Zonguldak Bülent Ecevit University, Maritime Faculty, Kepez Campus, Karadeniz Ereğli, Zonguldak 67300, Turkiye.
Mar Pollut Bull. 2024 Nov;208:116938. doi: 10.1016/j.marpolbul.2024.116938. Epub 2024 Sep 21.
Since marine and environmental pollution is a major problem for the maritime industry, preventive implementations are constantly being developed. In this context, this research aimed to determine the dominant factors in ships detected to have pollution prevention deficiencies in port state control (PSC). A total of 12,530 PSC reports carried out by Paris Memorandum of Understanding (MoU) region between 2017 and 2023 were analyzed with the association rule mining. The Apriori algorithm was performed to reveal hidden and meaningful relationships in the inspections. The dominant variables for inspections that detected pollution prevention deficiencies were ship flag, classification society, number of deficiencies, and inspection type. Association rules revealed that pollution prevention deficiency areas differed interestingly according to geographical region, classification society, and ship age. The findings may be a guide for stakeholders for pollution prevention during ship inspections, and contribute to the achievement of maritime-related Sustainable Development Goals (SDGs).
由于海洋和环境污染是航海业面临的一个主要问题，因此一直在不断制定预防措施。在这方面，本研究旨在确定在港口国控制（PSC）中发现船舶存在污染预防缺陷的主要因素。利用关联规则挖掘对 2017 年至 2023 年期间巴黎谅解备忘录（MoU）区域进行的总共 12530 次 PSC 报告进行了分析。采用 Apriori 算法揭示了检查中的隐藏和有意义的关系。检测到污染预防缺陷的检查的主要变量是船旗、船级社、缺陷数量和检查类型。关联规则显示，污染预防缺陷领域根据地理区域、船级社和船舶年龄有趣地有所不同。研究结果可为利益相关者在船舶检查期间进行污染预防提供指导，并有助于实现与海事相关的可持续发展目标（SDGs）。
