An extension of the linear regression model for improved vessel trajectory prediction utilising a priori AIS Information
| dc.contributor.advisor | Grobler, Trienko Lups | en_ZA |
| dc.contributor.advisor | Kleynhans, Waldo | en_ZA |
| dc.contributor.author | Burger, Christiaan Neil | en_ZA |
| dc.contributor.other | Stellenbosch University. Faculty of Science. Dept. of Computer Science. | en_ZA |
| dc.date.accessioned | 2022-02-17T11:25:53Z | |
| dc.date.accessioned | 2022-04-29T09:18:53Z | |
| dc.date.available | 2022-02-17T11:25:53Z | |
| dc.date.available | 2022-04-29T09:18:53Z | |
| dc.date.issued | 2022-04 | |
| dc.description | Thesis (MSc)--Stellenbosch University, 2022. | en_ZA |
| dc.description.abstract | 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. | en_ZA |
| dc.description.abstract | AFRIKAANSE OPSOMMING: As gevolg van die toename in maritieme aktiwiteite wˆereldwyd, het die afhanklikheid van tegnologie in die monitering, beheer en toesig van vaartuigaktiwiteite ook toegeneem. Een van die mees prominente stelsels vir die monitering van vaartuigaktiwiteit is die Outomatiese Identifikasiestelsel (OIS). ’n Toename in vaartuie wat toegerus is met OIS-transponders, en die toename in satelliet- en terrestri¨ele ontvangers, het gelei tot ’n aansienlike groei in OIS-boodskappe wat wˆereldwyd ontvang is. Dit het weer gelei tot die toename in dataryke ruimte-temporele bronne, wat verband hou met vaartuigaktiwiteite. Dit gee ontleders die vermo¨e om gevorderde vaartuig-bewegingsanalise uit te voer, waarvan ’n toepaslike voorbeeld, die verbetering van vaartuig-liggingvoorspelling is. In hierdie tesis stel ons ’n nuwe strategie voor om toekomstige liggings van vaartuie te voorspel, wat gebruik maak van historiese OIS-data. Die voorgestelde metode brei ’n Lineˆere Regressie Model (LRM) uit, deur gebruik te maak van historiese bewegingsdata en ruimte kaarte van a priori koers oor grond inligting (LRMAK). Die LRMAK het ’n lae kompleksiteit en is programmaties eenvoudig om te implementeer, met relatiewe akkurate voorspelling resultate. Ons vergelyk eers die LRM met ’n Diskrete Kalman Filter (DKF) op lineˆere trajekte. Dan brei ons die LRM uit om die LRMAK te vorm. Die LRMAK word vergelyk met ’n ander metode in literatuur wat die Enkel-punt Buur soektog (EPBS) genoem word. In die geval van trajek-voorspelling vir vrag- en tenkwa-vaartuie, het die LRMAK ’n verbeterde uitvoeringstyd en is vergelykbaar met ’n ander algoritme in literatuur, die EPBS, tot en met ’n voorspellingstydperk van ses-ure. | af_ZA |
| dc.description.version | Masters | en_ZA |
| dc.format.extent | 168 pages | en_ZA |
| dc.identifier.uri | http://hdl.handle.net/10019.1/124543 | |
| dc.language.iso | en_ZA | en_ZA |
| dc.publisher | Stellenbosch : Stellenbosch University | en_ZA |
| dc.rights.holder | Stellenbosch University | en_ZA |
| dc.subject | Linear Regression Model | en_ZA |
| dc.subject | Automatic identification system (AIS) | en_ZA |
| dc.subject | Vessel trajectory prediction | en_ZA |
| dc.subject | Geospatial data mining | en_ZA |
| dc.subject | Data Mining | en_ZA |
| dc.subject | UCTD | en_ZA |
| dc.title | An extension of the linear regression model for improved vessel trajectory prediction utilising a priori AIS Information | en_ZA |
| dc.type | Thesis | en_ZA |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- burger_extension_2022.pdf
- Size:
- 26.69 MB
- Format:
- Adobe Portable Document Format
- Description: