Thesis
Learning relationships between detected activities, sleep patterns, and physiological data
Washington State University
Master of Science (MS), Washington State University
2011
Handle:
https://hdl.handle.net/2376/100476
Abstract
The U.S Census Bureau has estimated that by 2050, the number of people with the age of 65 and above will be over 80 million. The present development of the demography of elderly people in the U.S as well as other parts of the world will generate a shortage of caretakers for elderly people in the near future. Further, older adults prefer staying in their own houses rather than staying at an elder care facility. Technological advancements are currently moving towards building a smart home system than can monitor every activity performed by on older adult using motion sensors, wearable sensors, object sensors etc. We focus on three topics that are of great importance to understand the well-being of the elderly population. The first topic is activity prediction using data collected from a wearable Actigraph sensor. We use machine learning algorithms to identify activities from this data. The second part of this thesis concentrates on predicting the sleep quality of older adults. Unfortunately many people have a poor understanding of the factors that influence their daily sleep quality. Many psychology studies have concentrated on identifying sleep quality using a user-annotated sleep diary. However, the presence of cognitive disabilities may influence their impression of sleep quality. In this thesis, we focus on identifying the sleep quality of people with cognitive disabilities. The third part of this thesis focuses on finding correlations between blood glucose levels and activities of people with diabetes. We find that there exists high correlation between glucose levels during sleep and the activities they perform during the day
Metrics
16 Record Views
Details
- Title
- Learning relationships between detected activities, sleep patterns, and physiological data
- Creators
- Raghavendiran Srinivasan
- Contributors
- Diane J. Cook (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, Wash. :
- Identifiers
- 99900525032101842
- Language
- English
- Resource Type
- Thesis