• 《工程索引》(EI)刊源期刊
  • 中文核心期刊(综合性理工农医类)
  • 中国科技论文统计源期刊
  • 中国科学引文数据库来源期刊

留言板

尊敬的读者、作者、审稿人, 关于本刊的投稿、审稿、编辑和出版的任何问题, 您可以本页添加留言。我们将尽快给您答复。谢谢您的支持!

姓名
邮箱
手机号码
标题
留言内容
验证码

基于一维卷积神经网络的儿童睡眠分期

许力 吴云肖 肖冰 许志飞 张远

许力, 吴云肖, 肖冰, 许志飞, 张远. 基于一维卷积神经网络的儿童睡眠分期[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2021.01.13.011
引用本文: 许力, 吴云肖, 肖冰, 许志飞, 张远. 基于一维卷积神经网络的儿童睡眠分期[J]. 工程科学学报. doi: 10.13374/j.issn2095-9389.2021.01.13.011
XU Li, WU Yun-xiao, XIAO Bing, XU Zhi-fei, ZHANG Yuan. One-dimensional convolutional neural network for children’s sleep staging[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2021.01.13.011
Citation: XU Li, WU Yun-xiao, XIAO Bing, XU Zhi-fei, ZHANG Yuan. One-dimensional convolutional neural network for children’s sleep staging[J]. Chinese Journal of Engineering. doi: 10.13374/j.issn2095-9389.2021.01.13.011

基于一维卷积神经网络的儿童睡眠分期

doi: 10.13374/j.issn2095-9389.2021.01.13.011
基金项目: 北京市自然科学基金资助项目(7212033);首都卫生发展科研专项资助项目(首发2018-4-6031)
详细信息
    通讯作者:

    E-mail: yuanzhang@swu.edu.cn

  • 中图分类号: TG391.7

One-dimensional convolutional neural network for children’s sleep staging

More Information
  • 摘要: 高质量睡眠与儿童的身体发育、认知功能、学习和注意力密切相关,由于儿童睡眠障碍的早期症状不明显,需要进行长期监测,因此急需找到一种适用于儿童睡眠监测,且能够提前预防和诊断此类疾病的方法。多导睡眠图(Polysomnography,PSG)是临床指南推荐的睡眠障碍基本检测方法,通过观察PSG各睡眠期间的变化和规律,对睡眠质量评估和睡眠障碍识别具有基础作用。本文对儿童睡眠分期进行了研究,利用多导睡眠图记录的单通道脑电信号,在Alexnet的基础上,用一维卷积代替二维卷积,提出一种1D-CNN结构,由5个卷积层、3个池化层和3个全连接层组成,并在1D-CNN中添加了批量归一化层(Batch normalization layer),保持卷积核的大小保持不变。针对数据集少的情况,采用了重叠的方法对数据集进行了扩充。实验结果表明,该模型儿童睡眠分期的准确率为84.3%。通过北京市儿童医院的PSG数据获得的归一化混淆矩阵,可以看出,Wake、N2、N3和REM期睡眠的分类性能很好。对于N1期睡眠,存在将N1期睡眠被误分类为Wake、N2和REM期睡眠的情况,因此以后的工作应重点提升N1期睡眠的准确性。总体而言,对于基于带有睡眠阶段标记的单通道EEG的自动睡眠分期,本文提出的1D-CNN模型可以实现针对于儿童的自动睡眠分期。在未来的工作中,仍需要研究开发更适合于儿童的睡眠分期策略,在更大数据量的基础上进行实验。

     

  • 图  1  CNN的层次结构及应用

    Figure  1.  CNN architecture and applications

    图  2  数据集重叠

    Figure  2.  Datasets overlapping

    图  3  1D-CNN模型

    Figure  3.  1D-CNN model

    图  4  睡眠分析系统原型

    Figure  4.  Prototype of the sleep analysis system

    图  5  训练和验证准确率

    Figure  5.  Training and validation accuracy

    图  6  训练和验证损失

    Figure  6.  Training and validation loss

    图  7  混淆矩阵

    Figure  7.  Confusion matrix

    表  1  超参数表

    Table  1.   Model hyperparameters

    ParameterValue
    OptimizerAdam
    Learning rate0.00001
    Loss functionCross-entropy
    Batch size256
    L2 regularization0.001
    下载: 导出CSV

