Sleep State Classification Using Power Spectral Density and Residual Neural Network with Multichannel EEG Signals
Source abstract
Abstract
This paper proposes a classification framework for automatic sleep stage detection in both male and female human subjects by analyzing the electroencephalogram (EEG) data of polysomnography (PSG) recorded for three regions of the human brain, i.e., the pre-frontal, central, and occipital lobes. Without considering any artifact removal approach, the residual neural network (ResNet) architecture is used to automatically learn the distinctive features of different sleep stages from the power spectral density (PSD) of the raw EEG data. The residual block of the ResNet learns the intrinsic features of different sleep stages from the EEG data while avoiding the vanishing gradient problem. The proposed approach is validated using the sleep dataset of the Dreams database, which comprises of EEG signals for 20 healthy human subjects, 16 female and 4 male. Our experimental results demonstrate the effectiveness of the ResNet based approach in identifying different sleep stages in both female and male subjects compared to state-of-the-art methods with classification accuracies of 87.8% and 83.7%, respectively.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: EEG and Brain-Computer Interfaces · Sleep and Wakefulness Research · Sleep and Work-Related Fatigue
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Computer Engineering and Information Technology, University of Ulsan, Ulsan 44610, Korea
ICT Convergence Safety Research Center, University of Ulsan, Ulsan 44610, Korea
Electronics and Telecommunications Research Institute (ETRI), Daejeon 34129, Korea
Funding
Electronics and Telecommunications Research Institute
References (60)
Show source-provided references
1. Morin, C.M., and Espie, C.A. (2011). The Oxford Handbook of Sleep and Sleep Disorders, Oxford University Press.
2. Sleep state switching10.1016/j.neuron.2010.11.032 ↗
3. EEG Sleep Stages Analysis and Classification Based on Weighed Complex Network Features
4. Altevogt, B.M., and Colten, H.R. (2006). Sleep Disorders and Sleep Deprivation: An Unmet Public Health Problem, National Academies Press.
5. Sleep epidemiology—A rapidly growing field10.1093/ije/dyr203 ↗
6. Sleep-wake classification via quantifying heart rate variability by convolutional neural network10.1088/1361-6579/aad5a9 ↗
7. Smart helmet: Wearable multichannel ECG and EEG10.1109/JTEHM.2016.2609927 ↗
8. Medical big data: Neurological diseases diagnosis through medical data analysis10.1007/s41019-016-0011-3 ↗
9. A computer aided analysis scheme for detecting epileptic seizure from EEG data10.2991/ijcis.11.1.51 ↗
10. Berry, R.B. (2018). The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications, American Academy of Sleep Medicine.
11. Analysis of Multichannel EEG Patterns During Human Sleep: A Novel Approach10.3389/fnhum.2018.00121 ↗
12. Practical considerations in the positioning of EEG electrodes10.1016/0013-4694(82)90010-4 ↗
13. Sleep EEG functional connectivity varies with age and sex, but not general intelligence10.1016/j.neurobiolaging.2019.02.007 ↗
14. From swing to cane: Sex differences of EEG resting-state temporal patterns during maturation and aging10.1016/j.dcn.2018.04.011 ↗
15. Ferrara, M., Bottasso, A., Tempesta, D., Carrieri, M., De Gennaro, L., and Ponti, G. (2015). Gender differences in sleep deprivation effects on risk and inequality aversion: Evidence from an economic experiment. PLoS ONE, 10.10.1371/journal.pone.0120029 ↗
16. Gender and age differences in polysomnography findings and sleep complaints of patients referred to a sleep laboratory10.1590/S0100-879X2008001200005 ↗
17. Assess sleep stage by modern signal processing techniques10.1109/TBME.2014.2375292 ↗
18. Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting10.1016/j.eswa.2010.04.043 ↗
19. Automated sleep stage identification system based on time–frequency analysis of a single EEG channel and random forest classifier10.1016/j.cmpb.2011.11.005 ↗
20. Chen, C., Ugon, A., Zhang, X., Amara, A., Garda, P., Ganascia, J.-G., Philippe, C., and Pinna, A. (2016, January 16–20). Personalized sleep staging system using evolutionary algorithm and symbolic fusion. Proceedings of the 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Orlando, FL, USA.10.1109/EMBC.2016.7591181 ↗
21. Sleep stage classification using covariance features of multi-channel physiological signals on Riemannian manifolds10.1016/j.cmpb.2019.06.008 ↗
22. Sermanet, P., Chintala, S., and LeCun, Y. (2012). Convolutional neural networks applied to house numbers digit classification. arXiv.
