睡眠階段判讀技術是在睡眠醫學研究中用來評估睡眠結構是否異常的基本關鍵技術。根據 R&K 法則的定義，人類的睡眠階段可以區分為四個階段，分別為清醒期、淺眠期、深眠期及快速動眼期。而睡眠分期主要係依據腦電圖，並輔以眼電圖及肌電圖進行判斷。
本研究使用不同組合的腦電圖、眼動圖及肌電圖訊號來偵測慢波睡眠，共有十六種頻道的組合。本研究依據慢波睡眠的高幅慢波特性，發展許多能反映其特性的特徵變數，並挑選合適的特徵變數使用類神經網路建立分類器，進行慢波睡眠的偵測。本研究特別注意到人與人之間生理訊號的差異並提出解決此問題的方法，進而提升偵測慢波睡眠的效能。實驗的資料人數分別為兩個不同睡眠中心的1318名受測者及947名受測者，本研究將這些受測者分成五組分別做訓練及引申測試的資料測試本研究所提出偵測慢波睡眠期方法的效能。使用單頻道腦電圖偵測1318名受測者的慢波睡眠結果與技師判讀結果比較，Kappa為0.63，使用雙眼眼動圖訊號Kappa為0.6，使用多頻道訊號組合最好的Kappa為0.66。本研究實驗資料的規模遠遠超過先前的研究，先前研究的受測者數量往往過少，所以結果較缺乏代表性。實驗結果證明本文提出偵測慢波睡眠的方法在受測者超過一千人次的資料中仍有一定程度的分類效能。

Sleep staging can be used to assess whether sleep structure is abnormal. According to the R&K rule, human sleep can be divided into four different stages: Awake, Light Sleep, Deep Sleep and Rapid-Eye-Movement (REM) Sleep. Conventionally, sleep staging are scored mainly by EEG signals and complementally by EOG and EMG signals.
The goal of this study is to detect slow wave sleep (SWS) automatically by using different combinations of EEG, EOG, and EMG signals. In particular, a total of 16 combinations of channels have been studied. Based on high amplitude slow wave characteristics of SWS, this study develops many of feature variables to characterize SWS. A subset of these features are employed to design neural network classifier to detect SWS. This study has noted interpersonal-differences in physiological signals between people and proposes solutions to this problem to improve the performance of SWS detection. The number of tested subjects from two different sleep centers is 1318 and 947 subjects, respectively. These subjects were divided into five groups for training and testing data in order to test performance of our proposed approach. By applying the proposed approach to 1318 subjects, the experimental results show that the proposed method achieves kappa of 0.63 by using a single EEG channel, kappa of 0.6 by using two channels EOG and kappa of 0.66 by using the best combination of multi-channel singals. The size of dataset used in this work is significantly large than those of previous studies and thus provide more reliable experimental results. The experimental results show that the proposed approach can provide satisfactory performance in dealing with dataset with more than 1000 subjects.

目錄 I
圖目錄 IV
表目錄 IX
摘要 XVII
Abstract XVIII
第一章 緒論 1
1.1前言 1
1.2研究動機與目的 2
1.3文獻回顧 3
第二章 睡眠生理訊號 7
2.1睡眠生理狀態 7
2.2睡眠檢查 9
2.3腦電圖、眼動圖及肌電圖的電位生理與電極位置 11
2.4睡眠分期規則 16
2.5不同睡眠階段的腦電圖、眼動圖和肌電圖型態 18
第三章 分類器與演算法 24
3.1類神經網路 24
3.1.1 MLP網路架構 25
3.1.2 MLP網路在型態鑑別上之相關設定 26
3.2最近鄰居分類器 27
3.3向量量化編碼方法 28
3.4 修正型LBG演算法 30
3.4.1向量量化過程中的失真 30
3.4.2主軸方向 31
3.4.3修正型LBG演算法程序 32
3.5應變式VQ分類方法 36
3.6 Simplex演算法 37
第四章 使用不同組合的腦電圖、眼動圖及肌電圖訊號自動偵測慢波睡眠 43
4.1建立特徵變數候選人 46
4.1.1越零點數目 47
4.1.2越零點間距 48
4.1.3越零點加權面積 51
4.1.4越零點間距標準差 52
4.1.5能量 52
4.1.6越零點直方圖 53
4.1.7越零點間距直方圖 54
4.2挑選特徵變數 55
4.3克服人與人之間生理訊號的差異而新增的特徵變數 60
4.3.1加入相對百分比 60
4.3.2加入區域百分比 63
4.4建立類神經分類器 66
4.5不同醫院訊號資料的轉換 70
第五章 實驗結果與討論 72
5.1分類效能的指標 72
5.2分類器的訓練、引申測試結果及討論 74
5.2.1不同睡眠中心的分類結果 75
5.2.2相同睡眠中心的分類結果 82
5.2.3相對高慢波比例下的分類結果 88
5.2.4有無戴陽壓呼吸器(CPAP)的相同受測者分類結果 92
5.3各頻道組合的效能比較 95
5.4進一步分析可能會影響偵測慢波睡眠效能的因素 98
5.4.1受測者人數增加對慢波睡眠偵測效能的影響 101
5.4.2慢波睡眠的分類錯誤分析 108
5.4.3受測者年紀對慢波睡眠偵測效能的影響 118
5.4.4受測者AHI對慢波睡眠偵測效能的影響 120
5.5整夜睡眠階段判讀結果與討論 126
5.5.1整夜睡眠階段判讀流程 127
5.5.2整夜睡眠階段判讀結果與效能比較 129
5.5.3受測者年紀與AHI對整夜睡眠階段判讀結果的影響 136
第六章 結論與未來展望 145
參考文獻 147
附錄I 勝美473名受測者與勝美 474 名受測者在雙頻道和四頻道組合之整夜睡眠階段判讀的訓練及引申測試逐頁分類結果 151

Agarwal, R., and Gotman, J., 2001, “Computer-Assisted sleep staging,” IEEE Transactions on Biomedical Engineering, vol. 48, pp. 1412-1423.
Agarwal, R., Takeuchi, T., Laroche, S., Gotman, J., 2005, “Detection of rap-id-eye movements in sleep studies,” IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING, vol. 52, pp. 1390-1396.
Baumgart-Schmitt, R., Herrmann, W.M., and Eilers, R., 1998, “On the use of neural network techniques to analyze sleep EEG data,” Neuropsychobiology, vol. 37, pp. 49-58.
Berthomier, C., Drouot, X., Herman-Stoica, M., Berthomier, P., Prado, J., Bokar-Thire, D., Benoit, O., Mattout, J., and d'Ortho, M.P., 2007, “Automatic analysis of single-channel sleep EEG: validation in healthy individuals,” Sleep, vol. 30, pp. 1587-1595.
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,” Med Biol Eng Comput, vol. 44, pp. 105-10.
Chidananda, G.K. and Krishna, G., 1979, “The condensed nearest neighbor rule using the concept of mutual nearest neighborhood,” IEEE Transactions on Information Theory, vol. IT-25, pp. 488–490.
Cover, T.M. and Hart, P.E., 1967, “Nearest neighbor pattern classification,” IEEE Trans. Inform. Theory, vol. IT-13, pp. 21-27.
Durka, P.J., Malinowska, U., Szelenberger, W., Wakarow, A., Blinowska, K.J., 2005, “High resolution parametric description of slow wave sleep,” Journal of Neuroscience Methods, vol. 147, pp. 15-21.
Flexer, A., Gruber, G., and Dorffner, G., 2005, “A reliable probabilistic sleep stager based on a single EEG signal,” Artificial Intelligence in Medicine, vol. 33, pp. 199-207.
Grözinger, M., WOLF, C., UHL, T., SCHAFFNER C., and Röschke, J., 1997, “Online Detection of REM sleep based on the comprehensive evaluation of short adjacent EEG segments by artificial neural networks,” Prog. Neuro-Psychopharmacol. & Biol. Psychiat, vol. 21, pp. 951-963.
Grözinger, M., Fell, J., and Röschke, J., 2001, “Neural net classification of REM sleep based on spectral measures as compared to nonlinear measures,” Biol. Cybern, vol. 85, pp. 335-341.
Hanaoka, M., Kobayashi, M., Yamazaki, H., 2002, “Automatic sleep stage scoring based on waveform recognition method and decision-tree learning,” Systems and Computers in Japan, vol. 33, pp. 1-13.
Hart, P.E., 1968, “The condensed nearest neighbor rule,” IEEE Transactions on Information Theory, vol. IT-14, pp. 515–516.
Haykin, S., 1999, “Neural Networks: A Comprehensive Foundation,” 2nd Edition, Pretice Hall Internation.
Herscovici, S., Pe’er, A., Papyan, S., and Lavie, P., 2007, “Detecting REM sleep from the finger: an automatics REM sleep algorithm based on peripheral arterial tone (PAT) and actigraphy,” Physiological Measurement, vol. 28, No. 2, pp. 129-140.
Kubat, M., Pfurtsceller, G., and Flotzinger, D., 1994, “AI-based approach to automatic sleep classification,” Biological Cybermetics, vol. 70, pp. 443-448.
Linde, Y., Buzo, A., and Gray, R.M., 1980, “An algorithm for vector quantizer design,” IEEE Transactions on Communications, vol. 28, No. 1, pp. 84-95.
Louis, R.P., Lee, J., Stephenson, R., 2004, “Design and validation of a computer-based sleep-scoring algorithm,” Journal of Neuroscience Methods, vol. 133, pp. 71-80.