    表  2  实验结果

    Table  2.   Experimental results

    MethodAccuracy / %PrecisionRecallF1-scoreK
    Our method85.570.8470.8660.8550.820
    DeepSleepNet69.580.6870.6590.6320.581
    下载: 导出CSV
  • [1] Halbower A C, Degaonkar M, Barker P B, et al. Childhood obstructive sleep apnea associates with neuropsychological deficits and neuronal brain injury. PLoS Med, 2006, 3(8): e301 doi: 10.1371/journal.pmed.0030301
    [2] Matricciani L, Paquet C, Galland B, et al. Children's sleep and health: A meta-review. Sleep Med Rev, 2019, 46: 136 doi: 10.1016/j.smrv.2019.04.011
    [3] Cardoso T S G, Pompéia S, Miranda M C. Cognitive and behavioral effects of obstructive sleep apnea syndrome in children: A systematic literature review. Sleep Med, 2018, 46: 46 doi: 10.1016/j.sleep.2017.12.020
    [4] Marcus C L, Moore R H, Rosen C L, et al. A randomized trial of adenotonsillectomy for childhood sleep apnea. N Engl J Med, 2013, 368(25): 2366 doi: 10.1056/NEJMoa1215881
    [5] Tabone L, Khirani S, Amaddeo A, et al. Cerebral oxygenation in children with sleep-disordered breathing. Paediatr Respir Rev, 2020, 34: 18
    [6] Rundo J V, Downey III R. Polysomnography. Handb Clin Neurol, 2019, 160: 381
    [7] Rechtschaffen A, Kales A. A Manual of Standardized Terminology, Techniques and Scoring System for Sleep Stages of Human Subjects. Washington, DC: U.S. Government Printing Office, 1968
    [8] Li Y J, Hong F, Yan H, et al. Research progress in sleep quality evaluation on-orbit. Space Med Med Eng, 2012, 25(6): 458

    李延军, 宏峰, 严洪, 等. 在轨睡眠质量评价的研究进展. 航天医学与医学工程, 2012, 25(6):458
    [9] Singh J, Badr M S, Diebert W, et al. American academy of sleep medicine (AASM) position paper for the use of telemedicine for the diagnosis and treatment of sleep disorders. J Clin Sleep Med, 2015, 11(10): 1187 doi: 10.5664/jcsm.5098
    [10] Newson J J, Thiagarajan T C. EEG frequency bands in psychiatric disorders: A review of resting state studies. Front Hum Neurosci, 2018, 12: 521 doi: 10.3389/fnins.2018.00521
    [11] Berry RB, Albertario CL, Harding SM, et al. The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications (Version 2.5). USA: American Academy of Sleep Medicine, 2018
    [12] Dong H, Supratak A, Pan W, et al. Mixed neural network approach for temporal sleep stage classification. IEEE Trans Neural Syst Rehabilitation Eng, 2018, 26(2): 324 doi: 10.1109/TNSRE.2017.2733220
    [13] Supratak A, Dong H, Wu C, et al. DeepSleepNet: A model for automatic sleep stage scoring based on raw single-channel EEG. IEEE Trans Neural Syst Rehabilitation Eng, 2017, 25(11): 1998 doi: 10.1109/TNSRE.2017.2721116
    [14] Phan H, Andreotti F, Cooray N, et al. SeqSleepNet: end-to-end hierarchical recurrent neural network for sequence-to-sequence automatic sleep staging. IEEE Trans Neural Syst Rehabilitation Eng, 2019, 27(3): 400 doi: 10.1109/TNSRE.2019.2896659
    [15] Mousavi S, Afghah F, Acharya U R. SleepEEGNet: Automated sleep stage scoring with sequence to sequence deep learning approach. PLoS One, 2019, 14(5): e0216456 doi: 10.1371/journal.pone.0216456
    [16] Neng W P, Lu J, Xu L. CCRRSleepNet: A hybrid relational inductive biases network for automatic sleep stage classification on raw single-channel EEG. Brain Sci, 2021, 11(4): 456 doi: 10.3390/brainsci11040456
    [17] Dehkordi P, Garde A, Karlen W, et al. Sleep stage classification in children using photoplethysmogram pulse rate variability // Computing in Cardiology 2014. Cambridge, 2014: 297
    [18] Gu J X, Wang Z H, Kuen J, et al. Recent advances in convolutional neural networks. Pattern Recognit, 2018, 77: 354 doi: 10.1016/j.patcog.2017.10.013
    [19] Feyissa AM, Tatum WO. Adult EEG. Handb Clin Neurol, 2019, 160: 103
    [20] Krizhevsky A, Sutskever I, Hinton G. ImageNet classification with deep convolutional neural networks //NIPS'12: Proceedings of the 25th International Conference on Neural Information Processing Systems. New York, 2012: 1097
    [21] Kalayeh M M, Shah M. Training faster by separating modes of variation in batch-normalized models. IEEE Trans Pattern Anal Mach Intell, 2020, 42(6): 1483 doi: 10.1109/TPAMI.2019.2895781
    [22] He K M, Zhang X Y, Ren S Q, et al. Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification // 2015 IEEE International Conference on Computer Vision (ICCV). Santiago, 2015: 1026
    [23] Kingma D P, Ba J. Adam: A method for stochastic optimization // International Conference on Learning Representations. San Diego, 2015: 13
    [24] Srivastava N, Hinton G, Krizhevsky A, et al. Dropout: A simple way to prevent neural networks from overfitting. J Mach Learn Res, 2014, 15: 1929
  • 加载中
图(7) / 表(2)
计量
  • 文章访问数:  15
  • HTML全文浏览量:  12
  • PDF下载量:  4
  • 被引次数: 0
出版历程
  • 收稿日期:  2021-01-13
  • 网络出版日期:  2021-08-26

目录

    /

    返回文章
    返回