02

Analysis of Ship Accidents in the Istanbul Strait Using Neuro-Fuzzy and Genetically Optimised Fuzzy Classifiers

Marine accident analysis is important for ships passing through narrow, shallow and busy waterways. This study analyses the accidents which have occurred in the Istanbul Strait and proposes both quantitative and qualitative assessments of marine accidents. Marine accidents occurring in the Istanbul Strait are analysed by using a method based on neuro-fuzzy and genetically optimised fuzzy classifiers. It can be concluded that accident severity increases when poor weather conditions prevail in the Strait regardless of ship size. Therefore, solutions to reduce unwanted events should be prioritised by accounting for weather conditions and the capacity of the vessels. This analysis indicates that the safety level would be significantly improved if all the vessels follow the passage guidelines.

 

Akten, N. (2004). Analysis of shipping casualties in the Bosphorus. Journal of Navigation, 57(3), 345–356.CrossRefGoogle Scholar
 
Arslan, O. and Turan, O. (2009). Analytical investigation of marine casualties at the Strait of Istanbul with SWOT–AHP method. Maritime Policy & Management, 36(2), 131–145.CrossRefGoogle Scholar
 
Aydogdu, Y.V., Yurtoren, C., Kum, S., Park, J.-S. (2010). Questionnaire survey on the risk perception in the Istanbul Strait. Journal of Navigation and Port Research, 34(7), 517–523, http://dx.doi.org/10.5394/KINPR.2010.34.7.517.CrossRefGoogle Scholar
 
Barnett, M.L. (2005). Searching for the root causes of maritime casualties - individual competence or organizational culture? WMU Journal of Maritime Affairs, 4(2), 131–145.CrossRefGoogle Scholar
 
Basar, E. (2010). Investigation into marine traffic and a risky area in the Turkish straits system: Çanakkale Strait, TRANSPORT, 25, 5–10.CrossRefGoogle Scholar
 
Basar, E. and Yildirim, U. (2014). Effect of the oil areas on marine traffic and oil spill risks at the Black Sea. Journal of ETA Maritime Science, 2(2), 105–110.Google Scholar
 
Bishop, C.M. (1995). Neural networks for pattern recognition. Oxford University Press.CrossRefGoogle Scholar
 
Cetisli, B. (2010a). Development of an adaptive neuro-fuzzy classifier using linguistic hedges: Part 1, Expert Systems with Applications, 37(8), 6093–6101.CrossRefGoogle Scholar
 
Cetisli, B. (2010b). The effect of linguistic hedges on feature selection: Part 2. Expert Systems with Applications, 37(8), 6102–6108.CrossRefGoogle Scholar
 
Cetisli, B. and Barkana, A. (2010). Speeding up the scaled conjugate gradient algorithm and its application in neuro-fuzzy classifier training, Springer. Soft Computing, 14(4), 365–378.CrossRefGoogle Scholar
 
Cetisli, B. and Kalkan, H. (2014). A new deterministic validation method for classifier success: Give&Take, 22nd IEEE Signal Processing and Communications Applications Conference (SIU), Trabzon, Turkey, 345–348.CrossRefGoogle Scholar
 
Çelik, M. and Çebi, S. (2009). Analytical HFACS for investigating human errors in shipping accidents. Accident Analysis and Prevention, 41(1), 66–75.CrossRefGoogle ScholarPubMed