SHIP COLLISION RISK ASSESSMENT USING CLUSTERING ALGORITHMS AND THEORY OF BELIEF FUNCTIONS

Abstract

Ship collision risk assessment is an essential process undertaken to identify potential hazards that may cause collisions in maritime operations. This process involves analyzing a lot of different factors such as weather conditions, traffic density, visibility,.... Therefore, in research activities, the most basic factors determines the extent of the risk is the calculation time and correction decisions. Proven effective methods such as fuzzy logic and neural networks have relatively but long computation time. The paper proposes a new other method using the theory of confidence functions with higher efficiency.