睡眠階段的判讀技術是睡眠醫學研究中的基礎核心技術，透過此技術可以得知睡眠的結構分佈，並依此作為其他相關睡眠研究的基本參考依據。由於各個睡眠階段的比例及結構經常會因睡眠障礙及身心疾病而發生改變，其中以快速動眼期睡眠特別容易受影響，因此若能準確的偵測快速動眼期，進而推算快速動眼期的各項參數，再與正常值交互對照比較，即有可能提供有效的資訊來協助醫護人員觀察相關病症的變化，在療程上可依據此資訊做應變性的調整。
本文的目的在於利用機器學習的方法來實現自動化偵測快速動眼期的技術。過去的研究皆透過以人工方式尋找快速動眼期的特徵變數，並且藉由不同的特徵指標組合模式，以一個或是多個腦波頻道及其他生理訊號頻道的結合。在此本文為討論使用卷積神經網路的技術，搭配單一腦電圖訊號進行快速動眼期的偵測，希望將此技術作為發展遠距離居家照護的根基。其資料庫則經由睡眠中心的支援，迄今已整理好超過約五百多人次的整夜睡眠紀錄，故研究規模會遠超過過去的所有文獻記載。目前本文所提出的整夜睡眠腦電圖訊號睡眠階段判讀結果，可得到快速動眼期與非快速動眼期兩睡眠期的分類效能達92.26%的訓練精度，而且代表一致性的kappa指標也有0.69以上，且後續透過鄰居法則及補償法則修正後，kappa值提升至0.848屬於高度相關和95.91%的正確率，其中靈敏度為86.60%與陽性預測率為87.71%。除詳盡比較探討各項可能影響判讀精度的因素，為了期許能發展出真正具有實用價值性的自動化快速動眼睡眠階段之判讀技術，利用跨睡眠中心的資料引申測試已發展出的機器學習分類器模組，由引申測試結果也得到近似的分類效能。

The sleep staging is the basic core technology in the study of sleep medicine. Via this technology, we can obtain the steep structure and use the results to help us to study different sleep related problems. The architecture of the sleep stages is often altered by various sleep disorders and physical or mental illnesses. Among all the sleep stages, the rapid eye movement (REM) sleep is particularly sensitive to these factors. In fact, many research results have demonstrated the relevance between REM sleep and the functions of cognition and learning. Therefore, if we can accurately detect REM sleep, by comparing REM parameters in different health conditions, we can generate valuable information to assist the medical specialists to evaluate the changes of the health conditions and adaptively adjust the medical treatment procedures.
The purpose of this thesis is to use a method of machine learning to perform automatic REM sleep detection. Compared to previous studies, this work has several unique features. To detect REM sleep, most of the previous studies needed to extract features from multiple channels of physiological signals. In comparison, this study only require a single channel of EEG signal and thus provide a convenient foundation for home care applications. With the support of the sleep centers, more than five hundred overnight sleep records have been used to develop the proposed approach. The size of the database is considerably larger than those used by the previous work.
By using a deep learning method, we achieve a detection accuracy of 92.26 with a corresponding kappa coefficient of 0.696. By developing a neighboring rule and a compensation rule, this study further improved the results to a kappa coefficient at 0.848, an accuracy of 95.91%, a sensitivity of 86.60%, and a positive predictive value of 87.71%. We have also tried to apply the proposed approach to different subgroups of patients. We have also tested the generalization capability of the proposed approach by using the REM detection method, which was developed by using data of one sleep data, to sleep data of another sleep data. The test results show that the performances of the proposed method is very similar in dealing with data from different sleep centers.

