No abstract

As tugboats interact very closely with ships in restricted waters, the possibility of accidents increases in these operations. Despite the high accident possibility, there is a gap in studies on tugboat accidents. This study aims to analyse accidents involving tugboats using data mining. For this purpose, a tugboat accidents dataset consisting of a total of 496 accident records for the period from 2008 to 2019 was collected. Logistic regression and decision tree algorithms were implemented to the dataset. The results revealed that tugboat propulsion type is the most important and influential factor in the severity of tugboat accidents. The inferences drawn from these results could be beneficial for tugboat operators and port authorities in enhancing their awareness of the factors affecting tugboat accidents. In addition, the outputs of this study can be a reference for management units in developing strategies for preventing tugboat accidents and can also be used in effective planning for practicable prevention programmes and practices.

Seafarers should be educated and trained according the conditions they face on board. An improved training method should be adopted. This way, the future officers will be qualified to intervene in emergency situations.

No abstract

Ship inspections are one of the best ways of improving safety at sea. Therefore, it is vital to determine the parameters that cause deficiencies in the prevention of ship accidents. The main purpose of this study is to analyze the inspection results of Turkish flagged ships using the data mining model. Considering a total of 209 inspection reports resulting in the detention of Turkish flagged ships between 2014 and 2019, the Apriori Algorithm was applied using SPSS Modeler 18.0 software to determine the association rules of deficiencies detected. The study found that the safety of navigation, living/working conditions, and emergency systems are the main factors creating association rules in deficiencies. On the other hand, when the deficiencies causing detention were analyzed, the most frequently associated variables were safety of navigation, certificate/documentation, and emergency systems. The results of the study are supposed to be useful for the flag state control mechanism in order to improve the port state control performance of Turkish flagged ships. We recommend that further research collect more data on the inspection of ships flying other flags of all sizes to update the proposed models and improve their analysis performance.