TY - GEN
T1 - AIS Data Pre-Processing for Trajectory Clustering Data Preparation
AU - Hartawan, I. Putu Noven
AU - Widyantara, I. Made Oka
AU - Karyawati, A. A.I.N.E.
AU - Er, Ngurah Indra
AU - Artana, Ketut Buda
AU - Sastra, Nyoman Putra
N1 - Publisher Copyright:
© 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - Automatic Identification System (AIS) is radio navigation equipment for a vessel that has been required by the International Maritime Organization (IMO). The AIS dataset contains vessel information and vessel position. Various analyses can utilize the availability of AIS's extensive data history. In those analyses, it is necessary to know the vessel's trajectory pattern. With the development of data mining techniques, vessel trajectory patterns can be obtained by clustering. However, AIS data cannot be directly used in the clustering process. Data pre-processing is required due to the complexity of the trajectory data and the need to reduce noises in AIS data with large sizes. This study proposes a pre-processing model with data cleaning, trajectory extraction, and trajectory compression stages. Results show that the proposed model can reduce noise and, at the same time, reduce rows that will affect the following clustering process.
AB - Automatic Identification System (AIS) is radio navigation equipment for a vessel that has been required by the International Maritime Organization (IMO). The AIS dataset contains vessel information and vessel position. Various analyses can utilize the availability of AIS's extensive data history. In those analyses, it is necessary to know the vessel's trajectory pattern. With the development of data mining techniques, vessel trajectory patterns can be obtained by clustering. However, AIS data cannot be directly used in the clustering process. Data pre-processing is required due to the complexity of the trajectory data and the need to reduce noises in AIS data with large sizes. This study proposes a pre-processing model with data cleaning, trajectory extraction, and trajectory compression stages. Results show that the proposed model can reduce noise and, at the same time, reduce rows that will affect the following clustering process.
KW - AIS
KW - clustering
KW - data pre-processing
KW - trajectory
UR - http://www.scopus.com/inward/record.url?scp=85124790527&partnerID=8YFLogxK
U2 - 10.1109/ICARES53960.2021.9665187
DO - 10.1109/ICARES53960.2021.9665187
M3 - Conference contribution
AN - SCOPUS:85124790527
T3 - Proceedings of the 2021 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2021
BT - Proceedings of the 2021 IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 5th IEEE International Conference on Aerospace Electronics and Remote Sensing Technology, ICARES 2021
Y2 - 3 November 2021 through 4 November 2021
ER -