Prediction of Grades of Ship Collision Accidents Based on Random Forests and Bayesian Networks

Tang, Li; Tang, Yuheng; Zhang, Kai; Du, Lina; Wang, Min

doi:10.1109/ictis.2019.8883590

Cited by 6 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, given the need to improve monitoring of the safety of navigating vessels, we propose a novel approach to maritime risk assessment through the use of machine learning. Few studies have sought to apply machine learning to vessel traffic data (Fujino et al 2018;Tang et al 2019) or specifically to maritime risk assessment (Jin et al 2019;Dorsey et al 2020). However, many have recognised that by combining vessel traffic, accident and other datasets, greater insights into maritime safety can be achieved (Lensu and Goerlandt, 2019;Kulkarni et al 2020).…”

Section: Introductionmentioning

confidence: 99%

A machine learning approach for monitoring ship safety in extreme weather events

et al. 2021

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

A machine learning approach for monitoring ship safety in extreme weather events

et al. 2021

View full text Add to dashboard Cite

“…To avoid overfitting and increase the prediction accuracy, a learning rate strategy is applied. The learning rate is used to scale the contribution of each tree model by introducing a factor ξ (0 < ξ ≤ 1), as indicated in Equation (12).…”

Section: Gradient Boosting Decision Treesmentioning

confidence: 99%

“…In the maritime field, several researchers have examined safety by predicting vessel accidents on the waterway [9], forecasting coastal waves [10], and examining ship collisions [11,12], among other aspects. Moreover, although several researchers have implemented risk assessment methods to identify the risk factors associated with container ports [4][5][6], research regarding the prediction of container port accidents remains limited.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Machine Learning-Based Models for Accident Prediction at a Korean Container Port

Kim

Lee

et al. 2021

Sustainability

View full text Add to dashboard Cite

The occurrence of accidents at container ports results in damages and economic losses in the terminal operation. Therefore, it is necessary to accurately predict accidents at container ports. Several machine learning models have been applied to predict accidents at a container port under various time intervals, and the optimal model was selected by comparing the results of different models in terms of their accuracy, precision, recall, and F1 score. The results show that a deep neural network model and gradient boosting model with an interval of 6 h exhibits the highest performance in terms of all the performance metrics. The applied methods can be used in the predicting of accidents at container ports in the future.

show abstract

Analysis of paint traces to determine the ship responsible for a collision

Lee¹,

Lee²,

Seo³

2021

Sci Rep

View full text Add to dashboard Cite

Although there have been many instances of ship collision at sea in recent times, not much research has been conducted on the topic. In this study, paint from an actual site of ship collision was collected and analyzed as evidence. The amount of evidence collected from the ships involved in the collision is either small or has inconsistent morphology. In addition, the contaminants and samples are often mixed in this evidence, making its analysis difficult. Paint traces of the damaged ship and the ship suspected to be responsible for the collision were compared through scanning electron microscopy with energy dispersive X-ray spectroscopy (SEM–EDS), attenuated total reflection–Fourier transform infrared spectroscopy (ATR–FTIR), thermogravimetry (TG) and derivative thermogravimetry (DTG), and pyrolysis–gas chromatography/mass spectrometry (Py–GC/MS) analyses. The ship responsible for the collision could be identified by characterization and by performing a comparative analysis of the extracted paint. Among the methods used in this study, Py–GC/MS can sensitively analyze even similar paints, and identified styrene and phthalic anhydride as the most prominent components of the paint used as evidence. The results obtained can be used to investigate the evidence collected from collision sites and to determine the ship responsible for the collision.

show abstract

Prediction of Grades of Ship Collision Accidents Based on Random Forests and Bayesian Networks

Cited by 6 publications

References 14 publications

A machine learning approach for monitoring ship safety in extreme weather events

A machine learning approach for monitoring ship safety in extreme weather events

Machine Learning-Based Models for Accident Prediction at a Korean Container Port

Analysis of paint traces to determine the ship responsible for a collision

Contact Info

Product

Resources

About