基於行動裝置之低成本高準確度睡眠狀態分類與聽覺刺激系統

簡易檢索 / 詳目顯示

回結果列表

研究生：	蔡正彥 Tsai, Zheng-Yen
論文名稱：	基於行動裝置之低成本高準確度睡眠狀態分類與聽覺刺激系統 Low-cost High-accuracy Sleep-stage Classification and Auditory Stimulation System using Electroencephalography on Mobile Devices
指導教授：	黃元豪 Huang, Yuan-Hao
口試委員:	黃柏鈞 Huang, Po-Chiun 楊家驤 Yang, Chia-Hsiang
學位類別：	碩士 Master
系所名稱：	電機資訊學院 - 通訊工程研究所 Communications Engineering
論文出版年：	2021
畢業學年度：	109
語文別：	英文
論文頁數：	66
中文關鍵詞：	睡眠狀態分類、深度學習、腦電圖
外文關鍵詞：	Sleep Stage Classification, Deep Learning, EEG
相關次數：	點閱：2 下載：0
分享至:	分享至facebook 分享至twitter

查詢本校圖書館目錄查詢臺灣博碩士論文知識加值系統勘誤回報

與睡眠時間相比，睡眠品質更為重要。為了標記並提高睡眠品質，睡眠階段分類扮演重要的角色。一般而言，我們在醫院通過多導睡眠監測儀獲得腦電波，然後需要睡眠技術人員的標記，這項工作很複雜、耗時且不舒服。因此，我們希望透過使用機器學習，在連接到可穿戴式單通道腦電圖設備的移動設備上實施機器學習來設計自動睡眠階段分類系統。睡眠階段預測演算法基於散射變換來提取時移不變和變形穩定的特徵。與參考演算法相比，我們減少了40.7％的特徵大小，以降低移動設備的計算複雜度。我們還使用LSTM代替SVM作為分類器，以預測睡眠階段。當移動系統檢測到受試者進入深度睡眠時，該設備將播放粉紅噪聲刺激以增強慢波的產生，從而改善睡眠記憶的鞏固。睡眠階段預測演算法的總體準確性在長庚醫院數據庫中為0.8329，在可穿戴設備數據庫中為0.7899。整體來說，這是一種低成本、高準確率的方法。

Compared with sleep duration, sleep quality is more important. To score and increase sleep quality, sleep stage classification plays an important role. Generally speaking, we obtain brain waves through Polysomnography (PSG) at the hospital, then needing a sleep technician scoring, and it's complex, time-consuming, and uncomfortable. Thus, we would like to design the automatic sleep stage classification system by using machine learning to implement on the mobile device which connects to a wearable single-channel electroencephalogram (EEG) device. The sleep stage predicted algorithm is based on the scattering transform to extract the time-shift invariant and deformation stable features. Compared with the reference algorithm, we reduce 40.7% number of feature size to cut down the computing complexity on the mobile device. We also replace the SVM with the LSTM as our classifier to predict sleep stages. When the mobile system detects the subject fall into deep sleep, the device will play the pink noise stimulation to boost the slow-wave generation that improves sleep memory consolidation. The overall accuracy of the sleep stages predicted algorithm is 0.8329 in CGMH database and 0.7899 in wearable device database. In other words, this is a low-cost high-accuracy method.

