Grouping Pilots' Maneuvering Types According to Berthing Velocity Using Agglomerative Clustering Algorithm

Abstract

A pilot guides a ship through a safe waterway based on extensive experience and knowledge of the region for piloting so that the ship can berth quickly and safely. There are insufficient studies on pilots who play crucial roles in pilotage, and most of the available studies have focused on psychological stress or tension. In this study, we group pilots through quantitative analysis of data to help in the safety management of pilots. In particular, berthing velocity and berthing energy were employed as basic data, and the mean and standard deviation values for each pilot after preprocessing were used for analysis. As a result of using the agglomerative clustering algorithm, we could group pilots into three types: cautious, efficient, and hazardous. Further, analysis of variance (ANOVA) showed that there was a significant difference between the cautious and hazardous types.