目錄
論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
目錄 vi
圖目錄 ix
表目錄 xi
第一章 緒論 1
1.1 前言 1
1.2 研究動機與目的 1
1.3 文獻回顧 3
1.4 小結 5
第二章 相關研究背景 6
2.1 國內睡眠醫學的發展 7
2.2 睡眠醫學與疾病的關聯 8
2.3 臨床的睡眠檢測標準 11
2.4 睡眠分期評估依據 12
2.5 小結 13
第三章 訊號處理與機器學習的介紹 15
3.1 資料庫簡述 16
3.1.1 腦波訊號的前處理 17
3.1.2 資料庫的篩選設定 18
3.2 機器學習軟體與硬體的應用 20
3.2.1 硬體設備 22
3.2.2 應用軟體的架構 23
3.3 分類器架構 24
3.3.1 卷積神經網路 27
3.3.2 MLP網路架構 30
3.4 鄰居法則改善分類效能 34
3.5 補償法則修正分類效能 35
3.6 小結 36
第四章 快速動眼期的偵測實驗結果 38
4.1 機器學習網路架構設定 38
4.2 分類效能指標 42
4.3 以整夜睡眠資料偵測REM期 44
4.4 以1比1睡眠資料形式偵測REM期 46
4.5 以相同睡眠結構比例資料偵測REM期 48
4.6 小結 49
第五章 引申測試及分類器補償修正 51
5.1 不同腦波頻道引申測試 51
5.2 C4腦波頻道訓練測試 52
5.3 鄰居法則分類器訓練修正結果 54
5.4 補償法則修正結果 55
5.5 以不同AHI族群各別建立分類器 56
5.6 跨睡眠中心的資料測試 61
5.7 小結 65
第六章 討論與未來展望 66
6.1 討論 66
6.2 未來展望 68
參考文獻 71
圖附錄 80
表附錄 85

1. Agarwal, R., & Gotman, J. (2001). Computer-assisted sleep staging. IEEE Transactions on Biomedical Engineering, 48 (12), 1412–1423.
2. Agarwal, R., Takeuchi, T., Laroche, S., & Gotman, J. (2005). Detection of rapid-eye movements in sleep studies. IEEE Transactions on Biomedical Engineering, 52 (8), 1390–1396.
3. Krizhevsky, A., Sutskever, I., Hinton, G. E. (2017). ImageNet classification with deep convolutional neural networks. Communications of the ACM, 60(6), 84-90.
4. Boukadoum AM and Kionas PY. (1986). EOG-based recording and automated detection of sleep rapid eye movements: a critical review, and some recommendations. Psychophysiology, 23, 598-610.
5. Bajaj, V., & Pachori, R. B. (2013). Automatic classification of sleep stages based on the time-frequency image of EEG signals. Computer Methods and Programs in Biomedicine, 112 (3), 320–328.
6. Berthomier, C., Drouot, X., Herman-Stoïca, M., Berthomier, P., Prado, J., Bokar-Thire, D., et al. (2007). Automatic analysis of single channel sleep EEG: Validation in healthy individuals. Sleep, 30 (11), 1587–1595.
7. Caffarel, J., Gibson, G. J., Harrison, J. P., Griffiths, C. J., & Drinnan, M. J. (2006). Comparison of manual sleep staging with automated neural network-based analysis in clinical practice. Medical & Biological Engineering & Computing, 44 (1-2), 105–110.
8. Corsi-Cabrera, M., Rosales-Lagarde, A., del Río-Portilla, Y., Sifuentes-Ortega, R., & Al- cántara-Quintero, B. (2015). Effects of selective REM sleep deprivation on pre- frontal gamma activity and executive functions. International Journal of Psy- chophysiology, 96 (2), 115–124.
9. Dykierek, P., Stadtmüller, G., Schramm, P., Bahro, M., van Calker, D., Braus, D. F., et al. (1998). The value of REM sleep parameters in differentiating Alzheimer’s disease from old-age depression and normal aging. Journal of Psychiatric Research, 32 (1), 1–9.
10. Douglas NJ, Thomas S, Jan MA. (1992). “Clinical value of polysomnography” Lancet, 339, 347-350.
11. Fraiwan, L., Lweesy, K., Khasawneh, N., Wenz, H., & Dickhaus, H. (2012). Automated sleep stage identification system based on time-frequency analysis of a single EEG channel and random forest classifier. Computer Methods and Programs in Biomedicine, 108 (1), 10–19.
12. Gann, H., Feige, B., Hohagen, F., van-Calker, D., Geiss, D., & Dieter, R. (2001). Sleep and the cholinergic rapid eye movement sleep induction test in patients with primary alcohol dependence. Biological Psychiatry, 50 (5), 383–390.
13. Goulart, L. I., Pinto, L. R., Jr., Perlis, M. L., Martins, R., Caboclo, L. O., Tufik, S., et al. (2014). Effects of different sleep deprivation protocols on sleep perception in healthy volunteers. Sleep Medicine, 15 (10), 1219–1224.
