Discovery of Patterns in Sleep Data
This research project aims to develop machine learning
techniques for automated discovery of meaningful patterns
in human sleep data. Our work to date has yielded an association
mining approach for exploratory analysis of sleep data
(Laxminarayan et al, 2005),
including tight bounds on the false discovery rate
(Laxminarayan et al, 2006),
construction of a terabyte-scale database of anonymized
polysomnographic recordings and health histories, and
discovery of naturally occurring subgroups of sleep
studies, or "sleep types", based on the stage composition of sleep
(Khasawneh et al, 2010 and 2011). Planned work includes modeling of
the dynamics of sleep. An initial step in this direction
is presented in (Usher et al, 2012).
Publications (asterisks denote student co-authors)
-
F. W. Usher*, C. Wang*, S. A. Alvarez, C. Ruiz, and M. Moonis.
"Machine Learning of Human Sleep Patterns based on Stage Bout Durations",
full paper (acceptance rate: 65/522 = 12.5%),
Proc. HEALTHINF 2012 (Fifth International Conference on Health
Informatics),
in conjunction with BIOSTEC 2012, Vilamoura, Portugal, Feb. 1-4, 2012
-
A. Khasawneh*, S. A. Alvarez, C. Ruiz, S. Misra*, and M. Moonis.
"EEG and ECG Characteristics of Human Sleep Composition Types",
full paper (acceptance rate: 48/538 = 8.9%), Best Paper Award,
Proc. HEALTHINF 2011 (Fourth International Conference on Health
Informatics),
in conjunction with BIOSTEC 2011, Rome, Italy, Jan. 26-29, 2011, 97-106
-
A. Khasawneh*, S. A. Alvarez, C. Ruiz, S. Misra*, and M. Moonis.
"Discovery of Sleep Composition Types using Expectation-Maximization",
Proc. 23rd IEEE International Symposium on Computer-Based Medical Systems
(CBMS 2010), Perth, Australia, Oct. 12-15, 2010
-
Laxminarayan*, P., Alvarez, S.A., Ruiz, C., Moonis, M.,
"Mining Statistically Significant Associations for Exploratory Analysis
of Human Sleep Data",
IEEE Transactions on Information Technology in Biomedicine,
vol 10, no 3 (July 2006), 440-450
-
Laxminarayan*, P., Ruiz, C., Alvarez, S.A., Moonis, M.,
"Mining Associations over Human Sleep Time Series",
Proc. 18th IEEE International Symposium on Computer-Based
Medical Systems (A. Tsymbal and P. Cunningham, eds.),
IEEE Computer Society Press, Dublin, Ireland, June 2005, 323-328
Project Personnel
Faculty
- Sergio A. Alvarez, Ph.D. (Boston College)
- Carolina Ruiz, Ph.D. (Worcester Polytechnic Institute)
- Majaz Moonis, M.D. (U. of Massachusetts Medical School and Day Kimball Hospital)
Current Students
- Chiying Wang
- Amro Khasawneh
Alumni
- Shivin Misra, M.S.
- Parameshvyas Laxminarayan, M.S.