Thesis
Modifying smart home to smart phone notifications using reinforcement learning algorithms
Washington State University
Master of Science (MS), Washington State University
2017
Handle:
https://hdl.handle.net/2376/102547
Abstract
Given the number of applications available on today's devices, the sheer volume of smart phone notifications can already be overwhelming. This burden will only get worse with the exploding popularity of the Internet of Things (IoT), where each IoT device sends its own set of notifications to a user's phone. The WSU Solar Smart Home looks to relieve some of that burden by modifying notifications using reinforcement learning. A user gives feedback to the system, and the system modifies which notifications the user sees and when. This study investigates a new set of learning algorithms, Strategy-Aware Bayesian Learning (SABL) and Inferring Strategy-Aware Bayesian Learning (I-SABL) to test their efficacy in assisting with notification selection. This research suggests that while SABL and I-SABL show promise for some users, there may not be a singular algorithm that can properly learn all possible users needs.
Metrics
Details
- Title
- Modifying smart home to smart phone notifications using reinforcement learning algorithms
- Creators
- Amanda Leah Zulas
- Contributors
- Matthew E. Taylor (Degree Supervisor)
- Awarding Institution
- Washington State University
- Academic Unit
- Electrical Engineering and Computer Science, School of
- Theses and Dissertations
- Master of Science (MS), Washington State University
- Publisher
- Washington State University; [Pullman, Washington] :
- Identifiers
- 99900525094501842
- Language
- English
- Resource Type
- Thesis