Wearable low-latency sleep stage classifier

Author

Chemparathy, Aditi ; Kassiri, Hossein ; Salam, M. Tariqus ; Boyce, Richard ; Bekmambetova, Fadime ; Adamantidis, Antoine ; Genov, Roman

Author_Institution

Dept. of Electr. & Comput. Eng., Univ. of Toronto, Toronto, ON, Canada

fYear

2014

fDate

22-24 Oct. 2014

Firstpage

592

Lastpage

595

Abstract

A wearable microsystem for low-latency automatic sleep stage classification and REM sleep detection in rodents is presented. The detection algorithm is implemented digitally to achieve low latency and is optimized for low complexity and power consumption. The algorithm uses both EEG and EMG signals as inputs. Experimental results using off-line signals from nine mice show REM detection sensitivity and specificity of 81.69% and 93.83%, respectively, with a latency of 39μs. The system will be used in a non-disruptive closed loop REM sleep suppression microsystem to study the effects of REM sleep deprivation on memory consolidation.

Keywords

electroencephalography; electromyography; medical signal detection; medical signal processing; micromechanical devices; signal classification; sleep; EEG signals; EMG signals; REM detection sensitivity; REM detection specificity; REM sleep deprivation; REM sleep detection; memory consolidation; nondisruptive closed loop REM sleep suppression microsystem; off-line signals; power consumption; wearable low-latency automatic sleep stage classification; wearable microsystem; Accuracy; Electroencephalography; Electromyography; Field programmable gate arrays; Hardware; Sensitivity; Sleep;

fLanguage

English

Publisher

ieee

Conference_Titel

Biomedical Circuits and Systems Conference (BioCAS), 2014 IEEE

Conference_Location

Lausanne

Type

conf

DOI

10.1109/BioCAS.2014.6981795

Filename

6981795