LGSleepNet: An Automatic Sleep Staging Model Based on Local and Global Representation Learning

TY - JOUR

T1 - LGSleepNet

T2 - An Automatic Sleep Staging Model Based on Local and Global Representation Learning

AU - Shen, Qi

AU - Xin, Junchang

AU - Liu, Xinyao

AU - Wang, Zhongyang

AU - Li, Chuangang

AU - Huang, Zhihong

AU - Wang, Zhiqiong

N1 - Publisher Copyright: © 1963-2012 IEEE.

PY - 2023/7/26

Y1 - 2023/7/26

N2 - Sleep staging is an indispensable indicator for measuring sleep quality and evaluating sleep disorders. Deep learning methods have been successfully applied to automatic sleep staging (ASS) based on electroencephalogram (EEG) signals, achieving significant progress. Previous studies have, however, been limited to extracting local features of EEG signals while neglecting the importance of global features. To solve this problem, we propose a novel ASS model named LGSleepNet, which consists of an asymmetric Siamese neural network (ASNN), deep adaptive orthogonal fusion (DAOF) block, and weighted polynomial cross entropy (WPCE) loss function. Specifically, the ASNN is capable of simultaneously extracting local and global features from EEG signals, which provides diverse semantic representations for sleep staging; moreover, a DAOF block is proposed to eliminate the information redundancy and semantic deviation among heterogeneous features by orthogonalization and adaptive fusion, which strengthens the correlation representation between local and global features. Ultimately, a WPCE loss function is designed to improve the decision-making ability of the classification head and alleviate the problem of sample imbalance. We evaluate the LGSleepNet on three publicly available datasets, namely Sleep-EDF-20, Sleep-EDF-78, and SVUH-UCD, which achieves macro F1-scores of 80.7%, 76.0%, and 75.1% and overall accuracy of 86.0%, 82.3%, and 76.3%, respectively. The experimental results indicate that the LGSleepNet performs at an advanced level compared to other state-of-the-art methods.

AB - Sleep staging is an indispensable indicator for measuring sleep quality and evaluating sleep disorders. Deep learning methods have been successfully applied to automatic sleep staging (ASS) based on electroencephalogram (EEG) signals, achieving significant progress. Previous studies have, however, been limited to extracting local features of EEG signals while neglecting the importance of global features. To solve this problem, we propose a novel ASS model named LGSleepNet, which consists of an asymmetric Siamese neural network (ASNN), deep adaptive orthogonal fusion (DAOF) block, and weighted polynomial cross entropy (WPCE) loss function. Specifically, the ASNN is capable of simultaneously extracting local and global features from EEG signals, which provides diverse semantic representations for sleep staging; moreover, a DAOF block is proposed to eliminate the information redundancy and semantic deviation among heterogeneous features by orthogonalization and adaptive fusion, which strengthens the correlation representation between local and global features. Ultimately, a WPCE loss function is designed to improve the decision-making ability of the classification head and alleviate the problem of sample imbalance. We evaluate the LGSleepNet on three publicly available datasets, namely Sleep-EDF-20, Sleep-EDF-78, and SVUH-UCD, which achieves macro F1-scores of 80.7%, 76.0%, and 75.1% and overall accuracy of 86.0%, 82.3%, and 76.3%, respectively. The experimental results indicate that the LGSleepNet performs at an advanced level compared to other state-of-the-art methods.

KW - Asymmetric Siamese neural network (ASNN)

KW - deep adaptive orthogonal fusion (DAOF)

KW - electroencephalogram (EEG)

KW - sleep staging

KW - weighted polynomial cross entropy (WPCE)

U2 - 10.1109/TIM.2023.3298639

DO - 10.1109/TIM.2023.3298639

M3 - Article

AN - SCOPUS:85165909077

SN - 0018-9456

VL - 72

JO - IEEE Transactions on Instrumentation and Measurement

JF - IEEE Transactions on Instrumentation and Measurement

M1 - 2521814

ER -