Web Mining for Improving Risk Assessment in Port State Control Inspection

Abstract

Port state control (PSC) inspection is the most important mechanism to ensure world marine safety. Existing PSC risk assessment systems estimate the risk of each candidate ship on the target factors, which is recorded in the inspection database, to help the port authorities identify ships at high risks. The performance of these systems is difficult to be improved due to the limited available factors. This paper presents an improved risk assessment system, which is strengthened by web mining technique. This system employs profile-based wrapper to extract inspection details from inspection report web pages and adopts a template-matching-based method to extract new target features from deficiency details. By incorporating new target features, the risk assessment system based on Support Vector Machine is improved. Experimental results have shown that the new system improves the risk assessment accuracy effectively.