Veselý, Viktor (2022) Chaos Control: Controlling Heart Arrhythmia Using an Echo State Network Controller. Bachelor's Thesis, Artificial Intelligence.
|
Text
chaos_control_thesis_vesely.pdf Download (1MB) | Preview |
|
![[img]](https://fse.studenttheses.ub.rug.nl/style/images/fileicons/text.png) |
Text
toestemming.pdf Restricted to Registered users only Download (131kB) |
Abstract
The regular propagation of the action potential on heart tissues is crucial for the optimal heart muscle contractions. Obstacles to the heart tissues such as scars can cause the propagation to become chaotic - small differences amplify over time and can become fatal for the diseased person. I used an echo state network (ESN) controller to investigate the effectiveness of the method on controlling a simulated heart arrhythmia, which can be modelled as chaotic action potential propagation. ESNs have been previously showed to predict a chaotic time series with unprecedented precision. I altered an existing computational heart model to exhibit such a chaotic dynamics. Whilst the validation error of the controller remained reasonably low, it was unable to control the arrhythmia. The controller performed significantly better on a simpler chaos control task (with 2 dimensions instead of 2560), suggesting that the original control task was too complex and unfeasible with our computational resources.
| Item Type: | Thesis (Bachelor's Thesis) |
|---|---|
| Supervisor name: | Jaeger, H. and Borst, J.P. |
| Degree programme: | Artificial Intelligence |
| Thesis type: | Bachelor's Thesis |
| Language: | English |
| Date Deposited: | 15 Aug 2022 09:28 |
| Last Modified: | 15 Aug 2022 09:28 |
| URI: | https://fse.studenttheses.ub.rug.nl/id/eprint/28341 |
Actions (login required)
 |
View Item |