14. Güne ¸s a, S., Polata, K., & Yosunkayab, S. (2010). Efficient sleep stage recognition system based on EEG signal using k-means clustering based feature weighting. Expert Systems, 37 (12), 7922–7928.
15. Horne, J. A. (2015). Human REM sleep: Influence on feeding behaviour, with clinical implications. Sleep Medicine, 16 (8), 910–916.
16. Hashizume, Y., Kuwahara, H., Uchimura, N., Mukai, M., Shirakawa, S., Satomura, T., et al. (2001). Examination of accuracy of sleep stages by means of an automatic sleep analysis system 'Sleep Ukiha'. Psychiatry Clinical Neurosciences, 55, 199-200.
17. Huang, C. S., Lin, C. L., Ko, L. W., Liu, S. Y., Su, T. P., & Lin, C. T. (2014). Knowledge-based identification of sleep stages based on two forehead electroen- cephalogram channels. Frontiers in Neuroscience, 8, 263.
18. Hassan, A. R., & Bhuiyan, M. I. H. (2016). Computer-aided sleep staging using Complete Ensemble Empirical Mode Decomposition with Adaptive Noise and bootstrap aggregating. Biomedical Signal Processing and Control, 24, 1-10.
19. Imtiaz, S. A., & Rodriguez-Villegas, E. (2014). A low computational cost algorithm for REM sleep detection using single channel EEG. Annals of Biomedical Engineering, 42 (11), 2344–2359.
20. Jaseja, B., & Jaseja, H. (2013). Rapid eye movement (REM) sleep: A reliable biomarker of intractability in epilepsy. Epilepsy & Behavior, 29 (1), 256–257.
21. Jo, H. G., Park, J. Y., Lee, C. K., An, S. K., & Yoo, S. K. (2010). Genetic fuzzy classifier for sleep stage identification. Computers in Biology and Medicine, 40 (7), 629–634.
22. Karlen, W., & Floreano, D. (2011). Adaptive sleep-wake discrimination for wearable devices. IEEE Transactions on Biomedical Engineering, 58 (4), 920–926.
23. Kluge, M., Schüssler, P., Dresler, M., Yassouridis, A., & Steiger, A. (2007). Sleep onset REM periods in obsessive compulsive disorder. Psychiatry Research, 152 (1), 29–35.
24. Koch, H., Christensen, J. A., Frandsen, R., Zoetmulder, M., Arvastson, L., Chris- tensen, S. R., et al. (2014). Automatic sleep classification using a data-driven topic model reveals latent sleep states. Journal of Neuroscience Methods, 235, 130–137.
25. Koley, B., & Dey, D. (2012). An ensemble system for automatic sleep stage classification using single channel EEG signal. Computers in Biology and Medicine, 42 (12), 1186–1195.
26. Lajnef, T., Chaibi, S., Ruby, P., Aguera, P. E., Eichenlaub, J. B., Samet, M., et al. (2015). Learning machines and sleeping brains: Automatic sleep stage classification using decision-tree multi-class support vector machines. Journal of Neuroscience Methods, 250, 94–105.
27. Lara-Carrasco, J., Nielsen, T. A., Solomonova, E., Levrier, K., & Popova, A. (2009). Overnight emotional adaptation to negative stimuli is altered by REM sleep de- privation and is correlated with intervening dream emotions. Journal of Sleep Research, 18 (2), 178–187.
28. Levendowski, D. J., Popovic, D., Berka, C., & Westbrook, P. R. (2012). Retrospective cross-validation of automated sleep staging using electroocular recording in patients with and without sleep disordered breathing. International Archives of Medicine, 5 (1), 21.
29. Liang, S. F., Kuo, C. E., Hu, Y. H., & Cheng, Y. S. (2012). A rule-based automatic sleep staging method. Journal of Neuroscience Methods, 205 (1), 169–176.
30. Miroslav K, Gert P, Doris F, 1994, “AI-based approach to automatic sleep classification” Biological Cybermetics, 70, 443-448.
31. M Grözinger, J Röschke, B Kögel. (1995). Automatic recognition of rapid eye movement (REM) sleep by artificial neural network. Journal of Sleep Research. 4. 86-91.
32. Malhotra, A., Younes, M., Kuna, S. T., Benca, R., Kushida, C. A., Walsh, J., et al. (2013). Performance of an automated polysomnography scoring system versus computer-assisted manual scoring. Sleep, 36 (4), 573–582.
33. Malinowska, U., Klekowicz, H., Wakarow, A., Niemcewicz, S., & Durka, P. J. (2009). Fully parametric sleep staging compatible with the classical criteria. Neuroinfor- matics, 7 (4), 245–253.
34. Mellman, T. A., Pigeon, W. R., Nowell, P. D., & Nolan, B. (2007). Relationships between REM sleep findings and PTSD symptoms during the early aftermath of trauma. Journal of Traumatic Stress, 20 (5), 893–901.
35. Menz, M. M., Rihm, J. S., Salari, N., Born, J., Kalisch, R., Pape, H. C., (2013). The role of sleep and sleep deprivation in consolidating fear memories. Neuroimage, 75, 87–96.
36. Nykamp, K., Rosenthal, L., Folkerts, M., Roehrs, T., Guido, P., & Roth, T. (1998). The effects of REM sleep deprivation on the level of sleepiness/alertness. Sleep, 21 (6), 609–614.
37. Nan H. L., Chung Y. H., Yuxi L., Mark L. N., Jia L. S., Chih Y. H., Chen W. Y. (2017). Detecting rapid eye movement sleep using a single EEG signal channel. Expert Systems with Applications, 87, 220-227.
38. Palagini, L., Baglioni, C., Ciapparelli, A., Gemignani, A., & Riemann, D. (2013). REM sleep dysregulation in depression: State of the art. Sleep Medicine Reviews, 17 (5), 377–390.
39. Pan, S. T., Kuo, C. E., Zeng, J. H., & Liang, S. F. (2012). A transition constrained discrete hidden Markov model for automatic sleep staging. BioMedical Engineering OnLine, 11, 52.
40. Park, H. J., Oh, J. S., Jeong, D. U., & Park, K. S. (2000). Automated sleep stage scoring using hybrid rule- and case-based reasoning. Computers and Biomedical Research, 33 (5), 330–349.
41. Pérusse, A. D., Pedneault-Drolet, M., Rancourt, C., Turcotte, I., St-Jean, G., & Bastien, C. H. (2015). REM sleep as a potential indicator of hyperarousal in psy- chophysiological and paradoxical insomnia sufferers. International Journal of Psy- chophysiology, 95 (3), 372–378.
42. Porée, F., Kachenoura, A., Gauvrit, H., Morvan, C., Carrault, G., & Senhadji, L. (2006). Blind source separation for ambulatory sleep recording. IEEE Trans Inf Technol Biomed, 10 (2), 293–301.
43. Rechtschaffen, A., & Kales, A. (1968). A manual of standardized terminology, techniques and scoring systems for sleep stages of human subject. Washington DC: National Institutes of Health [Pub. No. 204].
44. Rajeev A, Jean G. (2001). Computer-Assisted sleep staging, IEEE Transactions on Biomedical Engineering, 48, 1412-1423.
45. Robert C, Guilpin C, Limoge A. (1998). Review of neural network applications in sleep research” Journal of Neuroscience methods, 79, 187-193.
46. Riemann, D., Spiegelhalder, K., Nissen, C., Hirscher, V., Baglioni, C., & Feige, B. (2012). REM sleep instability–a new pathway for insomnia? Pharmacopsychiatry, 45 (5), 167–176.
47. Rosales-Lagarde, A., Armony, J. L., Del Río-Portilla, Y., Trejo-Martínez, D., Conde, R., & Corsi-Cabrera, M. (2012). Enhanced emotional reactivity after selective REM sleep deprivation in humans: An fMRI study. Frontiers in Behavioral Neuroscience, 6, 25.
48. Rosenberg, R. S., & Van Hout, S. (2013). The American academy of sleep medicine inter-scorer reliability program: Sleep stage scoring. Journal Clinical Sleep Medicine, 9 (1), 81–87.
49. Saxvig, I. W., Lundervold, A. J., Grønli, J., Ursin, R., Bjorvatn, B., & Portas, C. M. (2008). The effect of a REM sleep deprivation procedure on different aspects of memory function in humans. Psychophysiology, 45 (2), 309–317.
50. Shi, J., Liu, X., Li, Y., Zhang, Q., Li, Y., & Ying, S. (2015). Multi-channel EEG-based sleep stage classification with joint collaborative representation and multiple kernel learning. Journal of Neuroscience Methods, 254, 94–101.
