一种融合分组卷积和半监督的睡眠分期方法

doi:10.13190/j.jbupt.2021-246

北京邮电大学学报 ›› 2022, Vol. 45 ›› Issue (4): 7-12.doi: 10.13190/j.jbupt.2021-246

一种融合分组卷积和半监督的睡眠分期方法

谢攀¹, 彭才静², 何志慧², 张远¹

1. 西南大学电子信息工程学院, 重庆 400715;
2. 重庆市第九人民医院儿童呼吸科, 重庆 400715

收稿日期:2021-10-20 出版日期:2022-08-28 发布日期:2022-09-03
通讯作者: 张远(1976—),男,教授,博士生导师,邮箱:yuanzhang@swu.edu.cn。 E-mail:yuanzhang@swu.edu.cn
作者简介:谢攀(1994—),女,硕士生。

A Sleep Staging Method Combining Grouping Convolution with Semi-Supervised Learning

XIE Pan¹, PENG Caijing², HE Zhihui², ZHANG Yuan¹

1. College of Electronic and Information Engineering, Southwest University, Chongqing 400715, China;
2. Department of Pediatric Respiratory, the Ninth People's Hospital of Chongqing, Chongqing 400715, China

Received:2021-10-20 Online:2022-08-28 Published:2022-09-03

摘要/Abstract

摘要： 已有的睡眠分期研究大部分采用监督学习的方法，其模型训练高度依赖于大量优质的标签数据，所提取的特征也较为粗糙。为此，提出了将半监督学习应用于分组卷积神经网络的睡眠分期方法。首先，采用分组残差卷积网络作为骨干网络，使不同分组学习的特征多样化，让整个网络关注来自不同子空间的信息，从而提取多角度特征；其次，为减少标注技师的工作负担，采用半监督学习的方法，从大量未标注数据中提取特征与标注数据提取的特征进行对抗，以获得更多细粒度特征。实验结果表明，在Sleep-EDFx数据集上的睡眠分期准确率能够达到0.837±0.001，卡帕系数达到0.774±0.002，均优于对比算法。

关键词: 睡眠分期, 脑电信号, 半监督, 分组卷积

Abstract: Sleep is an important physiological activity of human body, and the quality of sleep affects physical and mental health. Most of the existing sleep staging is based on supervised learning, which is highly dependent on a large number of high-quality label data, and the extracted features are relatively rough. To save this issue, a sleep staging method combining grouped convolutional neural network and semi-supervised learning is proposed. First, the grouping residual convolution network is used as the backbone network to ensure the diversity of learning features and take the information from multiple subspaces into consideration, which extracts multi-angle features. Then, to reduce the workload of annotation technicians, semi-supervised learning method is adopted to extract features from a large number of unlabeled data and compete with those extracted from labeled data, which can obtain more fine-grained features. The experimental results show that the accuracy of sleep staging on sleep-EDFx can reach 0.837±0.001, and the Kappa coefficient reaches 0.774±0.002, which performs better than the baseline algorithm. The method presented has a good application prospect in the combination of medicine and industry.

Key words: sleep stage, electroencephalogram, semi-supervise, grouping convolution

中图分类号:

谢攀, 彭才静, 何志慧, 张远. 一种融合分组卷积和半监督的睡眠分期方法[J]. 北京邮电大学学报, 2022, 45(4): 7-12.

XIE Pan, PENG Caijing, HE Zhihui, ZHANG Yuan. A Sleep Staging Method Combining Grouping Convolution with Semi-Supervised Learning[J]. Journal of Beijing University of Posts and Telecommunications, 2022, 45(4): 7-12.

