Uncertainty-aware ship trajectory prediction via Spatio-Temporal Graph Transformer
Jincheng Gong, Huanhuan Li, Hang Jiao, Zaili Yang

Project |

• Introduced a novel ship trajectory prediction benchmark for Maritime Autonomous Surface Ships (MASS).
• Developed an advanced trajectory prediction algorithm that integrates spatio-temporal and probabilistic modelling.
• Pioneered an uncertainty-aware feature modelling approach to improve prediction reliability and interpretability.
• Validated the model’s performance across three benchmark datasets using three key evaluation metrics.

LLM4STP: A large language model-driven multi-feature fusion method for ship trajectory prediction
Hang Jiao, Jincheng Gong, Huanhuan Li, Jasmine Siu Lee Lam, Yaqing Shu, Jin Wang, Zaili Yang

Project |

• Propose LLM4STP, a novel multi-feature fusion method integrating LLMs and maritime knowledge for improved ship trajectory prediction.
• Introduce an adaptive graph-masked Transformer for dynamic ship interaction modelling, capturing complex spatial relationships.
• Combine local convolution and global LLM inference for effective multi-scale temporal modelling.
• Establish a system for trajectory uncertainty quantification using 2D Gaussian heatmaps and Geohash-based encoding.

Cybersecurity in smart port systems: A systematic review and data-driven research agenda
Yunfeng Zhao, Jincheng Gong, Huanhuan Li, Trung Thanh Nguyen, Christian Matthews, Zaili Yang

• Examines attack scenarios, technologies, and policy evolution in smart port cybersecurity.
• Reviews smart port cybersecurity literature to identify key research clusters and emerging themes.
• Utilises empirical data from the Maritime Cyber Attack Database (MCAD) to construct a global cyber-attack map.
• Identifies six research challenges, including CPS vulnerabilities, human factors, and AI-related threats.