IAES International Journal of Artificial Intelligence (IJ-AI) Vol. 12, No. 1, March 2023, pp. 1~11 ISSN: 2252-8938, DOI: 10.11591/ijai.v12.i1.pp1-11  1 Journal homepage: http://ijai.iaescore.com Automatic identification system-based trajectory clustering framework to identify vessel movement pattern I Made Oka Widyantara 1 , I Putu Noven Hartawan 2 , Anak Agung Istri Ngurah Eka Karyawati 3 , Ngurah Indra Er 1 , Ketut Buda Artana 4 1 Department of Electrical Engineering, Faculty of Engineering, Udayana University, Bali, Indonesia 2 Postgraduate Program of Electrical Engineering, Faculty of Engineering, Udayana University, Bali, Indonesia 3 Department of Computer Science, Faculty of Math and Natural Science, Udayana University, Bali, Indonesia 4 Department of Marine Engineering, Faculty of Marine Technology, Sepuluh Nopember Institute of Technology, Surabaya, Indonesia Article Info ABSTRACT Article history: Received Nov 20, 2021 Revised Jul 20, 2022 Accepted Aug 18, 2022 Automatic identification system (AIS) is a vessel radio navigation equipment that has been determined by international maritime organization (IMO). Historical AIS data can be utilized for anomaly detection, trajectory prediction, and vessel trajectory planning. These benefits can be achieved by identifying the vessel's trajectory pattern through trajectory clustering. However, more effort is needed in trajectory clustering using AIS data due to their large volume and the significant number of deficiencies. In addition, trajectory clustering cannot be directly applied to trajectory data, which also applies to vessel trajectory. Therefore, we propose a trajectory clustering framework by combining douglas peucker (DP), longest common subsequence (LCSS), multi-dimensional scaling (MDS), and density-based spatial clustering of applications with noise (DBSCAN). Our experiments, carried out with AIS data for the Lombok Strait, Indonesia, showed that the trajectory compression with DP significantly accelerates the similarity measurement process. Moreover, we found that the LCSS is the optimal algorithm for similarity measurement of vessel trajectories based on AIS data. We also applied the right combination of MDS and DBSCAN in density-based clustering. The proposed framework can distinguish trajectoriess in different directions, identify the noise, and produce good quality clusters in relatively fast total processing time. Keywords: Automatic identification system Data mining Density-based spatial clustering of applications with noise Longest common subsequence Trajectory Vessel This is an open access article under the CC BY-SA license. Corresponding Author: I Made Oka Widyantara Department of Electrical Engineering, Faculty of Engineering, Udayana University Kampus Unud Road, Jimbaran, Bali, Indonesia Email: oka.widyantara@unud.ac.id 1. INTRODUCTION The automatic identification system (AIS) is a radio navigation device that uses very high frequency (VHF) to transmit vessel data automatically between vessels at sea and receivers on land. Every vessel over 300 gross tons (GT) must have an AIS signal transmitter, according to the international maritime organization (IMO) regulation [1]–[4]. Vessel location, speed, lane, direction, turn rate, destination, and expected time of arrival are among the dynamic data supplied by AIS. Static data as are vessel name, vessel maritime mobile service identity (MMSI ID), message identity (ID), vessel type, vessel size, and current time also provided. Furthermore, AIS data has the advantage of providing the highest volume of vessel position data with wide water area coverage [5] and commercially accessible or open-source ais data, which other vessel reporting systems do not have [6]. Many things may be evaluated using AIS data due to the vast