DiBa: A Data-Driven Bayesian Algorithm for Sleep Spindle Detection

Author

Babadi, Behtash ; McKinney, Scott M. ; Tarokh, Vahid ; Ellenbogen, Jeffrey M.

Author_Institution

Dept. of Anesthesia, Critical Care & Pain Med., Boston, MA, USA

Volume

59

Issue

2

fYear

2012

Firstpage

483

Lastpage

493

Abstract

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.

Keywords

Karhunen-Loeve transforms; electroencephalography; neurophysiology; sleep; Bayesian hypothesis testing; EEG; EEG event detection; Karhunen-Loeve transform; data-driven Bayesian algorithm; electroencephalography; flexibility; instantaneous probability; scalability; sleep spindle detection; spontaneous brain rhythms; standard methods; Bayesian methods; Covariance matrix; Eigenvalues and eigenfunctions; Electroencephalography; Equations; Sleep; Transforms; Bayesian methods; Karhunen–Loève (KL) transform; electroencephalography (EEG); medical signal detection; sleep spindles; Adult; Algorithms; Bayes Theorem; Brain; Electroencephalography; Female; Humans; Male; Middle Aged; Signal Processing, Computer-Assisted; Sleep Stages;

fLanguage

English

Journal_Title

Biomedical Engineering, IEEE Transactions on

Publisher

ieee

ISSN

0018-9294

Type

jour

DOI

10.1109/TBME.2011.2175225

Filename

6072256