Browsing by Author "Burger, Christiaan Neil"

Now showing 1 - 1 of 1
  • Thumbnail Image
    Item
    An extension of the linear regression model for improved vessel trajectory prediction utilising a priori AIS Information
    (Stellenbosch : Stellenbosch University, 2022-04) Burger, Christiaan Neil; Grobler, Trienko Lups; Kleynhans, Waldo; Stellenbosch University. Faculty of Science. Dept. of Computer Science.
    ENGLISH ABSTRACT: As maritime activities increase globally, there is a greater dependency on technology in monitoring, control and surveillance of vessel activity. One of the most prominent systems for monitoring vessel activity is the Automatic Identification System (AIS). An increase in both vessels fitted with AIS transponders, and satellite- and terrestrial receivers has resulted in a significant increase in AIS messages received globally. This resultant rich spatial and temporal data source related to vessel activity provides analysts with the ability to perform enhanced vessel movement analytics, of which a pertinent example is the improvement of vessel location predictions. In this thesis, we propose a novel method for predicting future locations of vessels by making use of historic AIS data. The proposed method extends a Linear Regression Model (LRM), utilising historic AIS movement data in the form of a priori generated spatial maps of the course over ground (LRMAC). The LRMAC has low complexity and is programmatically easy to implement, and attains accurate prediction results. We first compare the LRM with a Discrete Kalman Filter (DKF) on linear trajectories. We then extend the LRM to form the LRMAC. The LRMAC is compared to another method in literature called the Single Point Neighbour Search (SPNS). For the use case of predicting Cargo and Tanker vessel trajectories, with a prediction horizon of up to six hours, the LRMAC has an improved execution time and performance compared to the SPNS.