Prediction of the severity of marine accidents using improved machine learning

Transportation Research Part E Logistics and Transportation Review, Год журнала: 2024, Номер 188, С. 103647 - 103647

Опубликована: Июль 2, 2024

Although many studies have focused on the occurrence likelihood of marine accidents, few analysis severity consequences, and even fewer prediction severity. To this end, a new research framework is proposed in study to accurately predict accidents. First, novel two-stage feature selection (FS) method was developed select rank Risk Influential Factors (RIFs) improve accuracy Machine Learning (ML) model interpretability FS. Second, comprehensive evaluation measure performance FS methods based stability, predictive improvement, statistical tests. Third, six well-established ML models were used compared different predictors. The Light Gradient Boosting (LightGBM) found best for accidents treated as benchmark model. Finally, LightGBM accident RIFs selected by method, effect risk control measures counterfactually analysed from quantitative perspective. This innovative use improved approaches can effectively analyse providing methodology triggering direction using Artificial Intelligence (AI) technologies safety assessment prevention studies. source code publicly available at: https://github.com/FengYinLeo/PGI-SDMI.

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

---

Time-evolving graph-based approach for multi-ship encounter analysis: Insights into ship behavior across different scenario complexity levels

Transportation Research Part A Policy and Practice, Год журнала: 2025, Номер 194, С. 104427 - 104427

Опубликована: Фев. 27, 2025

Язык: Английский

---

A novel data-driven method of ship collision risk evolution evaluation during real encounter situations

Reliability Engineering & System Safety, Год журнала: 2024, Номер 249, С. 110228 - 110228

Опубликована: Май 22, 2024

Язык: Английский

---

A novel method for ship carbon emissions prediction under the influence of emergency events

Transportation Research Part C Emerging Technologies, Год журнала: 2024, Номер 165, С. 104749 - 104749

Опубликована: Июль 13, 2024

Accurate prediction of ship emissions aids to ensure maritime sustainability but encounters challenges, such as the absence high-precision and high-resolution databases, complex nonlinear relationships, vulnerability emergency events. This study addresses these issues by developing novel solutions: a Spatiotemporal Trajectory Search Algorithm (STSA) based on Automatic Identification System (AIS) data; rolling structure-based Seasonal-Trend decomposition Loess technique (STL); modular deep learning model Structured Components, stacked-Long short-term memory, Convolutional neural networks Comprehensive forecasting module (SCLCC). Based solutions, case using pre post-COVID-19 AIS data demonstrates reliability pandemic's impact emissions. Numerical experiments reveal that STSA algorithm significantly outperforms conventional identification standard in terms accuracy navigation state identification; SCLCC exhibits greater resistance against events excels comprehensively capturing global information, thus yielding higher accurate results. sheds light changing dynamics transport its impacts carbon

Язык: Английский

---

COLERGs-constrained safe reinforcement learning for realising MASS's risk-informed collision avoidance decision making

Knowledge-Based Systems, Год журнала: 2024, Номер 300, С. 112205 - 112205

Опубликована: Июль 16, 2024

Язык: Английский

---

Bi-directional information fusion-driven deep network for ship trajectory prediction in intelligent transportation systems

Transportation Research Part E Logistics and Transportation Review, Год журнала: 2024, Номер 192, С. 103770 - 103770

Опубликована: Сен. 20, 2024

Язык: Английский

---

Investigation of the risk influential factors of maritime accidents: A novel topology and robustness analytical framework

Reliability Engineering & System Safety, Год журнала: 2024, Номер 254, С. 110636 - 110636

Опубликована: Ноя. 6, 2024

Язык: Английский

---

A game-based decision-making method for multi-ship collaborative collision avoidance reflecting risk attitudes in open waters

Ocean & Coastal Management, Год журнала: 2024, Номер 259, С. 107450 - 107450

Опубликована: Окт. 23, 2024

Язык: Английский

---

Experimental study on human evacuation onboard passenger ships considering heeling angle and opposite directions

Ocean Engineering, Год журнала: 2024, Номер 308, С. 118256 - 118256

Опубликована: Июнь 2, 2024

It is crucial to understand the movement characteristics and behaviour of individuals during ship emergencies for successful human evacuation on board ships. This study aimed analyse effect heeling angles comprehensive efficiency passenger ships through development a new experimental dataset evacuation. To achieve this, series tests were conducted using an simulator closely resembling scenarios recommended by International Maritime Organization (IMO). revealed that angle significantly reduces both walking running speeds participants. Notably, when 16°, males demonstrated better adaptability as their speed was less affected compared females. Additionally, height found be positively correlated with across different scenarios. In counter flow tests, experiment systematically quantified. The results showed time increased higher angles. Furthermore, participants tended maintain larger personal space in ship, resulting lower density reached 16° other outcomes this offer valuable insights validating models developing guidelines from

Язык: Английский

---