参考文献

[1] HENRY J C. Electroencephalography:basic principles, clinical applications, and related fields[J]. Neurology, 2006, 67(11):2092-2092.
[2] BERRYR B, BROOKS R, GAMALDO C E, et al. The AASM manual for the scoring of sleep and associated events[J]. Rules, Terminology and Technical Specifications, Darien, Illinois, American Academy of Sleep Medicine, 2012, 176:2012-2019.
[3] DELIMAYANTI M K, PURNAMA B, Nguyen N G, et al. Classification of brainwaves for sleep stages by high-dimensional FFT features from EEG signals[J]. Applied Sciences, 2020, 10(5):1797-1809.
[4] HUANG W, GUO B, SHEN Y, et al. Sleep staging algorithm based on multichannel data adding and multifeature screening[J/OL]. Computer Methods and Programs in Biomedicine, 2020, 187:105253[2021-08-28]. https://www.sciencedirect.com/science/article/pii/S0169260719304602.
[5] PHAN H, ANDREOTTI F, COORAY N, et al. DNN filter bank improves 1-max pooling CNN for single-channel EEG automatic sleep stage classification[C]//2018 40th Annual International Conference of the IEEE Engineering in Medicine and Biology Society. Piscataway, NJ:IEEE Press, 2018:453-456.
[6] KORKALAINEN H, AAKKO J, NIKKONEN S, et al. Accurate deep learning-based sleep staging in a clinical population with suspected obstructive sleep apnea[J]. IEEE Journal of Biomedical and Health Informatics, 2020, 24(7):2073-2081.
[7] LEE D H. Pseudo-label:the simple and efficient semi-supervised learning method for deep neural networks[C]//Workshop on Challenges in Repre-Sentation Learning.[S.l.]:ICML, 2013:896-902.
[8] SOHN K, BERTHELOT D, CARLINI N, et al. Fixmatch:simplifying semi-supervised learning with consistency and confidence[J]. Advances in Neural Information Processing Systems, 2020, 33:596-608.
[9] BAI H R, LU G Z. Semi-supervised end-to-end automatic sleep stage classification based on pseudo-label[C]//2021 IEEE International Conference on Power Electronics, Computer Applications. Piscataway, NJ:IEEE Press, 2021:83-87.
[10] ZHOU B Y, CUI Q, WEI X S, et al. BBN:bilateral-branch network with cumulative learning for long-tailed visual recognition[C]//2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway, NJ:IEEE Press, 2020:9716-9725.
[11] XIE S N, GIRSHICK R, DOLLÁR P, et al. Aggregated residual transformations for deep neural networks[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:5987-5995.
[12] IOANNOU Y, ROBERTSON D, CIPOLLA R, et al. Deep roots:improving CNN efficiency with hierarchical filter groups[C]//2017 IEEE Conference on Computer Vision and Pattern Recognition. Piscataway, NJ:IEEE Press, 2017:5977-5986.
[13] LEE T K, BADDAR W J, KIM S T, et al. Convolution with logarithmic filter groups for efficient shallow CNN[C]//International Conference on Multimedia Modeling. Cham:Springer International Publishing, 2018:117-129.
[14] GOLDBERGER A L, AMARAL L A, GLASS L, et al. PhysioBank, PhysioToolkit, and PhysioNet:components of a new research resource for complex physiologic signals[J]. Circulation, 2000, 101(23):E215-E220.
[15] GUILLOT A, SAUVET F, DURING E H, et al. Dreem open datasets:multi-scored sleep datasets to compare human and automated sleep staging[J]. IEEE Transactions on Neural Systems and Rehabilitation Engineering:a Publication of the IEEE Engineering in Medicine and Biology Society, 2020, 28(9):1955-1965.

一种融合分组卷积和半监督的睡眠分期方法

A Sleep Staging Method Combining Grouping Convolution with Semi-Supervised Learning

RichHTML

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 7

编辑推荐

Metrics

本文评价

[1]	晁浩, 马庆敏, 刘永利. 利用卷积回声状态网络实现脑电情感识别[J]. 北京邮电大学学报, 2022, 45(2): 36-43.
[2]	霍纬纲, 王星, 梁锐. 融合互信息估计和对抗自编码器的异常检测[J]. 北京邮电大学学报, 2021, 44(5): 28-34.
[3]	李端玲, 成苈委, 于功敬, 张忠海, 于淑月. 融合小波包和神经网络的脑电信号处理方法[J]. 北京邮电大学学报, 2021, 44(3): 94-99.
[4]	孙艺, 夏启钊. 半监督聚类目标下粒子群算法的分析与改进[J]. 北京邮电大学学报, 2020, 43(5): 21-26.
[5]	曹志义, 牛少彰, 张继威. 基于生成对抗网络的遮挡图像修复算法[J]. 北京邮电大学学报, 2018, 41(3): 81-86.
[6]	刘珍, 王若愚, 刘琼. 基于Bootstrapping的因特网流量分类方法[J]. 北京邮电大学学报, 2014, 37(5): 66-70,79.
[7]	张韬政,王小捷,仝辉. 交互结构最优化算法中辅助问题的相关性[J]. 北京邮电大学学报, 2011, 34(4): 14-18.