Systems driven intelligent decision support methods for ship collision and grounding prevention: Present status, possible solutions, and challenges

Reliability Engineering & System Safety, Год журнала: 2024, Номер unknown, С. 110489 - 110489

Опубликована: Сен. 1, 2024

Язык: Английский

---

A machine learning-based data-driven method for risk analysis of marine accidents

Journal of Marine Engineering & Technology, Год журнала: 2024, Номер unknown, С. 1 - 12

Опубликована: Июнь 19, 2024

In view of the frequent occurrence marine accidents and complex interaction various risk-influencing factors (RIFs), a data-driven method to risk analysis that combines association rule mining (ARM) network (CN) is proposed in this study. The efficient FP-Growth algorithm applied facilitate ARM examine patterns frequently occur accidents. Subsequently, CN theory employed scrutinise multifaceted role RIFs their interactions accident system, which involves basic characteristics network, identification key through application weighted LeaderRank (WLR) algorithm, robustness analysis. results study indicate compared with random networks, networks exhibit higher level complexity, brings challenges safety prevention control. Inadequate regulation, violations, deficiencies management systems are identified as RIFs, stressing urgency improving supervision, strengthening law enforcement system. This may maritime traffic development methods.

Язык: Английский

---

Risk influencing factors on the consequence of waterborne transportation accidents in China (2013-2023) based on data-driven machine learning

Reliability Engineering & System Safety, Год журнала: 2025, Номер unknown, С. 110829 - 110829

Опубликована: Янв. 1, 2025

Язык: Английский

---

Risk assessment of emergency operations of floating storage and regasification unit

Journal of Marine Engineering & Technology, Год журнала: 2024, Номер 23(5), С. 357 - 372

Опубликована: Июнь 14, 2024

As the receiving terminal of liquefied natural gas (LNG), efficient emergency response floating storage and regasification unit (FSRU) is crucial to ensure safety LNG transportation at sea. However, few existing literature study risk issues FSRUs during operations. In order improve capability FSRU, this proposes an innovative assessment method identify hazards, quantify rank risks associated with disposal operations FSRU accidents. Firstly, a comprehensive index hierarchy system applicable human, equipment, environment, management aspects accident established through extensive review, analysis reports, expert judgments. Secondly, based on concept Intuitionistic Fuzzy Numbers, Hybrid Weighted Euclidean Distance (IFHWED) operator used enhance conventional FMEA approach. This considers varying levels confidence integrates subjective objective weights influential factors (RIFs), efficacy validated sensitivity analysis. Finally, evaluation model employing Analytic Hierarchy Process (AHP) fuzzy algorithms aggregate values RIFs. The findings offer decision-makers insights into operation, provide valuable guiding strategies for management, emergencies

Язык: Английский

---

Numerical study on inverse grading segregation mechanism of single coarse particles with different particle sizes under two-dimensional cyclic shear

Physics of Fluids, Год журнала: 2025, Номер 37(2)

Опубликована: Фев. 1, 2025

Granular mixtures with size differences can segregate when subjected to shaking or shear. This study investigates the mechanism underlying inverse grading segregation of single coarse particles varying sizes under cyclic A self-developed two-dimensional testing device combined three-dimensional printing technology and image identification capabilities segment anything model enabled construction a shear numerical based on rigid blocks. The analysis concentrated movement evolution macroscopic structure particle system, local topological structures surrounding particles. findings reveal following: (1) Larger lower shape factors result in shorter times free surface higher vertical velocities. (2) Throughout cycles, net force acting each fluctuates around zero, while its position displays zigzag upward trend. (3) Within typical cycle, larger increase void ratio, aiding their lift. Vertical displacement exhibit double peak pattern inversely related coordination number, horizontal periodically zero. (4) Weighted degree centrality negatively correlates particles, reflecting dual influence importance velocity. Fine occupying two corners create lifting effect, driving motion. Additionally, enhance importance, accelerating process.

Язык: Английский

---

Using Fuzzy Multi-Criteria Decision-Making as a Human-Centered AI Approach to Adopting New Technologies in Maritime Education in Greece

Information, Год журнала: 2025, Номер 16(4), С. 283 - 283

Опубликована: Март 30, 2025

The need to review maritime education has been highlighted in the relevant literature. Maritime curricula should incorporate recent technological advances, as well address needs of sector. In this paper, Fuzzy Delphi Method (FDM) and Analytic Hierarchy Process (FAHP) are utilized order propose a fuzzy multicriteria decision-making (MCDM) methodology that can be used assess importance new technologies design evaluation model assist policy-making. This study integrates perspectives main stakeholders, namely, lecturers sector management. We selected data from group 19 experienced professors business managers. results indicate such artificial intelligence (AI), augmented virtual reality (AR/VR), Internet Things (IoT), digital twins (DTs), cybersecurity, eLearning platforms, constitute set requirements policies meet by designing their appropriately. suggests logic MCDM methods human-centered AI approach for developing explainable policy-making models integrate stakeholder capture subjectivity is often inherited perspectives.