51. Sousa, T., Cruz, A., Khalighi, S., Pires, G., & Nunes, U. (2015). A two-step automatic sleep stage classification method with dubious range detection. Computers in Biology and Medicine, 59, 42–53.
52. Spiegel, R., Herzog, A., & Köberle, S. (1999). Polygraphic sleep criteria as predic- tors of successful aging: An exploratory longitudinal study. Biological Psychiatry, 45 (4), 435–442.
53. Schaltenbrand N, lengelle R, Macher JP. (1993). Neural Network model: Application to Automatic analysis of Human Sleep. Computers and Biomedical Research, 26, 157-171.
54. Schaltenbrand N, lengelle R, Toussaint M. (1996). Sleep stage scoring using the Neural Network model: Comparison between visual and automatic analysis in Normal subjects and patients. Sleep, 19:26-35.
55. Steiger, A., & Kimura, M. (2010). Wake and sleep EEG provide biomarkers in depression. Journal of Psychiatric Research, 44 (4), 242–252.
56. Stepnowsky, C., Levendowski, D., Popovic, D., Ayappa, I., & Rapoport, D. M. (2013). Scoring accuracy of automated sleep staging from a bipolar electroocular recording compared to manual scoring by multiple raters. Sleep Medicine, 14 (11), 1199–1207.
57. Sinha R.K., (2008). Artificial Neural Network and Wavelet Based Automated Detection of Sleep Spindles, REM Sleep and Wake States, J Med Syst, 32, 291-299
58. Su, B. L., Luo, Y., Hong, C. Y., Nagurka, M. L., & Yen, C. W. (2015). Detecting slow wave sleep using a single EEG signal channel. Journal of Neuroscience Methods, 243, 47–52.
59. Tagluk, M. E., Sezgin, N., & Akin, M. (2010). Estimation of sleep stages by an artificial neural network employing EEG, EMG and EOG. Journal of Medical Systems, 34 (4), 717–725.
60. Tandon, R., Lewis, C., Taylor, S. F., Shipley, J. E., DeQuardo, J. R., Jibson, M., et al. (1996). Relationship between DST nonsuppression and shortened REM latency in schizophrenia. Biological Psychiatry, 40 (7), 660–663.
61. Virkkala, J., Hasan, J., Värri, A., Himanen, S. L., & Müller, K. (2007a). Automatic sleep stage classification using two-channel electro-oculography. Journal of Neu- roscience Methods, 166 (1), 109–115.
62. Virkkala, J., Hasan, J., Värri, A., Himanen, S. L., & Müller, K. (2007b). Automatic detection of slow wave sleep using two channel electro-oculography. Journal of Neuroscience Methods, 160 (1), 171–177.
63. Vu, M. H., Hurni, C., Mathis, J., Roth, C., & Bassetti, C. L. (2011). Selective REM sleep deprivation in narcolepsy. Journal of Sleep Research, 20, 50–56.
64. Wiesner, C. D., Pulst, J., Krause, F., Elsner, M., Baving, L., Pedersen, A., et al. (2015). The effect of selective REM-sleep deprivation on the consolidation and affective evaluation of emotional memories. Neurobiol Learn Mem, 122, 131–141.
65. Wu, H. T., Talmon, R., & Lo, Y. L. (2015). Assess sleep stage by modern signal processing techniques. IEEE Transactions on Biomedical Engineering, 62 (4), 1159–1168.
66. Yaghouby, F., & Sunderam, S. (2015). Quasi-supervised scoring of human sleep in polysomnograms using augmented input variables. Computers in Biology and Medicine, 59, 54–63.
67. Zhu, G., Li, Y., & Wen P., P. (2014). Analysis and classification of sleep stages based on difference visibility graphs from a single-channel EEG signal. IEEE Journal of Biomedical and Health Informatics, 18 (6), 1813-1821.
68. 李宜容，2010，使用不同組合的腦電圖、眼動圖及肌動圖訊號自動偵測快速動眼睡眠期，碩士論文，國立中山大學機械與機電工程研究所.
69. 劉勝義，2004，臨床睡檢查學，合計圖書出版社。
70. 劉勝義，2011，睡眠醫學實務，合計圖書出版社。
71. 傅運文 譯，2017，深度學習快速入門-使用TensorFlow，博碩文化股份有限公司。