Contents
Introduction 1
1 Sleep Stages and Sleep Quality . . . . . . . . . . . . . . . . . . . . . . . 1
2 Research Motivation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 2
3 Related Works . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 4
4 Organization of This Thesis . . . . . . . . . . . . . . . . . . . . . . . . . 6
Sleep Stages and Auditory Stimulation 7
1 Introduction of EEG . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 7
1.1 Placement of Electrodes . . . . . . . . . . . . . . . . . . . . . . . 7
1.2 Waveform of EEG . . . . . . . . . . . . . . . . . . . . . . . . . . 8
2 Sleep Stage . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 11
2.1 Whole-Night Sleep Structure . . . . . . . . . . . . . . . . . . . . . 12
2.2 Categories of Brain Activity and Characteristic of Sleep Stage . . 12
3 Auditory Stimulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 15
Proposed Sleep Stages Classification Algorithm and Auditory Stimulation System 19
1 Data Acquistition . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 19
2 Pre-processing . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 20
2.1 Resampling . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
2.2 Filtering . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 21
2.3 Normalization . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 22
3 Feature Extraction . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.1 Scattering Transform . . . . . . . . . . . . . . . . . . . . . . . . . 23
3.2 Feature Selection . . . . . . . . . . . . . . . . . . . . . . . . . . . 31
4 Neural Network Model Classifier . . . . . . . . . . . . . . . . . . . . . . . 33
4.1 RNN-LSTM Model . . . . . . . . . . . . . . . . . . . . . . . . . . 33
4.2 Proposed RNN-LSTM Architecture . . . . . . . . . . . . . . . . . 35
5 Auditory Stimulation . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 36
Experimental Result 41
1 Experimental Environments, Dataset, Wearable EEG Headset and Study Design . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 41
2 SVM Classification Performance . . . . . . . . . . . . . . . . . . . . . . . 45
2.1 Performance of Scattering Transform . . . . . . . . . . . . . . . . 46
2.2 Performance of Feature Selection . . . . . . . . . . . . . . . . . . 48
3 RNN-LSTM Classification Performance . . . . . . . . . . . . . . . . . . . 50
3.1 Performance of Scattering Transform . . . . . . . . . . . . . . . . 50
3.2 Performance of Feature Selection . . . . . . . . . . . . . . . . . . 52
4 Discussion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 57
Conclusion and Future Work 61
1 Conclusion . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61
2 Future Work . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . . 61
References 63
                                