23. Automatic classification of motor impairment neural disorders from EEG signals using deep convolutional neural networks
24. Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network10.1515/bmt-2016-0156 ↗
25. Ebrahimi, F., Mikaeili, M., Estrada, E., and Nazeran, H. (2008, January 20–25). Automatic sleep stage classification based on EEG signals by using neural networks and wavelet packet coefficients. Proceedings of the 2008 30th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, Vancouver, BC, Canada.10.1109/IEMBS.2008.4649365 ↗
26. Sleep EEG signal analysis based on correlation graph similarity coupled with an ensemble extreme machine learning algorithm10.1016/j.eswa.2019.07.007 ↗
27. De Automatic Sleep Stage Classification Using Single-Channel EEG: Learning Sequential Features with Attention-Based Recurrent Neural Networks
28. Deep Residual Networks with Dynamically Weighted Wavelet Coefficients for Fault Diagnosis of Planetary Gearboxes10.1109/TIE.2017.2762639 ↗
29. He, K., Zhang, X., Ren, S., and Sun, J. (2015, January 7–13). Delving deep into rectifiers: Surpassing human-level performance on imagenet classification. Proceedings of the IEEE International Conference on Computer Vision 2015, Santiago, Chile.10.1109/ICCV.2015.123 ↗
30. He, K., Zhang, X., Ren, S., and Sun, J. (July, January 26). Deep residual learning for image recognition. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA.
31. Gradient-based learning applied to document recognition10.1109/5.726791 ↗
32. Krizhevsky, A., Sutskever, I., and Hinton, G.E. (2012, January 3–6). Imagenet classification with deep convolutional neural networks. Proceedings of the Advances in Neural Information Processing Systems, Lake Tahoe, NV, USA.
33. Multiple Wavelet Coefficients Fusion in Deep Residual Networks for Fault Diagnosis10.1109/TIE.2018.2866050 ↗
34. Power Spectral Analysis of EEG as a Potential Marker in the Diagnosis of Spastic Cerebral Palsy Cases10.5121/ijbes.2016.3303 ↗
35. PSD Based Coherence Analysis of EEG Signals for Stroop Task
36. The effects of age and gender on sleep EEG power spectral density in the middle years of life (ages 20–60 years old)10.1111/1469-8986.3820232 ↗
37. Sleep Spindles: Mechanisms and Functions10.1152/physrev.00042.2018 ↗
38. Can spectral power predict subjective sleep quality in healthy individuals?10.1111/jsr.12848 ↗
39. (2020, September 16). The DREAMS Subjects Database. Available online: https://zenodo.org/record/2650142#.Xy-n5igzYkl.
40. Learning algorithms for classification: A comparison on handwritten digit recognition
41. An Approach of Sleep Stage Classification Based on Time-frequency Analysis and Random Forest on a Single Channel
42. Belakhdar, I., Kaaniche, W., Djmel, R., and Ouni, B. (2016, January 21–23). A comparison between ANN and SVM classifier for drowsiness detection based on single EEG channel. Proceedings of the 2nd International Conference on Advanced Technologies for Signal and Image Processing (ATSIP 2016), Monastir, Tunisia.10.1109/ATSIP.2016.7523132 ↗
43. Resolving Gender Difference in Problem Solving Based On the Analysis of Electroencephalogram (EEG) Signals
44. Sex differences in light sensitivity impact on brightness perception, vigilant attention and sleep in humans10.1038/s41598-017-13973-1 ↗
45. Periodogram analysis and continuous spectra10.1093/biomet/37.1-2.1 ↗
46. On the efficiency of procedures for smoothing periodograms from time series with continuous spectra10.1093/biomet/42.1-2.143 ↗
47. The diagnostic value of power spectra analysis of the sleep electroencephalography in narcoleptic patients10.1016/j.sleep.2015.09.005 ↗
48. Analysis of power spectrum estimation using welch method for various window techniques
49. Deep learning10.1038/nature14539 ↗
50. He, K., Zhang, X., Ren, S., and Sun, J. (2016, January 11–14). Identity mappings in deep residual networks. Proceedings of the European Conference on Computer Vision, Amsterdam, The Netherlands.10.1007/978-3-319-46493-0_38 ↗
51. Lin, X., Zhao, C., and Pan, W. (2017, January 4–9). Towards accurate binary convolutional neural network. Proceedings of the Advances in Neural Information Processing Systems, Long Beach, CA, USA.
52. Pakhomov, D., Premachandran, V., Allan, M., Azizian, M., and Navab, N. Deep residual learning for instrument segmentation in robotic surgery. Proceedings of the International Workshop on Machine Learning in Medical Imaging.
53. Khan, R.U., Zhang, X., Kumar, R., and Aboagye, E.O. (2018, January 12–14). Evaluating the performance of resnet model based on image recognition. Proceedings of the 2018 International Conference on Computing and Artificial Intelligence, Chengdu, China.10.1145/3194452.3194461 ↗
54. Learning criteria for training neural network classifiers10.1007/BF01428124 ↗
55. Glorot, X., Bordes, A., and Bengio, Y. (2011, January 11–13). Deep sparse rectifier neural networks. Proceedings of the Fourteenth International Conference on Artificial Intelligence and Statistics, Fort Lauderdale, FL, USA.
56. Kingma, D.P., and Ba, J. (2014). Adam: A method for stochastic optimization. arXiv.
57. Cross-validation methods10.1006/jmps.1999.1279 ↗
58. The impact of class imbalance in classification performance metrics based on the binary confusion matrix10.1016/j.patcog.2019.02.023 ↗
59. Goutte, C., and Gaussier, E. (2005, January 21–23). A probabilistic interpretation of precision, recall and F-score, with implication for evaluation. Proceedings of the European Conference on Information Retrieval, Santiago de Compostela, Spain.10.1007/978-3-540-31865-1_25 ↗
60. Machine learning basics