睡眠醫學其中很重要的課題就是睡眠結構。整夜睡眠的結構，除了快速動眼期，另一種就是非快速動眼期。非快速動眼期中扮演重要的角色就是慢波睡眠（SWS），慢波睡眠對保持頭腦清醒極為重要，也有資料顯示慢波睡眠對人體本身回復疲勞有很大的影響，因此在睡眠中有無SWS對在睡眠中有無真正休息為一個很大的指標。
　　有鑑於在睡眠判讀上的繁雜以及費時，本研究以單一腦波訊號來偵測SWS波睡眠，其目的希望能以最少及最有判斷力的腦波訊號判別SWS，本論文以兩個方向來著手，第一部分為個人化的應用，因睡眠判讀過程的不易，希望測試者只要能夠經過一次PSG檢查後並標註SWS，往後就可以使用此系統辨識此人，節省再度標註同一人的過程。第二部份為延伸化應用，測試者經過此系統後，就可判讀並偵測出SWS，達到延伸至未知待測組的目的。
　　本研究的核心在於綜合各種不同的類神經網路產生類神經資料庫，用不同標準篩選來應用，以適用於在多變化的生理訊號。其發展的分類器在自動偵測上平均有90.69%分類正確率，靈敏度平均為90.09%，特異度平均為91.24%。而在個人化的應用上，平均有93.37%分類正確率，靈敏度平均為92.91%，特異度平均為96.13%，此測試樣本為62名。而本論文在測試樣本也選取AHI大於20以上的做測試，分類效果平均也達到9成，顯示此方法在自動偵測以及個人化應用上有一定程度的分類能力。

One of the important topics in sleep medicine is sleep structure. Normal sleep consists of rapid eye movement (REM) sleep and nonrapid eye movement (NRME) sleep states. NREM sleep can be further classified into stage 1, 2 and slow wave sleep (SWS) according to the current sleep scoring standard. Among them, SWS has been considered to be very important due to its r restorative value.

The goal of this research is to detect SWS by using a single channel EEG signal. Its applications can be divided into two phases. In the first phase, a personalized SWS detector is designed for each individuals By combining these personalized SWS detectors, the second phase develops a general SWS detection method that can be applied to general population with any personalized training process.

By applying the proposed method to 62 persons, the experimental results show that the proposed method, in average, achieves 90.69% classification accuracy 90.09% sensitivity and 93.97% specificity. Our experimental results also demonstrate, when applied to persons with higher AHI (apnoea-hypopnea index) values, the proposed method can still provided satisfactory results.

目錄
摘要 III
Abstract IV
第一章 緒論 1
1.1引言 1
1.2研究動機與目的 2
1.3論文架構 4
第二章 睡眠醫學以及腦電波訊號 5
2.1睡眠檢查 5
2.2 腦電圖生理電位和電極位置 5
2.3夜間睡眠以及腦波 7
2.4 睡眠期以及其腦波特徵判讀標準 10
第三章 MLP網路架構和委員會機器(Committee Machine) 14
3.1 類神經網路 14
3.2 委員會機器 15
第四章 單一腦波訊號偵測慢波睡眠 17
4.1 計算訊號的能量以及頻寬 17
4.2 不同頻帶能量百分比做為特徵 17
4.3 EEG時域特徵向量 18
4.4 EEG頻域特徵向量 21
4.5 時域特徵和頻域特徵產生委員會機器 23
4.6 以基本特徵選取類神經網路 25
4.6.1使用Power比例以及Bandwidth比例 25
4.6.2　使用SWS和Others個數比例 30
第五章 實驗結果與討論 32
5.1 個人化分類器結果 32
5.2 使用分類器測試其他人實驗 35
5.3 測試10<AHI<20受測樣本實驗 39
5.4討論以及分析 40
5.4.1 分析測試精度 40
5.4.2 分類錯誤SWS分析 42
5.4.3 各種標準門檻使用多少委員數分析 43
第六章 總結與未來展望 45
參考文獻 48
附錄Ι　AHI 小於10以下受測以及訓練樣本62名 50
附錄II　AHI 大於10小於20受測以及訓練樣本34名 52
附錄III 使用各個門檻值選取委員精度列表 53

Agarwal R and Gotman Jean. “Computer-Assisted Sleep Staging”, IEEE Transactions on Biomedical Engineering, vol.48, pp1412-1423, 2001.
Baumgart-Schmitt R , Herrmann W M et al. “On the Use of Neural Network Techniques to Analyze Sleep EEG Data”, Neuropsychobiology , vol. 37,pp49-58
Caffarel J, Gibson J et al. “Comparison of manual sleep staging with automated neural network-based analysis in clinical practice”, International Federation for Medical and Biological Engineering, vol 44,pp105-110, 2006.
Estrada E, Nazeran H et al. “EEG Feature Extraction For Classification Of Sleep Stages”,Proceedings of the 26th Annual International Conference of the IEEE EMBS ,pp196-199 ,2004.
Flexer A , Gruber G et al. “A reliable probabilistic sleep stager based on a single EEG signal”, Aritifiicial Intelligence in Medicine, vol.33,pp199-207, 2005.
Fell J, R&#246;schke J et al, “Discrimination of sleep stages:a comparison between spectral and nonlinear EEG measure”, Electroencephalography and clinical Neurophysiology, vol 98, pp401-410, 1996.
Haykin S, 1999, Neoral Networks : A Comprehensive foundation, 2nd ed. Englewood cliffs , NJ: Pretice-Hall.
Iber C,MD et al. “The AASM Manual for the Scoring of Sleep and Associated Event”AASM Manual for Scoring Sleep,2007.
Louis RP., Lee J et al, “Design and validation of a computer-based sleep-scoring algorithm”, Journal of Neuroscience Methods, vol 133, pp71-80, 2004.
Magosso E , Ursino M et al. “Visual and computer-based detection of slow eye movements in overnight and 24-h EOG recordings”, Clinical Neurophysiology, vol.118, pp1122-1133, 2007.

Park H J , Oh J S et al. “Automated Sleep Stage Scoring Using Hybrid Rule and Case-Based Reasoning”, Computers and Biomedical Reserach, vol.33, pp330-349, 2000.
Pin&#234;roa P , Garciaa P , “Sleep stage classification using fuzzy sets and
machine learning techniques”, Neurocomputing, vol. 58–60, pp58–60, 2004.
Principe JC, Gala SK et al, “Sleep Staging Automaton Based on the Theory of Ecidence”, IEEE Transactions on biomedical Engineering, vol. 35, No.5, pp503-509, 1999.
Por&#232;e F, Kachenoura A et al. “Blind Source Separation for Ambulatory
Sleep Recording”, IEEE TRANSACTIONS ON INFORMATION TECHNOLOGY IN BIOMEDICINE, Vol. 10, No. 2, pp293-301, 2006.
Tian JY, Liu JQ “Automated Sleep Staging by a Hybrid System Comprising Neural Network and Fuzzy Rule-based Reasonong”, IEEE Engineering in Meddicine and Biology 27th Annual Conference, pp4115-4118, 2005.

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, ”博士論文, 國立中山大學機械與機電工程研究所.
吳炯廷, 2007, “以雙眼眼電圖相關係數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.
劉勝義, 2004 , 臨床睡眠檢查學, 合計圖書出版社
葉怡成, 1997, 應用類神經網路, 儒林