Graph neural networks enabled accident causation prediction for maritime vessel traffic

Reliability Engineering & System Safety, Год журнала: 2025, Номер unknown, С. 110804 - 110804

Опубликована: Янв. 1, 2025

Язык: Английский

---

Leveraging Large Language Models for Enhancing Safety in Maritime Operations

Applied Sciences, Год журнала: 2025, Номер 15(3), С. 1666 - 1666

Опубликована: Фев. 6, 2025

Maritime operations play a critical role in global trade but face persistent safety challenges due to human error, environmental factors, and operational complexities. This review explores the transformative potential of Large Language Models (LLMs) enhancing maritime through improved communication, decision-making, compliance. Specific applications include multilingual communication for international crews, automated reporting, interactive training, real-time risk assessment. While LLMs offer innovative solutions, such as data privacy, integration, ethical considerations must be addressed. concludes with actionable recommendations insights leveraging build safer more resilient systems.

Язык: Английский

---

Quantitative Analysis of Risk Coupling Effects in Highway Accidents: A Focus on Primary and Secondary Accidents

Applied Sciences, Год журнала: 2025, Номер 15(6), С. 3114 - 3114

Опубликована: Март 13, 2025

Analyzing risk coupling effects in highway accidents provides guidance for preventive decoupling measures. Existing studies rarely explore the differences between primary (PA) and secondary (SA) from a quantitative perspective. This study proposes method to measure of PA SA on highways examine their differences. A domain-pretrained named entity recognition (NER) model, TRBERT-BiLSTM-CRF, is proposed identify factors types based 431 accident investigation reports published by emergency management departments China. The N-K model was applied calculate values different scenarios SA, Wilcoxon signed-rank test performed them. Finally, were compared, targeted prevention recommendations are provided. results showed that our NER achieved best macro-F1 score traffic recognition. Most increased with number types, but value five lower than four factors, indicating do not always superimpose each other complex scenarios. Moreover, there significant mechanisms SA. suggest likelihood occurrences should be reduced through standardized vehicle inspections flexible control measures, respectively, thereby enhancing safety.

Язык: Английский

---

Construction of a Cognitive Graph for Intelligent Manufacturing Robot Behavior

Опубликована: Дек. 27, 2024

Язык: Английский

---

Research on the Design of Multimodal Maritime Data Management System

Journal of the Korean Society of Marine Environment and Safety, Год журнала: 2024, Номер 30(7), С. 836 - 843

Опубликована: Дек. 30, 2024

Язык: Английский

---