EEG-based mental workload level estimation using deep learning models

Kunjira Kingphai; Yashar Moshfeghi

EEG-based mental workload level estimation using deep learning models

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

Abstract

Deep learning-based approaches have recently received much attention and managed to accurately capture variance characteristics in the Electroencephalography (EEG) signals. In this paper, we aim to classify the subject’s mental workload (MWL) level from EEG signal by using deep learning models named Stacked Gated Recurrent Unit (GRU), Bidirectional GRU (BGRU), BGRU-GRU, Stacked Long-Short Term Memory (LSTM), Bidirectional LSTM (BLSTM), BLSTM-LSTM and Convolutional Neural Network (CNN). The classification was performed on a publicly available mental workload dataset, STEW. Our encouraging results show the potential of deep learning models for MWL level detection.

Original language	English
Title of host publication	Contemporary Ergonomics & Human Factors 2022
Subtitle of host publication	Proceedings for the Annual Conference of the Chartered Institute of Ergonomics and Human Factors
Editors	Nora Balfe, David Golightly
Place of Publication	Birmingham
Number of pages	3
Publication status	Published - 24 Jun 2022

Keywords

EEG
deep learning
mental workload classification

Cite this

@inproceedings{7adb9fd50e9e458da418e4821c5e15d2,

title = "EEG-based mental workload level estimation using deep learning models",

abstract = "Deep learning-based approaches have recently received much attention and managed to accurately capture variance characteristics in the Electroencephalography (EEG) signals. In this paper, we aim to classify the subject{\textquoteright}s mental workload (MWL) level from EEG signal by using deep learning models named Stacked Gated Recurrent Unit (GRU), Bidirectional GRU (BGRU), BGRU-GRU, Stacked Long-Short Term Memory (LSTM), Bidirectional LSTM (BLSTM), BLSTM-LSTM and Convolutional Neural Network (CNN). The classification was performed on a publicly available mental workload dataset, STEW. Our encouraging results show the potential of deep learning models for MWL level detection.",

keywords = "EEG, deep learning, mental workload classification",

author = "Kunjira Kingphai and Yashar Moshfeghi",

year = "2022",

month = jun,

day = "24",

language = "English",

isbn = "9781999652746",

editor = "Nora Balfe and David Golightly",

booktitle = "Contemporary Ergonomics & Human Factors 2022",

}

EEG-based mental workload level estimation using deep learning models. / Kingphai, Kunjira; Moshfeghi, Yashar.
Contemporary Ergonomics & Human Factors 2022: Proceedings for the Annual Conference of the Chartered Institute of Ergonomics and Human Factors. ed. / Nora Balfe; David Golightly. Birmingham, 2022.

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - EEG-based mental workload level estimation using deep learning models

AU - Kingphai, Kunjira

AU - Moshfeghi, Yashar

PY - 2022/6/24

Y1 - 2022/6/24

N2 - Deep learning-based approaches have recently received much attention and managed to accurately capture variance characteristics in the Electroencephalography (EEG) signals. In this paper, we aim to classify the subject’s mental workload (MWL) level from EEG signal by using deep learning models named Stacked Gated Recurrent Unit (GRU), Bidirectional GRU (BGRU), BGRU-GRU, Stacked Long-Short Term Memory (LSTM), Bidirectional LSTM (BLSTM), BLSTM-LSTM and Convolutional Neural Network (CNN). The classification was performed on a publicly available mental workload dataset, STEW. Our encouraging results show the potential of deep learning models for MWL level detection.

AB - Deep learning-based approaches have recently received much attention and managed to accurately capture variance characteristics in the Electroencephalography (EEG) signals. In this paper, we aim to classify the subject’s mental workload (MWL) level from EEG signal by using deep learning models named Stacked Gated Recurrent Unit (GRU), Bidirectional GRU (BGRU), BGRU-GRU, Stacked Long-Short Term Memory (LSTM), Bidirectional LSTM (BLSTM), BLSTM-LSTM and Convolutional Neural Network (CNN). The classification was performed on a publicly available mental workload dataset, STEW. Our encouraging results show the potential of deep learning models for MWL level detection.

KW - EEG

KW - deep learning

KW - mental workload classification

UR - https://publications.ergonomics.org.uk/publications/eeg-based-mental-workload-level-estimation-using-deep-learning-models.html

M3 - Conference contribution book

SN - 9781999652746

BT - Contemporary Ergonomics & Human Factors 2022

A2 - Balfe, Nora

A2 - Golightly, David

CY - Birmingham

ER -

EEG-based mental workload level estimation using deep learning models

Abstract

Keywords

Other files and links

Fingerprint

Cite this