Comprehensive Analysis of Port State Control on Turkish Flagged Ships Through the Association Rule Mining

Abstract

Port state control (PSC) 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 PSC inspection results of Turkish flagged ships using the data mining model. Considering a total of 209 PSC 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. However, 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 to improve the port state control performance of Turkish flagged ships. We recommend that further research collect more data on the PSC inspection of ships flying other flags to update the proposed models and improve their analysis performance.

Keywords

• Port State Control
• Ship Inspections
• Turkish Flagged Ships
• Data Mining
• Association Rule

Türk Bayraklı Gemiler Üzerine Uygulanan Liman Devleti Denetimlerinin Birliktelik Kuralı Madenciliği ile Kapsamlı Analizi

Abstract

Gemi denetimleri, denizde emniyeti artırmanın en iyi yollarından biridir. Bu nedenle gemi kazalarının önlenmesinde eksikliklere neden olan parametrelerin belirlenmesi hayati önem taşımaktadır. Bu çalışmanın temel amacı, Türk bayraklı gemilerin denetim sonuçlarının veri madenciliği modeli kullanılarak analiz edilmesidir. 2014-2019 yılları arasında Türk bayraklı gemilerin tutulması ile sonuçlanan toplam 209 denetim raporu dikkate alınarak, tespit edilen eksikliklerin birliktelik kurallarını belirlemek için Apriori Algoritması uygulaması SPSS Modeler 18.0 yazılımı kullanılarak yapılmıştır. Çalışmada, seyir emniyeti, yaşam/çalışma koşulları ve acil durum sistemleri eksikliklerinin birliktelik kurallarını oluşturan ana faktörler olduğu bulunmuştur. Bunun yanı sıra, tutulmaya neden olan eksiklikler incelendiğinde, ilişki sıklığı en fazla olan değişkenler seyir güvenliği, sertifika/dokümantasyon ve acil durum sistemleri olmuştur. Çalışmanın sonuçlarının, Türk bayraklı gemilerin liman devleti denetimi performansının iyileştirilmesi için bayrak devleti kontrol mekanizmasına faydalı olacağı düşünülmektedir. Gelecek çalışmalar için önerilen modelleri güncellemek ve analiz performanslarını iyileştirmek adına daha geniş çaplı bir veri setinin kullanılması tavsiye edilmektedir.

Keywords

• Liman Devleti Denetimi
• Gemi Denetimleri
• Türk Bayraklı Gemiler
• Veri Madenciliği
• Birliktelik Kuralı

References

1. Abaya, S.A., (2012). Association rule mining based on Apriori algorithm in minimizing candidate generation. International Journal of Scientific and Engineering Research 3(7): 1-4.
2. Agrawal, R., Imielinski, T., Swami, A.N., 1993. Mining association rules between sets of items in large databases. Proceedings of the 1993 ACM SIGMOD International Conference on Management of Data, 207–216.
3. Agrawal, R., Srikant, R., 1994. Fast algorithms for mining association rules. Proc. 20th International Conference of Very Large Data Bases, VLDB, 1215: 487-499.
4. Akyar, D.A., Çelik, M.S., 2018. The Analysis of Turkish Flagged Vessels' Deficiencies and Detentions within the Scope of Black Sea MOU-PSC Inspections. Third Mediterranean International Congress on Social Sciences (MECAS III), 137-153.
5. Bolat, F., (2019). Türk Bayraklı Gemilerın Tokyo Mutabakat Zaptı Bölgesindeki Performanslarının İncelenmesi. Avrasya Uluslararası Araştırmalar Dergisi 7(19): 468-487.
6. Çakır, E., Fışkın, R., Sevgili, C., (2021). Investigation of tugboat accidents severity: An application of association rule mining algorithms. Reliability Engineering and System Safety 209: 107470.
7. Chen, M.S., Han, J., Yu, P.S., (1996). Data mining: an overview from a database perspective. IEEE Transactions on Knowledge and data Engineering 8(6): 866-883.
8. Chung, W.H., Kao, S.L., Chang, C.M., Yuan, C.C., (2020). Association rule learning to improve deficiency inspection in port state control. Maritime Policy Management 47(3): 332–351, doi: 10.1080/03088839.2019.1688877.

