Dual approach for automated sleep spindles detection within EEG background activity in infant polysomnograms

Author

Held, Claudio M. ; Causa, Leonardo ; Estévez, Pablo ; Pérez, Claudio ; Garrido, Marcelo ; Algarín, Cecilia ; Peirano, Patricio

Author_Institution

Dept. of Electr. Eng., Chile Univ., Santiago, Chile

Volume

1

fYear

2004

fDate

1-5 Sept. 2004

Firstpage

566

Lastpage

569

Abstract

An automated system for sleep spindles detection within EEG background activity, combining two different approaches, is presented. The first approach applies detection criteria on the sigma-band filtered EEG signal, including fuzzy thresholds. The second approach mimics an expert´s procedure. A sleep spindle detection is validated if both approaches agree. The method was applied on a testing set, consisting of continuous sleep recordings of two patients, totaling 1132 epochs (pages). A total of 803 sleep spindles events were marked by the experts. Results showed an 87.7% agreement between the detection system and the medical experts.

Keywords

electroencephalography; medical signal detection; medical signal processing; paediatrics; sleep; EEG background activity; automated sleep spindles detection; fuzzy thresholds; infant polysomnograms; sigma-band filtered EEG signal; Electroencephalography; Electromyography; Electrooculography; Humans; Pathology; Pattern recognition; Pediatrics; Sleep; Support vector machine classification; Support vector machines; EEG; infants sleep; pattern recognition; sleep spindles;

fLanguage

English

Publisher

ieee

Conference_Titel

Engineering in Medicine and Biology Society, 2004. IEMBS '04. 26th Annual International Conference of the IEEE

Conference_Location

San Francisco, CA

Print_ISBN

0-7803-8439-3

Type

conf

DOI

10.1109/IEMBS.2004.1403220

Filename

1403220