Xiuju Fu

Sijin Sun, Liangbin Zhao, Ming Deng et al.

Digital testing has emerged as a key paradigm for the development and verification of autonomous maritime navigation systems, yet the availability of realistic and diverse safety-critical encounter scenarios remains limited. Existing approaches either rely on handcrafted templates, which lack realism, or extract cases directly from historical data, which cannot systematically expand rare high-risk situations. This paper proposes a data-driven framework that converts large-scale Automatic Identification System (AIS) trajectories into structured safety-critical encounter scenarios. The framework combines generative trajectory modeling with automated encounter pairing and temporal parameterization to enable scalable scenario construction while preserving real traffic characteristics. To enhance trajectory realism and robustness under noisy AIS observations, a multi-scale temporal variational autoencoder is introduced to capture vessel motion dynamics across different temporal resolutions. Experiments on real-world maritime traffic flows demonstrate that the proposed method improves trajectory fidelity and smoothness, maintains statistical consistency with observed data, and enables the generation of diverse safety-critical encounter scenarios beyond those directly recorded. The resulting framework provides a practical pathway for building scenario libraries to support digital testing, benchmarking, and safety assessment of autonomous navigation and intelligent maritime traffic management systems. Code is available at https://anonymous.4open.science/r/traj-gen-anonymous-review.

Sijin Sun, Liangbin Zhao, Jiaxiang Cai et al.

Dialogue topic segmentation is critical in many human-AI collaborative applications which requires identifying heterogeneous boundary cues, including lexical transitions near utterance edges and semantic discontinuities across utterances. Existing utterance models often dilute these local lexical signals. We propose CobSeg, a novel multi-branch architecture that separates coherence-level semantic continuity from lexical boundary transitions and recovers both through directional boundary prediction. CobSeg further uses boundary informativeness weighting to emphasize high-utility utterance positions, and incorporates a corpus-derived topic coherence cue with learned combination weights. While CobSeg is evaluated as a compact trainable segmenter under supervised gold-boundary training and a pseudo-label setting with automatically induced boundaries, it performs enhanced boundary prediction without LLM calls during inference. Across five benchmarks, it improves $P_k$ and $W_d$ particularly when local lexical cues are prominent: under gold supervision, it reduces $P_k$ by 0.7 points and $W_d$ by 0.6 points on VHF, and reaches $P_k$ of 1.0 on DialSeg711; with induced boundaries, it reduces $P_k$ by 14.8 points on VHF, by 1.5 points on DialSeg711, and by 1.1 points on TIAGE, outperforming prior non-LLM approaches.

Deqing Zhai, Xiuju Fu, Xiao Feng Yin et al.

In this study, a probability density-based approach for constructing trajectories is proposed and validated through an typical use-case application: Estimated Time of Arrival (ETA) prediction given origin-destination pairs. The ETA prediction is based on physics and mathematical laws given by the extracted information of probability density-based trajectories constructed. The overall ETA prediction errors are about 0.106 days (i.e. 2.544 hours) on average with 0.549 days (i.e. 13.176 hours) standard deviation, and the proposed approach has an accuracy of 92.08% with 0.959 R-Squared value for overall trajectories between Singapore and Australia ports selected.

Deqing Zhai, Xiuju Fu, Xiao Feng Yin et al.

In this study, a novel coordinative scheduling optimization approach is proposed to enhance port efficiency by reducing weighted average turnaround time. The proposed approach is developed as a heuristic algorithm applied and investigated through different observation windows with weekly rolling horizon paradigm method. The experimental results show that the proposed approach is effective and promising on mitigating the turnaround time of vessels. The results demonstrate that largest potential savings of turnaround time (weighted average) are around 17 hours (28%) reduction on baseline of 1-week observation, 45 hours (37%) reduction on baseline of 2-week observation and 70 hours (40%) reduction on baseline of 3-week observation. Even though the experimental results are based on historical datasets, the results potentially present significant benefits if real-time applications were applied under a quadratic computational complexity.

Deqing Zhai, Xiuju Fu, Xiao Feng Yin et al.

Given the trend of digitization and increasing number of maritime transport, prediction of vessel berth stay has been triggered for requirements of operation research and scheduling optimization problem in the era of maritime big data, which takes a significant part in port efficiency and maritime logistics enhancement. This study proposes a systematic and dynamic approach of predicting berth stay for tanker terminals. The approach covers three innovative aspects: 1) Data source employed is multi-faceted, including cargo operation data from tanker terminals, time-series data from automatic identification system (AIS), etc. 2) The process of berth stay is decomposed into multiple blocks according to data analysis and information extraction innovatively, and practical operation scenarios are also developed accordingly. 3) The predictive models of berth stay are developed on the basis of prior data analysis and information extraction under two methods, including regression and decomposed distribution. The models are evaluated under four dynamic scenarios with certain designated cargoes among two different terminals. The evaluation results show that the proposed approach can predict berth stay with the accuracy up to 98.81% validated by historical baselines, and also demonstrate the proposed approach has dynamic capability of predicting berth stay among the scenarios. The model may be potentially applied for short-term pilot-booking or scheduling optimizations within a reasonable time frame for advancement of port intelligence and logistics efficiency.

