EEG-Based Sleep Quality Evaluation with Deep Transfer Learning
In this paper, we propose a subject-independent approach with deep transfer learning to evaluate the last-night sleep quality using EEG data. To reduce the intrinsic cross-subject differences of EEG data and background noise variations during signal acquisition, we adopt two classes of transfer learning methods to build subject-independent classifiers. One is to find a subspace by matrix decomposition and regularization theory, and the other is to learn the common shared structure with the deep autoencoder. The experimental results demonstrate that deep transfer learning model achieves the mean classification accuracy of 82.16% in comparison with the baseline SVM (65.74%) and outperforms other transfer learning methods. Our experimental results also indicate that the neural patterns of different sleep quality are discriminative and stable: the delta responses increase, the alpha responses decrease when sleep is partially deprived, and the neural patterns of 4-h sleep and 6-h sleep are more similar compared with 8-h sleep.
KeywordsSleep quality EEG Neural pattern Deep transfer learning
This work was supported in part by grants from the National Key Research and Development Program of China (Grant No. 2017YFB1002501), the National Natural Science Foundation of China (Grant No. 61673266), the Major Basic Research Program of Shanghai Science and Technology Committee (Grant No. 15JC1400103), ZBYY-MOE Joint Funding (Grant No. 6141A02022604), and the Technology Research and Development Program of China Railway Corporation (Grant No. 2016Z003-B).
- 2.Berry, R.B.: Fundamentals of Sleep Medicine. Elsevier Health Sciences, Amsterdam (2011)Google Scholar
- 6.Lorenzo, I., Ramos, J., Arce, C., Guevara, M.A., Corsi-Cabrera, M.: Effect of total sleep deprivation on reaction time and waking EEG activity in man. Sleep 18(5), 346–354 (1995)Google Scholar
- 8.Shi, L.C., Jiao, Y.Y., Lu, B.L.: Differential entropy feature for EEG-based vigilance estimation. In: 35th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6627–6630. IEEE (2013)Google Scholar
- 9.Shi, L.C., Lu, B.L.: Off-line and on-line vigilance estimation based on linear dynamical system and manifold learning. In: 32nd Annual International Conference of the IEEE Engineering in Medicine and Biology Society, pp. 6587–6590. IEEE (2010)Google Scholar
- 10.Wang, L.L., Zheng, W.L., Ma, H.W., Lu, B.L.: Measuring sleep quality from EEG with machine learning approaches. In: International Joint Conference on Neural Networks, pp. 905–912. IEEE (2016)Google Scholar
- 12.Zheng, W.L., Lu, B.L.: Personalizing EEG-based affective models with transfer learning. In: Proceedings of the 25th International Joint Conference on Artificial Intelligence, pp. 2732–3738 (2016)Google Scholar
- 13.Zhuang, F., Cheng, X., Luo, P., Pan, S.J., He, Q.: Supervised representation learning: transfer learning with deep autoencoders. In: Proceedings of the 24th International Joint Conference on Artificial Intelligence, pp. 4119–4125 (2015)Google Scholar