- 186 views
- 196 downloads
Sound Relaxation: Soundscape Exploration using Reinforcement Learning
-
- Author / Creator
- Guo, Yourui
-
High stress levels and depression are commonly observed in hospitalized patients, which may negatively impact them on recovery after surgery. Sound therapy has been widely used for its effectiveness in increasing relaxation and reducing stress levels, and one could also fine-tune music features such as pitch, volume and reverb to improve sleep quality and reduce anxiety. Our sound therapy project aims to select and fine-tune a soundscape that maximizes a subject's relaxation level. We simplified this problem and formulated it as a reinforcement learning problem where the goal is to select a soundscape, and determine the best volume setting for each of its component sounds. For the virtual subject experiment, we tested RTA*, UCT and few baseline algorithms. We also conducted experiments on human subjects, divided into a treatment group that listen to sounds selected by the UCT algorithm and a control group that listen to sounds selected by a human experimenter. The UCT algorithm displayed the same performance as the human, suggesting that sound therapy can be automated using UCT.
-
- Subjects / Keywords
-
- Graduation date
- Fall 2020
-
- Type of Item
- Thesis
-
- Degree
- Master of Science
-
- License
- Permission is hereby granted to the University of Alberta Libraries to reproduce single copies of this thesis and to lend or sell such copies for private, scholarly or scientific research purposes only. Where the thesis is converted to, or otherwise made available in digital form, the University of Alberta will advise potential users of the thesis of these terms. The author reserves all other publication and other rights in association with the copyright in the thesis and, except as herein before provided, neither the thesis nor any substantial portion thereof may be printed or otherwise reproduced in any material form whatsoever without the author's prior written permission.