Format

Send to

Choose Destination
Sensors (Basel). 2019 Jan 31;19(3). pii: E601. doi: 10.3390/s19030601.

Quality Assessment of Single-Channel EEG for Wearable Devices.

Author information

1
hlSorbonne Université, UPMC Univ. Paris 06, INSERM U-1127, CNRS UMR-7225, Institut du Cerveau et de la Moelle Épinière (ICM), Groupe Hospitalier Pitié Salpêtrière-Charles Foix, 75013 Paris, France. grosselin.fanny@gmail.com.
2
myBrainTechnologies, 75010 Paris, France. grosselin.fanny@gmail.com.
3
myBrainTechnologies, 75010 Paris, France. xavier.navarro@mybraintech.com.
4
myBrainTechnologies, 75010 Paris, France. alessia.vozzi@gmail.com.
5
myBrainTechnologies, 75010 Paris, France. katerina.pandremmenou@mybraintech.com.
6
hlSorbonne Université, UPMC Univ. Paris 06, INSERM U-1127, CNRS UMR-7225, Institut du Cerveau et de la Moelle Épinière (ICM), Groupe Hospitalier Pitié Salpêtrière-Charles Foix, 75013 Paris, France. fabrizio.devicofallani@gmail.com.
7
INRIA, Aramis Project-Team, F-75013 Paris, France. fabrizio.devicofallani@gmail.com.
8
myBrainTechnologies, 75010 Paris, France. yohan.attal@mybraintech.com.
9
CNRS UMR-7225, Groupe Hospitalier Pitié-Salpêtrière-Charles Foix, 75013 Paris, France. neurodynamicslab@gmail.com.

Abstract

The recent embedding of electroencephalographic (EEG) electrodes in wearable devices raises the problem of the quality of the data recorded in such uncontrolled environments. These recordings are often obtained with dry single-channel EEG devices, and may be contaminated by many sources of noise which can compromise the detection and characterization of the brain state studied. In this paper, we propose a classification-based approach to effectively quantify artefact contamination in EEG segments, and discriminate muscular artefacts. The performance of our method were assessed on different databases containing either artificially contaminated or real artefacts recorded with different type of sensors, including wet and dry EEG electrodes. Furthermore, the quality of unlabelled databases was evaluated. For all the studied databases, the proposed method is able to rapidly assess the quality of the EEG signals with an accuracy higher than 90%. The obtained performance suggests that our approach provide an efficient, fast and automated quality assessment of EEG signals from low-cost wearable devices typically composed of a dry single EEG channel.

KEYWORDS:

artefact detection; electroencephalography (EEG); muscular artefacts; quality assessment; single-channel EEG; wearable systems

PMID:
30709004
PMCID:
PMC6387437
DOI:
10.3390/s19030601
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for Multidisciplinary Digital Publishing Institute (MDPI) Icon for PubMed Central
Loading ...
Support Center