Язык: Английский

---

A novel method for complexity analysis of marine traffic based on complex networks

Proceedings of the Institution of Mechanical Engineers Part M Journal of Engineering for the Maritime Environment, Год журнала: 2025, Номер unknown

Опубликована: Апрель 27, 2025

The identification of marine traffic complexity is critical for the development and implementation intelligent maritime transportation systems. Analyzing extensive data on ship movements enhances situational awareness aids Vessel Traffic Services Operators (VTSOs) in real-time monitoring complex behaviors waterways. However, predominant systems-based analysis predominantly utilizes undirected Marine Situation Complex Network (MTSCN), which inconsistent with actual navigation situation. Firstly, a directed MTSCN constructed this study, accounts asymmetry navigational influences between ships. Secondly, Node Importance Evolution Model (NIEM) developed network traffic, employing two indicators: comprehensive degree strength. Finally, evaluation performance NIEM substantiated through case studies robustness analysis. research results show that construction takes into account differences ships, indicators consider transmission contributions nodes within network, therefore fits nautical situation better than MTSCN. findings confirm newly model significantly VTSOs identifying high-complexity ships requiring closer supervision, thereby enhancing management improving safety.

Язык: Английский

---

Predictive Analytics for Risk Reduction in Vehicle Supply Chain Management

Advances in computational intelligence and robotics book series, Год журнала: 2025, Номер unknown, С. 391 - 404

Опубликована: Май 1, 2025

The use of machine learning for customer profile, predictive analytics, and cluster analysis, AI-powered audience segmentation is revolutionizing campaigns to raise awareness car safety. By identifying target demographics, driving patterns, risk variables, this strategy guarantees highly customized marketing campaigns. AI can send safety messages by grouping audiences according concerns using behavioral modeling clustering algorithms. Proactive outreach made possible which forecasts engagement levels accident probability. improving precision marketing, technique that are seen the appropriate people at moment. Additionally, dynamic content adaption automatic campaign optimization AI-driven segmentation, maximizes impact. Through integration data real-time tracking, automated outreach, companies public drive meaningful change.

Язык: Английский

---

An Ensemble Decision Trees Model to Predict Traffic Pattern for Maritime Traffic Management

IET Intelligent Transport Systems, Год журнала: 2025, Номер 19(1)

Опубликована: Янв. 1, 2025

ABSTRACT This study presents a traffic pattern prediction model using ensembles of decision trees, leveraging AIS data to classify maritime patterns. The integrates static information, such as origin and destination, with dynamic data, including ship speed, course spatial position, define extract relevant features. By combining traditional algorithms tree ensemble model, stacked predictive framework is constructed trained on these extracted characteristics. applied validated from the Fujiangsha waters Jiangsu section Yangtze River. Comparative analysis reveals that this consistently outperforms models, maintaining stable accuracy above 98% across diverse scenarios. Testing unseen further confirms model's reliability, aligning well actual navigation findings suggest has strong potential (1) forecast routes for improved management, (2) infer behaviour based predicted patterns (3) support future applications in intelligent navigation.

Язык: Английский

---

Design of Customized Teaching Strategies Based on User Behavior Analysis in the Digital Transformation of Health Education

Applied Mathematics and Nonlinear Sciences, Год журнала: 2024, Номер 9(1)

Опубликована: Янв. 1, 2024

Abstract With the greater popularity of Internet, on one hand, online education platforms have flourished and informatization has entered a new era, with massive learning behavior data generated by learners in different platforms. This paper constructs portrait student based characteristics their health class. Based clustering analysis method big mining algorithm, user’s behavioral are analyzed. On this basis, algorithm is improved using collaborative filtering personalized recommendation introducing LDA model, customized teaching model constructed context education, its application effect explored. From four dimensions “course completion characteristics”, “teaching interaction “learning input characteristics,” achievement we analyzed groups students investigated application. “The were analyzed, it was concluded that Group A B performed better, but C accounted for higher percentage 24%. Finally, according to filtering-based digital students’ test scores pre post-test, average experimental subjects increased after post-test. The mean third post-test 4.27, 4.44, 4.35, respectively. It can be significant improvement classroom effectiveness.

Язык: Английский

---