FCM 기법을 이용한 해양사고 협력 데이터베이스 교환 시스템 연구

Abstract

Marine accidents have always caused huge economic losses as well as environmental pollution. The analysis of past accident cases, reviewing experience and lessons, is important and necessary for preventing marine accidents. With the same subject above, the Korean Maritime Safety Tribunal provides past marine accident DB and associated retrieval system on its homepage. However, most of the marine events that occurred were not due to a single reason, but multiple ones. In addition, one marine event could often come under several categories. However, the retrieval system’s DB, now used on the Korean Maritime Safety Tribunal Homepage, failed to retrieve according to multi-reasons or multi-categories because it was built based on single category or other information. In order to solve this problem, a new retrieval system will be proposed in this paper; the system will use the linguistic label to describe the cluster after analyzing the relational properties between marine accidents and will cluster by FCM algorithm, then will add an interface to allow users to get the results they want through choosing multiple reasons or multiple categories.