Magosso, E., Ursino, M., Zaniboni, A., Provini, F., and Montagna, P., 2007, “Visual and computer-based detection of slow eye movements in overnight and 24-h EOG recordings,” Clin Neurophysiol, vol. 118, pp. 1122-1133.
Mendez, M., Bianchi, A.M., Villantieri, O., Cerutti, S., 2006, “Time-varying analysis of the heart rate variability during REM and non REM sleep stages,” Conf Proc IEEE Eng Med Biol So,1:3576-9.
Nelder, J.A., Mead, R., 1965, “A Simplex for Function Minimization,” Computer Journal, vol. 7, pp. 308-313.
Park, H.-J., Oh, J.-S., Jeong, D.-U., and Park, K.-S., 2000, “Automated sleep stage scoring using hybrid rule- and case-based reasoning,” Computers and Biomedical Research, vol. 33, pp.330-349.
Porèe, F., Kachenoura, A., Gauvrit, H., Morvan, C., Carrault, G., and Senhadji, L., 2006, “Blind Source Separation for Ambulatory Sleep Recording,” IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, vol. 10, No. 2, pp. 293-301.
Rechtschaffen, A. and Kales, A., 1968, “A manual of standardized terminology: techniques and scoring system for sleep stages of human subjects,” Los Angeles, Calif: UCLA Brain Information Service/Brain Research Institute.
Robert, C., Karasinski, P., Natowicz, R., Limoge, A., 1996, “Adult rat vigilance states discrimination by artificial neural networks using a single EEG channel,” Physiol Behav, vol. 59, pp. 1051-60.
Robert, C., Guilpin, C., and Limoge, A., 1998, “Review of neural network applications in sleep research,” Journal of Neuroscience methods, vol. 79, pp. 187-193.
Schaltenbrand, N., lengelle, R., macher, J.P., 1993, “Neural Network model : Application to Automatic analysis of Human Sleep,” Computers and Biomedical Research, vol. 26, pp. 157-171.
Schaltenbrand, N., lengelle, R., Toussaint, M. et al., 1996, “Sleep stage scoring using the Neural Network model : Comparison between Visual and automatic analysis in Normal subjects and patients,” Sleep, vol. 19, pp. 26-35.
Sinha, R.K., 2008, “Artificial neural network and wavelet based automated detection of sleep spindles, REM sleep and wake states,” J. Med. Syst. vol. 32, pp. 291-299.
Viera, A.J. and Garret, J.M., 2005, “Understanding Interobserver Agreement: The Kappa Stastic,” Family Medicine, vol. 37, No. 5, pp. 360-363.
Virkkala, J., Hasan, J., Värri, A., Himanen, S.L., and Müller, K., 2007, “Automatic sleep stage classification using two-channel electro-oculography,” Journal of Neuroscience Methods, vol. 166, pp. 109-15.
Virkkala, J., Hasan, J., Värri, A., Himanen, S.L., and Müller, K., 2007, “Automatic detection of slow wave sleep using two channel electro-oculography,” Journal of Neuroscience Methods, vol. 160, pp. 171-177.
Yen, C.W., Young, C.N., and Nagurka, M.L., 2004, “A vector quantization method for nearest neighbor classifier design,” Pattern Recognition Letters, vol. 25, pp. 725-731.
Epstein, L.J. and Mardon, S., 李宛蓉譯, 2007, “哈佛醫生的優質睡眠全書,” 商周出版.
王文彥，2009， “以單眼眼動圖進行睡眠階段判讀” ，國立中山大學碩士學位論文。
王彥仕，2008， “以眼電圖訊號偵測快速動眼睡眠期與清醒期” ，國立中山大學碩士學位論文。
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” ，國立中山大學碩士學位論文。
吳炯廷，2007， “以雙眼眼電圖相關係數偵測快速動眼睡眠期” ，國立中山大學碩士學位論文。
邱晧智，2008， “以單頻道腦電波訊號偵測慢波睡眠” ，國立中山大學碩士學位論文。
陳道信，2009， “以眼動圖訊號處理睡眠階段分類問題” ，國立中山大學碩士學位論文。
萬台飛、陸建邦，1986，眼振圖手冊，合記圖書出版社。
楊傑能，2007， “以眼電圖訊號檢測快速動眼睡眠期的向量量化編碼方法” ，國立中山大學博士學位論文。
蔡東遠，2010， “使用不同組合的腦電圖、眼動圖及肌動圖訊號自動分類清醒期及淺睡期” ，國立中山大學碩士學位論文。
劉勝義，2004，臨床睡眠檢查學，合記圖書出版社。
戴子斐，2009， “以單頻道腦電圖進行睡眠階段判讀” ，國立中山大學碩士學位論文。