Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/71126
Title: Predict marine vessels’ trajectory with machine learning methods
Authors: Cho, Siqi
Keywords: DRNTU::Engineering::Electrical and electronic engineering
Issue Date: 2017
Abstract: Machine learning techniques have been widely used in various industries to perform forecasting and predictions. One such application that is covered in this project is trajectory prediction of maritime vessels. Information on vessels, such as International Maritime Organisation (IMO) ship identification number, its position, speed over ground (SOG) and course over ground (COG) etc. are broadcasted via automatic identification system (AIS). Making use of the availability of historical AIS data, various machine learning techniques can be applied to make future trajectory prediction based on the vessel’s current motion. The predictions made can be then visualised onto a map for users such as ship captains at sea, and port managements on land to plan the path of the vessel sailing in the port areas. The use of prediction can also be able to spot anomalous vessel’s trajectory which might lead to collision. This could improve port management, traffic efficiency around port and reduce incidents of vessels collision. With safety in mind, bring about this project to design a system, comprises of multiple sub-systems to make prediction using various machine learning algorithms, utilising the predictions made to visualise onto a map.
URI: http://hdl.handle.net/10356/71126
Rights: Nanyang Technological University
Fulltext Permission: restricted
Fulltext Availability: With Fulltext
Appears in Collections:EEE Student Reports (FYP/IA/PA/PI)

Files in This Item:
File Description SizeFormat 
FYP_Report_v2.017.pdf
  Restricted Access
1.89 MBAdobe PDFView/Open

Page view(s)

238
Updated on May 9, 2021

Download(s) 50

23
Updated on May 9, 2021

Google ScholarTM

Check

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.