3D CNN based Multilevel Feature Fusion for Workload Estimation

Youngchul Kwak; Woo Jin Song; Byoung Kyong Min; Seong Eun Kim

doi:10.1109/BCI48061.2020.9061639

3D CNN based Multilevel Feature Fusion for Workload Estimation

Youngchul Kwak, Woo Jin Song, Byoung Kyong Min, Seong Eun Kim

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

Abstract

Mental workload is defined as the proportion of the information processing capability used to perform a task. High cognitive load requires additional resources that may reduce the processing efficiency and performance. Therefore, the technique of workload estimation can ensure a proper working environment to promote the working efficiency of each person. In this paper, we propose a three-dimensional convolutional neural network (3D CNN) based a multilevel feature fusion algorithm for mental workload estimation using electroencephalogram (EEG) signals. Raw EEG signals are converted to 3D EEG images and then multilevel features are extracted in each layer of the 3D convolution operation and each multilevel feature is multiplied by a weighting factor, which determines the importance of the feature. The accuracy of our network is 90.3%, which is better than conventional algorithms.

Original language	English
Title of host publication	8th International Winter Conference on Brain-Computer Interface, BCI 2020
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728147079
DOIs	https://doi.org/10.1109/BCI48061.2020.9061639
Publication status	Published - 2020 Feb
Event	8th International Winter Conference on Brain-Computer Interface, BCI 2020 - Gangwon, Korea, Republic of Duration: 2020 Feb 26 → 2020 Feb 28

Publication series

Name	8th International Winter Conference on Brain-Computer Interface, BCI 2020

Conference

Conference	8th International Winter Conference on Brain-Computer Interface, BCI 2020
Country	Korea, Republic of
City	Gangwon
Period	20/2/26 → 20/2/28

Keywords

Convolutional neural network
electroencephalogram (EEG)
mental workload

ASJC Scopus subject areas

Behavioral Neuroscience
Cognitive Neuroscience
Artificial Intelligence
Human-Computer Interaction

Access to Document

10.1109/BCI48061.2020.9061639

Cite this

Kwak, Y., Song, W. J., Min, B. K., & Kim, S. E. (2020). 3D CNN based Multilevel Feature Fusion for Workload Estimation. In 8th International Winter Conference on Brain-Computer Interface, BCI 2020 [9061639] (8th International Winter Conference on Brain-Computer Interface, BCI 2020). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/BCI48061.2020.9061639

3D CNN based Multilevel Feature Fusion for Workload Estimation. / Kwak, Youngchul; Song, Woo Jin; Min, Byoung Kyong; Kim, Seong Eun.

8th International Winter Conference on Brain-Computer Interface, BCI 2020. Institute of Electrical and Electronics Engineers Inc., 2020. 9061639 (8th International Winter Conference on Brain-Computer Interface, BCI 2020).

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

Kwak, Y, Song, WJ, Min, BK & Kim, SE 2020, 3D CNN based Multilevel Feature Fusion for Workload Estimation. in 8th International Winter Conference on Brain-Computer Interface, BCI 2020., 9061639, 8th International Winter Conference on Brain-Computer Interface, BCI 2020, Institute of Electrical and Electronics Engineers Inc., 8th International Winter Conference on Brain-Computer Interface, BCI 2020, Gangwon, Korea, Republic of, 20/2/26. https://doi.org/10.1109/BCI48061.2020.9061639

@inproceedings{81af1746b2994fc3ba9e96987602930f,

title = "3D CNN based Multilevel Feature Fusion for Workload Estimation",

abstract = "Mental workload is defined as the proportion of the information processing capability used to perform a task. High cognitive load requires additional resources that may reduce the processing efficiency and performance. Therefore, the technique of workload estimation can ensure a proper working environment to promote the working efficiency of each person. In this paper, we propose a three-dimensional convolutional neural network (3D CNN) based a multilevel feature fusion algorithm for mental workload estimation using electroencephalogram (EEG) signals. Raw EEG signals are converted to 3D EEG images and then multilevel features are extracted in each layer of the 3D convolution operation and each multilevel feature is multiplied by a weighting factor, which determines the importance of the feature. The accuracy of our network is 90.3%, which is better than conventional algorithms.",

keywords = "Convolutional neural network, electroencephalogram (EEG), mental workload",

author = "Youngchul Kwak and Song, {Woo Jin} and Min, {Byoung Kyong} and Kim, {Seong Eun}",

year = "2020",

month = feb,

doi = "10.1109/BCI48061.2020.9061639",

language = "English",

series = "8th International Winter Conference on Brain-Computer Interface, BCI 2020",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "8th International Winter Conference on Brain-Computer Interface, BCI 2020",

note = "8th International Winter Conference on Brain-Computer Interface, BCI 2020 ; Conference date: 26-02-2020 Through 28-02-2020",

}

TY - GEN

T1 - 3D CNN based Multilevel Feature Fusion for Workload Estimation

AU - Kwak, Youngchul

AU - Song, Woo Jin

AU - Min, Byoung Kyong

AU - Kim, Seong Eun

PY - 2020/2

Y1 - 2020/2

N2 - Mental workload is defined as the proportion of the information processing capability used to perform a task. High cognitive load requires additional resources that may reduce the processing efficiency and performance. Therefore, the technique of workload estimation can ensure a proper working environment to promote the working efficiency of each person. In this paper, we propose a three-dimensional convolutional neural network (3D CNN) based a multilevel feature fusion algorithm for mental workload estimation using electroencephalogram (EEG) signals. Raw EEG signals are converted to 3D EEG images and then multilevel features are extracted in each layer of the 3D convolution operation and each multilevel feature is multiplied by a weighting factor, which determines the importance of the feature. The accuracy of our network is 90.3%, which is better than conventional algorithms.

AB - Mental workload is defined as the proportion of the information processing capability used to perform a task. High cognitive load requires additional resources that may reduce the processing efficiency and performance. Therefore, the technique of workload estimation can ensure a proper working environment to promote the working efficiency of each person. In this paper, we propose a three-dimensional convolutional neural network (3D CNN) based a multilevel feature fusion algorithm for mental workload estimation using electroencephalogram (EEG) signals. Raw EEG signals are converted to 3D EEG images and then multilevel features are extracted in each layer of the 3D convolution operation and each multilevel feature is multiplied by a weighting factor, which determines the importance of the feature. The accuracy of our network is 90.3%, which is better than conventional algorithms.

KW - Convolutional neural network

KW - electroencephalogram (EEG)

KW - mental workload

UR - http://www.scopus.com/inward/record.url?scp=85084065394&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85084065394&partnerID=8YFLogxK

U2 - 10.1109/BCI48061.2020.9061639

DO - 10.1109/BCI48061.2020.9061639

M3 - Conference contribution

AN - SCOPUS:85084065394

T3 - 8th International Winter Conference on Brain-Computer Interface, BCI 2020

BT - 8th International Winter Conference on Brain-Computer Interface, BCI 2020

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 8th International Winter Conference on Brain-Computer Interface, BCI 2020

Y2 - 26 February 2020 through 28 February 2020

ER -