Building a hybrid algorithm based decision support system to prevent ship collisions

Abstract

Decision support systems constitute the focus of many studies in the maritime industry as vessel accidents are often caused by human errors. In this study, an anti-collision decision support system is proposed. The system consists of three main parts. An artificial neural network system capable of predicting the forward position of ships, a fuzzy logic system that calculates which of the surrounding ships is at greater risk of collision, and a collision avoidance route using the CSGA (Cuckoo Search-Genetic Algorithm) algorithm. In this study, scenarios have been created in order to measure the success of collision prevention system. The CSGA algorithm used in the calculation of collision prevention routes and the ACO (Ant Colony Optimization), PSO (Particle Swarm Optimization), and GA (Genetic Algorithm) algorithms previously used in the literature were also used for calculation and the results compared in terms of efficiency. While measuring the efficiency of algorithms; the time spent on the calculation and the efficiency of the recommended collision avoidance routes are considered. In the collision avoidance system with the CSGA algorithm, on average, the calculation times were 29.47 times faster than ACO, 5.78 times faster than PSO, and 2.72 times faster than GA. Considering the appropriateness of the paths calculated by the algorithms, the CSGA algorithm has found an average of %7. 85 in comparison to PSO, %2.62 in comparison to PSA, and %1.18 in comparison to GA.