de Jong, Ivo (2019) Adapting CoSyNE to fight forest fires. Bachelor's Thesis, Artificial Intelligence.
|
Text
AI_BA_2019_IVODEJONG.pdf Download (539kB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
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 name: | Wiering, M.A. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 24 Jul 2019 |
| Last Modified: | 24 Jul 2019 12:01 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/20404 |
Actions (login required)
 |
View Item |