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
N1 - Funding Information:
Corresponding author: Seong-Eun Kim. This work was supported in part by the National Research Foundation of Korea (NRF) grant funded by the Korean government (MSIP) (2017R1C1B5017254, 2018M3C1B8017549, 2018R1A2B6004084), and in part by the Institute for Information & Communications Technology Promotion (IITP) grant funded by the Korea government (No. 2017-0-00451, 2017-0-00432, and 2019-2016-0-00464).
Publisher Copyright:
© 2020 IEEE.
PY - 2020/2/1
Y1 - 2020/2/1
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
U2 - 10.1109/BCI48061.2020.9061639
DO - 10.1109/BCI48061.2020.9061639
M3 - Conference contribution
AN - SCOPUS:85084065394
SN - 9781728147079
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 -