[1] Y.-J. Liu, "Sleep stages classification and auditory stimulation system using electroencephalography
on mobile devices," Master's thesis, National Tsing Hua University, August 2020.
[2] A. Rechtschaen and A. Kales. (1968) A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects. [Online]. Available: https://sleepfoundation.org/excessivesleepiness/content/why-do-we-need-sleep
[3] C. Iber, S. Ancoli-Isreal, A. C. Jr., and S. Quan, Eds., The AASM Manual for Scoring of Sleep and Associated Events-Rules: Technical Specication. America: American Academy of Sleep Medicine, 2007.
[4] R. Berry, R. Brooks, C. Gamaldo, S. Harding, R. Lloyd, C. Marcus, and B. Vaughn. (2012) Rules for scoring respiratory events in sleep: update of the 2007 aasm manual for the scoring of sleep and associated events. [Online]. Available:
https://sleepfoundation.org/excessivesleepiness/content/why-do-we-need-sleep
[5] C. Tononi and G. Cirelli, "Sleep and the price of plasticity: from synaptic and cellular homeostasis to memory consolidation and integration," Neuron, pp. 12-34, 2014.
[6] G. Keklund and T. Akerstedt, "Objective components of individual differences in subjective sleep quality," Journal of Sleep Research, vol. 6, no. 4, pp. 217-220, 1997.
[7] N. Papalambros, G. Santostasi, R. Malkani, R. Braun, S. Weintraub, K. Paller, and P. Zee, "Sleep and the price of plasticity: from synaptic and cellular homeostasis to memory consolidation and integration," Frontiers in Human Neuroscience, pp.1-14, 2017.
[8] M. Bellesi, B. Riedner, G.Garcia-Molina, C. Cirelli, and G. Tononi, "Enhancement of sleep slow waves: underlying mechanisms and practical consequences," Frontiers in Systems Neuroscience, pp. 8:1-17, 2014.
[9] N. Papalambros, G. Santostasi, R. Malkani, R. Braun, S. Weintraub, K. Paller, and P. Zee, "Sleep and the price of plasticity: from synaptic and cellular homeostasis to memory consolidation and integration," Frontiers in Human Neuroscience, p. 11, 2017.
[10] G.-R. Liu, Y.-L. Lo, Y.-C. Sheu, and H.-T. Wu, "Diuse to fuse eeg spectra - intrinsic geometry of sleep dynamics for classification," 2018.
[11] A. Tautan, A. C. Rossi, R. de Francisco, and B. Ionescu, "Automatic sleep stage detection using a single channel frontal eeg," in 2019 E-Health and Bioengineering Conference (EHB), 2019, pp. 1-4.
[12] S. M. I. Niroshana, X. Zhu, Y. Chen, and W. Chen, "Automatic sleep stage classification based on convolutional neural networks," in 2019 IEEE 1st Global Conference on Life Sciences and Technologies (LifeTech), 2019, pp. 275-276.
[13] Y. Liu, R. Fan, and Y. Liu, "Deep identity confusion for automatic sleep staging based on single-channel eeg," in 2018 14th International Conference on Mobile Ad-Hoc and Sensor Networks (MSN), 2018, pp. 134-139.
[14] Y. Zhang, Z. Yang, K. Lan, X. Liu, Z. Zhang, P. Li, D. Cao, J. Zheng, and J. Pan, "Sleep stage classification using bidirectional lstm in wearable multi-sensor systems,"
in IEEE INFOCOM 2019 - IEEE Conference on Computer Communications
Workshops (INFOCOM WKSHPS), 2019, pp. 443-448.
[15] A. J. Boe, L. L. M. Koch1, M. K. O'Brien, N. Shawen, J. A. Rogers, R. L. Lieber, K. J. Reid, P. C. Zee, and A. Jayaraman, "Automating sleep stage classification using wireless, wearable sensors," Nature Partner Journal, vol. 2, p. 131, 2019.
[16] M. Schonauer, "Sleep spindles: timed for memory consolidation," Current Biology, vol. 28, issue 11, pp. 656-658, 4 June 2018.
[17] F. Ebrahimi, M. Mikaeili, E. Estrada, and H. Nazeran, "Automatic sleep stage classification based on eeg signals by using neural networks and wavelet packet coefficients," in 2008 30th Annual International Conference of the IEEE Engineering
in Medicine and Biology Society, 2008, pp. 1151-1154.
[18] O. Tsinalis, P. Matthews, and Y. Guo, "Automatic sleep stage scoring using time-frequency analysis and stacked sparse autoencoders," Annals of Biomedical Engineering, vol. 44, pp. 1587-1597, 2015.
[19] L. Marshall, H. Helgadottir, M. Molle, and J. Born, "Boosting slow oscillations during sleep potentiates memory," Nature, vol. 444, no. 7119, pp. 610-613, 11 2006.
[20] M. Bellesi, B. A. Riedner, G. Garcia-Molina, C. Cirelli, and G. Tononi, "Enhancement of sleep slow waves: underlying mechanisms and practical consequences," Frontiers in Systems Neuroscience, vol. 8, pp. 1-17, 10 2014.
[21] B. A. Riedner, B. K. Hulse, F. Ferrarelli, S. Sarasso, and G. Tononi, "Enhancing sleep slow waves with natural stimuli," Medicamundi, vol. 45, no. 2, pp. 82-88, 2010.
[22] H.-V. V. NGO, J. C. CLAUSSEN, J. BORN, and M. MOLLE, "Induction of slow oscillations by rhythmic acoustic stimulation," August 2012.
[23] C.-H. Lin, "The composition of electroencephalogram application software programming textbook," Master's thesis, Chaoyang University of Technology, 2015.
[24] J. Anden and S. Mallat, "Deep scattering spectrum," IEEE Transactions on Signal Processing, vol. 62, no. 16, pp. 4114-4128, 2014.
[25] I. Guyon, J. Weston, and S. Barnhill, "Gene selection for cancer classification using support vector machines," Machine Learning, vol. 46, no. 1-3, pp. 389-422, 2002.
[26] H. Dong, A. Supratak, W. Pan, C.Wu, P. M. Matthews, and Y. Guo, "Mixed neural network approach for temporal sleep stage classification," IEEE Transactions on Neural Systems and Rehabilitation Engineering, vol. 26, no. 2, pp. 324-333, 2018.
[27] S. Hochreiter and J. Schmidhuber, "Long short-term memory," Neural Computation, vol. 9, no. 8, pp. 1735-1780, 1997.
[28] F. A. Gers, N. N. Schraudolph, and J. Schmidhuber, "Learning precise timing with lstm recurrent networks," J. Mach. Learn. Res., vol. 3, no. 1, pp. 115-143, 2003.
[29] D. P. Kingma and J. Ba, "Adam: A method for stochastic optimization," CoRR, vol. abs/1412.6980, 2015.
[30] S. Ioe and C. Szegedy, "Batch normalization: Accelerating deep network training by reducing internal covariate shift," ser. Proceedings of Machine Learning Research, vol. 37, 2015, pp. 448-456.
[31] N. Papalambros, G. Santostasi, R. Malkani, R. Braun, S. Weintraub, K. Paller, and P. Zee, "Acoustic enhancement of sleep slow oscillations and concomitant memory improvement in older adults," Frontiers in Human Neuroscience, vol. 11, p. 109,
2017.
[32] R. Kohavi, "A study of cross-validation and bootstrap for accuracy estimation and model selection," vol. 14, 03 2001.

簡易檢索 / 詳目顯示

相關論文