Feature Extraction and Selection for EEG and Motion Data in Tasks of the Mental Status Assessing

Alexey Syskov, Vasilii Borisov, Vsevolod Tetervak, Vladimir Kublanov

2018

Abstract

In the paper the results of extracting and selection the features of EEG data and accelerometer for mental status evaluation are shown. We have used 14 channel wireless EEG-system Emotiv EPOC+ with accelerometer (motional data - MD) for short-term recording under several functional states for 10 healthy subjects: Functional rest (rest state), TOVA-test (mental load), Hyperventilation (physical load) and Aftereffect (after test state). We then extracted core features from EEG-only and MD-only data using principal component analysis. After that, supervised learning methods were used for mental state classification: EEG-only core features for AF3, T7, O1, T8, AF4 channels, MD-only core features and EEG- MD integrated core features. Experimental results showed that integrated core features for mental status evaluation have higher prediction accuracy 92,0% for decision tree method.

Paper Citation

in Harvard Style

Syskov A., Borisov V., Tetervak V. and Kublanov V. (2018). Feature Extraction and Selection for EEG and Motion Data in Tasks of the Mental Status Assessing . In Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 1: BIODEVICES; ISBN 978-989-758-277-6, SciTePress, pages 164-172. DOI: 10.5220/0006593001640172

in Bibtex Style

@conference{biodevices18,
author={Alexey Syskov and Vasilii Borisov and Vsevolod Tetervak and Vladimir Kublanov},
title={Feature Extraction and Selection for EEG and Motion Data in Tasks of the Mental Status Assessing },
booktitle={Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 1: BIODEVICES},
year={2018},
pages={164-172},
publisher={SciTePress},
organization={INSTICC},
doi={10.5220/0006593001640172},
isbn={978-989-758-277-6},
}

in EndNote Style

TY - CONF

JO - Proceedings of the 11th International Joint Conference on Biomedical Engineering Systems and Technologies (BIOSTEC 2018) - Volume 1: BIODEVICES
TI - Feature Extraction and Selection for EEG and Motion Data in Tasks of the Mental Status Assessing
SN - 978-989-758-277-6
AU - Syskov A.
AU - Borisov V.
AU - Tetervak V.
AU - Kublanov V.
PY - 2018
SP - 164
EP - 172
DO - 10.5220/0006593001640172
PB - SciTePress