Javascript must be enabled for the correct page display

Adapting CoSyNE to fight forest fires

de Jong, Ivo (2019) Adapting CoSyNE to fight forest fires. Bachelor's Thesis, Artificial Intelligence.

[img]
Preview
Text
AI_BA_2019_IVODEJONG.pdf

Download (539kB) | Preview
[img] Text
Toestemming.pdf
Restricted to Registered users only

Download (118kB)

Abstract

Limiting the area burned in a forest fire can be done by digging out a circle where the fuel is removed so the fire cannot spread. Determining the size of this circle has previously been solved in simulations where the circle is determined by 8 points, set at varying distances with the neuroevolutionary algorithm ESP and having an agent navigate along these points by following the shortest path. This paper instead controls the distance of the points by an adaptation of CoSyNE, but the main focus lies on the navigation between these points. The performance is compared between shortest path navigation, navigation with an adaptation of CoSyNE, and the same adaption with the addition of dropconnect. These CoSyNE adaptations were given the input of shortest path navigation as a recommendation. While the CoSyNE navigation, particularly with the dropconnect addition, was able to find better solutions for each map than the shortest path, the exploration required for this gave both algorithms a worse average performance on each map.

Item Type: Thesis (Bachelor's Thesis)
Supervisor:
Supervisor nameSupervisor E mail
Wiering, M.A.M.A.Wiering@rug.nl
Degree programme: Artificial Intelligence
Thesis type: Bachelor's Thesis
Language: English
Date Deposited: 24 Jul 2019
Last Modified: 24 Jul 2019 12:01
URI: http://fse.studenttheses.ub.rug.nl/id/eprint/20404

Actions (login required)

View Item View Item