9. Fu, J., Chen, X., Wu, S., Shi, C., Wu, H., Zhao, J., Xiong, P., (2020a). Mining ship deficiency correlations from historical port state control (PSC) inspection data. PLoS One 15(2): e0229211.
10. Fu, J., Chen, X., Wu, S., Shi, C., Zhao, J., Xian, J. (2020b). Ship Detention Situation Prediction via Optimized Analytic Hierarchy Process and Naïve Bayes Model. Mathematical Problems in Engineering 2020: 1-11, doi: 10.1155/2020/8147310.
11. Kumar, K.S., Chezian, R.M., (2012). A survey on association rule mining using apriori algorithm. International Journal of Computer Applications 45(5): 47-50.
12. Li, N., Zeng, L., He, Q., Shi, Z., 2012. Parallel implementation of apriori algorithm based on mapreduce. 13th ACIS International Conference on Software Engineering, Artificial Intelligence, Networking and Parallel/Distributed Computing 236-241.
13. Maragatham, G., Lakshmi, M., (2012). A recent review on association rule mining. Indian Journal of Computer Science and Engineering (IJCSE) 2(6): 831-836.
14. Osman, M.T., Yuli, C., Li, T., Senin, S.F., (2020). Association rule mining for identification of port state control patterns in Malaysian ports. Maritime Policy and Management 48(8): 1082-1095, doi: 10.1080/03088839.2020.1825854.
15. Tsou, M.C., (2019). Big data analysis of port state control ship detention database. Journal of Marine Engineering and Technology 18(3): 113–121, doi: 10.1080/20464177.2018.1505029.
16. Wang, S., Yan, R., Qu, X., (2019). Development of a non-parametric classifier: Effective identification, algorithm, and applications in port state control for maritime transportation. Transportation Research Part B: Methodological 128: 129–157, doi: 10.1016/j.trb.2019.07.017.
17. Wicaksono, D., Jambak, M.I., Saputra, D.M., (2020). The comparison of apriori algorithm with preprocessing and FP-growth algorithm for finding frequent data pattern in association rule. Advances in Intelligent Systems Research 172: 315-319.
18. Xiao, Y., Wang, G., Lin, K.C., Qi, G., Li, K.X., (2020). The effectiveness of the New Inspection Regime for Port State Control: Application of the Tokyo MoU. Maritime Policy 115: 103857, doi: 10.1016/j.marpol.2020.103857.
19. Yan, R., Wang, S., Fagerholt, K., (2020). A semi-“smart predict then optimize” (semi-SPO) method for efficient ship inspection. Transportation Research Part B: Methodological 142: 100–125, doi: 10.1016/j.trb.2020.09.014
20. Yan, R., Wang, S., Peng, C., (2021). An Artificial Intelligence Model Considering Data Imbalance for Ship Selection in Port State Control Based on Detention Probabilities. Journal of Computational Science 48: 101257, doi: 10.1016/j.jocs.2020.101257
21. Yuan, X., 2017. An improved Apriori algorithm for mining association rules. AIP Conference Proceedings, 1820(1): 080005, doi: 10.1063/1.4977361.
22. Yılmaz, F., Ece, N.J., (2017). Analysis of the Relationship Between Variables Related to Paris Mou-PSC Inspections and the Results of Inspection Applied to Turkish Flagged Ships. Journal of ETA Maritime Science 5(2): 172-185.
23. Zhao, Q., Bhowmick, S.S. (2003). Association rule mining: A survey. CAIS, Technical Report, Nanyang Technological University, Singapore, Note No. 2003116.