Real-Time Detection of Sleep Arousals with a Head-Mounted Accelerometer


METADATA ONLY
Loading...

Date

2023

Publication Type

Conference Paper

ETH Bibliography

yes

Citations

Altmetric
METADATA ONLY

Data

Rights / License

Abstract

Wearable electroencephalography (EEG) enables real-time interactions with the sleeping brain in real-life settings. An important parameter to monitor during these interactions are sleep arousals, i.e. temporary increases in EEG frequency, that compose sleep dynamics, but are challenging to detect without delay. We describe the development of an EEG- and accelerometer(ACC)-based sensing approach to detect arousals in real-time. We investigated the ability of these sensing modalities to timely and accurately detect arousals. When evaluated on 6 nights of mobile recordings, ACC had a median real-time delay of 2 s and was therefore better suited for an early detection of arousals than EEG (4.7 s). The detection performance was independent of sleep stages, but worked better on longer arousals. Our results demonstrate that a head-mounted ACC might be a cost-effective and easy-to-integrate solution for arousal detection where short delays are important or EEG signals are not available.

Publication status

published

Editor

Book title

2023 45th Annual International Conference of the IEEE Engineering in Medicine & Biology Society (EMBC)

Journal / series

Volume

Pages / Article No.

10340686

Publisher

IEEE

Event

45th Annual International Conference of the IEEE-Engineering-in-Medicine-and-Biology-Society (EMBC 2023)

Edition / version

Methods

Software

Geographic location

Date collected

Date created

Subject

Accelerometers; Sleep; Electroencephalography; Real-time systems; Biology; Delays; Sensors

Organisational unit

01225 - D-ITET Zentr. f. projektbasiertes Lernen / D-ITET Center for Project-Based Learning

Notes

Funding

Related publications and datasets