Abstract

One of vessel monitoring systems which employs predetermined equipment to discover the movements and activities of vessels is AIS (Automatic Identification System). AIS contains the ship data either static (ship name, ship size, sailing time) or dynamic data (ship speed, rate of turn, ship heading). The ship tracking information system can be accessed by public, but manual monitoring will be difficult to do, given that data is increasingly heterogeneous and complex as well as its volumes increase exponentially. As a result, a more efficient method of data mining and processing are needed. In this study, k-NN algorithm is applied with the aim of classifying ships sailing in Indonesian waters. The algorithm is tested on real time AIS database using k-NN and the neighborhood component analysis (NCA). The result shows that NCA,KNN has higher accuracy than using k-NN on original classifier.

Original languageEnglish
Title of host publicationProceedings - 2019 International Seminar on Application for Technology of Information and Communication
Subtitle of host publicationIndustry 4.0: Retrospect, Prospect, and Challenges, iSemantic 2019
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages331-335
Number of pages5
ISBN (Electronic)9781728138329
DOIs
Publication statusPublished - Sept 2019
Event2019 International Seminar on Application for Technology of Information and Communication, iSemantic 2019 - Semarang, Indonesia
Duration: 21 Sept 201922 Sept 2019

Publication series

NameProceedings - 2019 International Seminar on Application for Technology of Information and Communication: Industry 4.0: Retrospect, Prospect, and Challenges, iSemantic 2019

Conference

Conference2019 International Seminar on Application for Technology of Information and Communication, iSemantic 2019
Country/TerritoryIndonesia
CitySemarang
Period21/09/1922/09/19

Keywords

  • AIS
  • Data Mining
  • K-NN
  • Neighborhood component analysis
  • Vessel

Fingerprint

Dive into the research topics of 'Classification of Ship-Based Automatic Identification Systems Using K-Nearest Neighbors'. Together they form a unique fingerprint.

Cite this