Deqing Zhai, Xiuju Fu, Xiao Feng Yin et al.

In this study, a novel coordinative scheduling optimization approach is proposed to enhance port efficiency by reducing average wait time and turnaround time. The proposed approach consists of enhanced particle swarm optimization (ePSO) as kernel and augmented firefly algorithm (AFA) as global optimal search. Two paradigm methods of the proposed approach are investigated, which are batch method and rolling horizon method. The experimental results show that both paradigm methods of proposed approach can effectively enhance port efficiency. The average wait time could be significantly reduced by 86.0% - 95.5%, and the average turnaround time could eventually save 38.2% - 42.4% with respect to historical benchmarks. Moreover, the paradigm method of rolling horizon could reduce to 20 mins on running time over 3-month datasets, rather than 4 hrs on batch method at corresponding maximum performance.

Xiaocai Zhang, Xiuju Fu, Zhe Xiao et al.

This paper investigates the prediction of vessels' arrival time to the pilotage area using multi-data fusion and deep learning approaches. Firstly, the vessel arrival contour is extracted based on Multivariate Kernel Density Estimation (MKDE) and clustering. Secondly, multiple data sources, including Automatic Identification System (AIS), pilotage booking information, and meteorological data, are fused before latent feature extraction. Thirdly, a Temporal Convolutional Network (TCN) framework that incorporates a residual mechanism is constructed to learn the hidden arrival patterns of the vessels. Extensive tests on two real-world data sets from Singapore have been conducted and the following promising results have been obtained: 1) fusion of pilotage booking information and meteorological data improves the prediction accuracy, with pilotage booking information having a more significant impact; 2) using discrete embedding for the meteorological data performs better than using continuous embedding; 3) the TCN outperforms the state-of-the-art baseline methods in regression tasks, exhibiting Mean Absolute Error (MAE) ranging from 4.58 min to 4.86 min; and 4) approximately 89.41% to 90.61% of the absolute prediction residuals fall within a time frame of 10 min.

Sijin Sun, Liangbin Zhao, Ming Deng et al.

Vessel Traffic Services (VTS) are essential for maritime safety and regulatory compliance through real-time traffic management. However, with increasing traffic complexity and the prevalence of heterogeneous, multimodal data, existing VTS systems face limitations in spatiotemporal reasoning and intuitive human interaction. In this work, we propose VTS-LLM Agent, the first domain-adaptive large LLM agent tailored for interactive decision support in VTS operations. We formalize risk-prone vessel identification as a knowledge-augmented Text-to-SQL task, combining structured vessel databases with external maritime knowledge. To support this, we construct a curated benchmark dataset consisting of a custom schema, domain-specific corpus, and a query-SQL test set in multiple linguistic styles. Our framework incorporates NER-based relational reasoning, agent-based domain knowledge injection, semantic algebra intermediate representation, and query rethink mechanisms to enhance domain grounding and context-aware understanding. Experimental results show that VTS-LLM outperforms both general-purpose and SQL-focused baselines under command-style, operational-style, and formal natural language queries, respectively. Moreover, our analysis provides the first empirical evidence that linguistic style variation introduces systematic performance challenges in Text-to-SQL modeling. This work lays the foundation for natural language interfaces in vessel traffic services and opens new opportunities for proactive, LLM-driven maritime real-time traffic management.

Jing Li, Yinghua Yao, Yuangang Pan et al.

Worst-case fairness with off-the-shelf demographics achieves group parity by maximizing the model utility of the worst-off group. Nevertheless, demographic information is often unavailable in practical scenarios, which impedes the use of such a direct max-min formulation. Recent advances have reframed this learning problem by introducing the lower bound of minimal partition ratio, denoted as $α$, as side information, referred to as ``$α$-sized worst-case fairness'' in this paper. We first justify the practical significance of this setting by presenting noteworthy evidence from the data privacy perspective, which has been overlooked by existing research. Without imposing specific requirements on loss functions, we propose reweighting the training samples based on their intrinsic importance to fairness. Given the global nature of the worst-case formulation, we further develop a stochastic learning scheme to simplify the training process without compromising model performance. Additionally, we address the issue of outliers and provide a robust variant to handle potential outliers during model training. Our theoretical analysis and experimental observations reveal the connections between the proposed approaches and existing ``fairness-through-reweighting'' studies, with extensive experimental results on fairness benchmarks demonstrating the superiority of our methods.