliable decision-making for ship collision risk. In order to estimate the ship collision risk, the conventional support vector machine (SVM) was applied. Regardless of the advantage of the SVM to resolve the uncertainty problem by using the collected ships’ parameters, it has inherent weak points. In this study, the relevance vector machine (RVM), which can present reliable probabilistic results based on Bayesian theory, was applied to estimate the collision risk. The proposed method was compared with the results of applying the SVM. It showed that the estimation model using RVM is more accurate and efficient than the model using SVM. We expect to support the reasonable decision-making of the navigator through more accurate risk estimation, thus allowing early evasive actions.