·1260 工程科学学报，第43卷.第9期 Rehabilitation Eng,2018,26(2):324 [19]Feyissa AM,Tatum WO.Adult EEG.Handb Clin Neurol,2019, [13]Supratak A,Dong H,Wu C,et al.DeepSleepNet:A model for 160:103 automatic sleep stage scoring based on raw single-channel EEG. [20]Krizhevsky A,Sutskever I,Hinton G.ImageNet classification with IEEE Trans Neural Syst Rehabilitation Eng,2017,25(11):1998 deep convolutional neural networks //NIPS'12:Proceedings of the [14]Phan H,Andreotti F,Cooray N,et al.SeqSleepNet:end-to-end 25th International Conference on Neural Information Processing hierarchical recurrent neural network for sequence-to-sequence Systems.New York,2012:1097 automatic sleep staging.IEEE Trans Neural Syst Rehabilitation [21]Kalayeh MM,Shah M.Training faster by separating modes of Eg,2019,27(3):400 variation in batch-normalized models.IEEE Trans Pattern Anal [15]Mousavi S,Afghah F,Acharya U R.SleepEEGNet:Automated Mach Intell,.2020,42(6:1483 sleep stage scoring with sequence to sequence deep learning [22]He K M,Zhang X Y,Ren S Q,et al.Delving deep into rectifiers: approach.PLoS One,2019,14(5):e0216456 Surpassing human-level performance on ImageNet classification / [16]Neng W P,Lu J,Xu L.CCRRSleepNet:A hybrid relational 2015 IEEE International Conference on Computer Vision (ICCV). inductive biases network for automatic sleep stage classification on Santiago,2015:1026 raw single-channel EEG.Brain Sci,2021,11(4):456 [23]Kingma D P,Ba J.Adam:A method for stochastic optimization / [17]Dehkordi P,Garde A,Karlen W,et al.Sleep stage classification in International Conference on Learning Representations.San Diego, children using photoplethysmogram pulse rate variability / 2015:13 Computing in Cardiology 2014.Cambridge,2014:297 [24]Srivastava N,Hinton G,Krizhevsky A,et al.Dropout:A simple [18]Gu J X,Wang Z H,Kuen J,et al.Recent advances in way to prevent neural networks from overfitting.J Mach Learn convolutional neural networks.Pattern Recognit,2018,77:354 Res,2014,15:1929Rehabilitation Eng, 2018, 26（2）: 324 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 [13] 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 [14] 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 [15] 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 [16] 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 [17] Gu  J  X,  Wang  Z  H,  Kuen  J,  et  al.  Recent  advances  in convolutional neural networks. Pattern Recognit, 2018, 77: 354 [18] Feyissa  AM,  Tatum  WO.  Adult  EEG. Handb Clin Neurol,  2019, 160: 103 [19] 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 [20] 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 [21] 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 [22] Kingma D P, Ba J. Adam: A method for stochastic optimization // International Conference on Learning Representations. San Diego, 2015: 13 [23] 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 [24] · 1260 · 工程科学学报，第 43 卷，第 9 期