A Risk Assessment System for Improving Port State Control Inspection

• Published in: 2007 International Conference on Machine Learning and Cybernetics Vol. 2; pp. 818 - 823
• Main Authors: Rui-Feng Xu, Qin Lu, Wen-Jie Li, Li, K.X., Hai-Sha Zheng
• Format: Conference Proceeding
• Language: English
• Published: IEEE 01.08.2007
• Subjects: Control systems; Cybernetics; Delay; Inspection; Logistics; Machine learning; Marine vehicles; Port State Control; Risk assessment; Risk management; Spatial databases; Support vector machines; Target factors
• ISBN: 1424409721; 9781424409723
• ISSN: 2160-133X
• DOI: 10.1109/ICMLC.2007.4370255

Port state control (PSC) inspection is the most important mechanism to ensure world marine safe. This paper presents a risk assessment system, which estimates the risk of each candidate ship based on its generic factors and history inspection factors to select high-risk one before conducting on-board PSC inspection. The target factors adopted in Paris MOU PSC inspection and Tokyo MOU PSC inspection are considered in this system as well as the new factors discovered in the PSC inspection database. A risk assessment system based on support vector machine (SVM) is developed to classify candidate ships to high risk or low risk, respectively, based on the target factors. Experiment results show that the proposed system enhances the risk assessment accuracy effectively.