TY - JOUR
T1 - DiBa
T2 - A Data-Driven Bayesian Algorithm for Sleep Spindle Detection
AU - Babadi, Behtash
AU - Babadi, Behtash
AU - McKinney, Scott M.
AU - Tarokh, Vahid
AU - Ellenbogen, Jeffrey M.
AU - Ellenbogen, Jeffrey M.
PY - 2012/2
Y1 - 2012/2
N2 - 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.
AB - 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.
UR - http://www.scopus.com/inward/record.url?scp=84861167363&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=84861167363&partnerID=8YFLogxK
U2 - 10.1109/TBME.2011.2175225
DO - 10.1109/TBME.2011.2175225
M3 - Article
C2 - 22084041
AN - SCOPUS:84861167363
SN - 0018-9294
VL - 59
SP - 483
EP - 493
JO - IEEE Transactions on Biomedical Engineering
JF - IEEE Transactions on Biomedical Engineering
IS - 2
ER -