DiBa: a data-driven Bayesian algorithm for sleep spindle detection.

Published

Journal Article

Although the spontaneous brain rhythms of sleep have commanded much recent interest, their detection and analysis remains suboptimal. In this paper, we develop a data-driven Bayesian algorithm for sleep spindle detection on the electroencephalography (EEG). The algorithm exploits the Karhunen-Loève transform and Bayesian hypothesis testing to produce the instantaneous probability of a spindle's presence with maximal resolution. In addition to possessing flexibility, transparency, and scalability, this algorithm could perform at levels superior to standard methods for EEG event detection.

Full Text

Duke Authors

Cited Authors

  • Babadi, B; McKinney, SM; Tarokh, V; Ellenbogen, JM

Published Date

  • February 2012

Published In

Volume / Issue

  • 59 / 2

Start / End Page

  • 483 - 493

PubMed ID

  • 22084041

Pubmed Central ID

  • 22084041

Electronic International Standard Serial Number (EISSN)

  • 1558-2531

International Standard Serial Number (ISSN)

  • 0018-9294

Digital Object Identifier (DOI)

  • 10.1109/tbme.2011.2175225

Language

  • eng