TY - GEN
T1 - Improving Sleep Stage Classification Performance by Single-Channel EEG Data Augmentation via Spectral Band Blending
AU - Lee, Choel Hui
AU - Kim, Hyun Ji
AU - Heo, Jae Wook
AU - Kim, Hakseung
AU - Kim, Dong Joo
N1 - Funding Information:
This research was supported by the Institute for Information & communications Technology Promotion (IITP) grant funded by the Korea government (MSIT) (No. 2017-0-00432, Development of non-invasive integrated BCI SW platform to control home appliances and external devices by user's thought via AR/VR interface) and the National Research Foundation of Korea (NRF) grant (2019R1A2C1003399, 2020R1C1C1006773). *Asterisk denotes the corresponding author.
Publisher Copyright:
© 2021 IEEE.
PY - 2021/2/22
Y1 - 2021/2/22
N2 - Classification of sleep stage for neurophysiological signals acquired during polysomnography is an important task in the diagnosis of sleep disorders and sleep research. However, current manual sleep stage labeling by trained experts involves heavy labour intensity. Furthermore, previous models regarding the automation of sleep stage classification using machine learning are highly susceptible to class imbalance problem, which is prevalent in polysomnography recordings. This study proposes an automated sleep stage classification method based on data augmentation via spectral band blending to address class imbalance problem, and thereby improving the performance of machine learning models for sleep stage classification. In this endeavour, EEG recordings from 153 healthy subjects were utilized to develop the EEGNet-BiLSTM as the baseline model. When compared the performance of sleep stage classification between EEGNet-BiLSTM with and without data augmentation, EEGNet-BiLSTM without data augmentation yielded approximately 82% accuracy and 0.70 kappa-value, whereas the proposed method showed 87% accuracy and 0.73 kappa-value. Our proposed method, EEGNet-BiLSTM with data augmentation, is superior in terms of accuracy and consistency compared to the conventional baseline model.
AB - Classification of sleep stage for neurophysiological signals acquired during polysomnography is an important task in the diagnosis of sleep disorders and sleep research. However, current manual sleep stage labeling by trained experts involves heavy labour intensity. Furthermore, previous models regarding the automation of sleep stage classification using machine learning are highly susceptible to class imbalance problem, which is prevalent in polysomnography recordings. This study proposes an automated sleep stage classification method based on data augmentation via spectral band blending to address class imbalance problem, and thereby improving the performance of machine learning models for sleep stage classification. In this endeavour, EEG recordings from 153 healthy subjects were utilized to develop the EEGNet-BiLSTM as the baseline model. When compared the performance of sleep stage classification between EEGNet-BiLSTM with and without data augmentation, EEGNet-BiLSTM without data augmentation yielded approximately 82% accuracy and 0.70 kappa-value, whereas the proposed method showed 87% accuracy and 0.73 kappa-value. Our proposed method, EEGNet-BiLSTM with data augmentation, is superior in terms of accuracy and consistency compared to the conventional baseline model.
KW - class imbalance problem
KW - data augmentation
KW - deep learning
KW - electroencephalography
KW - sleep stage
KW - sleep stage classification
UR - http://www.scopus.com/inward/record.url?scp=85104859643&partnerID=8YFLogxK
U2 - 10.1109/BCI51272.2021.9385297
DO - 10.1109/BCI51272.2021.9385297
M3 - Conference contribution
AN - SCOPUS:85104859643
T3 - 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021
BT - 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - 9th IEEE International Winter Conference on Brain-Computer Interface, BCI 2021
Y2 - 22 February 2021 through 24 February 2021
ER -