Mining of missing ship trajectory pattern in automatic identification system

Abstract

Background/Objectives: Ship trajectories in Vessel Traffic Service (VTS) system are generated by integrating the Automatic Identifica-tion System (AIS) or Radar system. However, the AIS system has missing data section caused by AIS device problems, radio jamming, and so on. These data have been confusing ship navigators and VTS operators. Methods/Statistical analysis: In order to extract missing AIS data, time intervals of sequent points from each ship trajectory are calculated. The section with missing AIS data is above a threshold time limit defined by characteristics. Using k-means algorithm, missing AIS data were clustered into several clusters stored by ship's ID and sailing direction. Using association rule mining analysis, meaningful association pattern were calculated by missing AIS dataset. Findings: As a result of the association rule mining, we found several missing AIS situation patterns. In case of the west route, the proba-bility of missing AIS situation is high when they enter the east and passenger routes. Also, the probability of missing AIS situation of passing the passenger route is high when that ship enter the LNG, east and west routes. Improvements/Applications: These results can be used to predict the probability of missing AIS data in VTS system.