許多人被睡眠疾病與相關問題所困擾。目前臨床睡眠診斷上主要使用PSG所收錄的電生理訊號作為專家來判讀睡眠階段的依據。然而，專家判讀需要耗費許多人力與時間且受專家個人主觀上的影響，所以很多基於多通道睡眠生理訊號的自動睡眠判讀系統已被開發。可是收錄多重生理訊號有很多缺點，如大量的電極線對於使用者造成睡眠干擾與無法獨立使用等問題。腦電訊號是臨床的睡眠判讀法則中主要的判讀依據。因此我們先開發了一套基於單通道腦電訊號的自動睡眠判讀系統。我們使用多尺度熵與自迴歸模型參數來分析32位健康的成年人的整夜睡眠時的腦電訊號，並運用線性分類器進行睡眠階段分類。我們也針對睡眠週期的連續性和睡眠階段的限制，考慮前後週期所擁有的資訊，將線性分類器判斷後的結果再做平滑化處理以得到最後自動睡眠判讀的結果。本系統的判讀結果與專家判讀結果相比，整體一致性與kappa係數可以達到87.15％和0.81，這效能亦優於目前臨床判讀的標準。
相較於腦電訊號，眼動訊號只需在眼部周圍黏貼電極，並且也能擷取到某些睡眠腦電訊號的特徵。因此眼動訊號兼具居家使用的便利性與可應用於睡眠階段判讀的優點。為了適用於居家照顧，我們再開發出一個基於單通道睡眠眼動訊號的自動睡眠判讀系統。除了多尺度熵與自迴歸模型參數，我們也提出了一個新的特徵-多尺度線段長度，來提升快速眼動期的準確率。經過同樣32位受試者的整晚眼動訊號的分析與測試，本系統的判讀結果與專家判讀結果相比，整體一致性與kappa係數可以達到83.33％和0.75。這效能是目前只使用睡眠眼動訊號的自動判讀方法中最好的。因此我們把這套自動判讀方法再延伸到居家睡眠環境控制的應用上。
在本論文的附錄中，我們亦展示了我們的自動睡眠判讀方法的可應用性。近年來，有很多評估使用者睡眠品質或監測睡眠環境的系統被開發。然而，目前依據使用者的睡眠期來主動改變睡眠環境，以幫助使用者擁有更好的睡眠品質之產品與方法非常稀少。燈光是睡眠環境中的主要因素，因此我們結合單通道眼動電訊號的自動睡眠判讀方法以及根據使用者的睡眠期來調整燈光強度的演算法來開發一套閉迴路人機界面系統。經由3位受測者的測試結果，證實以我們的系統來控制睡眠環境燈光的可行性。我們未來將會考慮更多睡眠環境的因素來幫助使用者擁有健康、舒適與安全的睡眠品質與環境。
此外，許多研究指出睡眠與記憶鞏固或學習效益提升非常的相關。但是這些相關實驗的步驟往往需要專家與實驗人員整晚長時間的監控，造成許多的人力與時間的耗費。未來我們也會把我們的方法應用於睡眠與記憶鞏固或學習效益提升等相關實驗的自動化上，以節省更多的人力與時間成本。

Sleep diseases, such as insomnia and obstructive sleep apnea, seriously affect patients’ quality of life. For diagnosis, polysomnographic (PSG) recordings are most usually taken for sleep stage scoring. However, manual scored by well-trained expert which is a time-consuming and subjective process. Many multi-channel-based automatic sleep staging methods have been developed. These approaches have many drawbacks. For example, the large amount of wires connections for conventional PSG often cause sleep interference and not self-applicable. Sleep EEG signals is the main basis of the manual sleep scoring rules in clinical diagnosis. Therefore, we develop an automatic sleep staging method based on single-channel sleep EEG signals. We utilize multiscale entropy and autoregressive model coefficients to analyze the 32 all-night sleep EEG recordings from 32 healthy adult and the linear discriminant analysis (LDA) was utilized to classify each epoch into five sleep stages. After classifying the sleep stage by LDA, some misclassified epochs can be corrected according to the temporal contextual information. We utilize the smoothing process to smooth and fine-tune the results of the classifier. The average accuracy and kappa coefficient of the proposed method applied to 16 all-night (PSG) recordings compared with the manual scorings can reach 87.15 % and 0.81, respectively. The results are also better than the range in the inter-score agreement.
Compared to EEG, electrodes placement of EOG recording is around the eyes, and EOG signals are also coupling some of sleep characteristics of EEG signals. Therefore, EOG has the ease of use in the home and can be applied to sleep scoring. For the applicability of home care, we also develop an automatic sleep staging method based on single-channel sleep EOG signals. In addition to multiscale entropy and autoregressive model coefficients, we also propose a new feature, multiscale line length, to enhance the sensitivity of rapid eye movement (REM) stage. The average accuracy and kappa coefficient of the proposed method compared with the manual scorings can reach 83.33 % and 0.75, respectively. The performance of our proposed method is the best in currently automatic sleep staging methods based on single-channel sleep EOG signals. So we extend the automatic sleep staging method to the application of sleep environmental control at home.
In the appendix, we also show the applicability of our automatic sleep scoring method. Recently, many systems or products to support healthy sleep by monitoring the sleep environment or users’ activities and sleep quality have been developed. However, actively on-line adjusting conditions of the sleep environment according to sleep stages of the user are rare. Light is the main factor in sleep environment. We use our proposed sleep scoring method combined with a light-control algorithm based on sleep stage to develop a closed-loop human–computer interaction (HCI) system. With the experimental results of three subjects, the feasibility of controlling the light in sleep environments is demonstrated. In the future, we will consider more sleep environmental factors for the healthy, comfortable and safe sleep quality and environment.
In addition, many previous studies had pointed out that sleep and memory consolidation, learning, or performance improvement is very relevant. However, these related experiments often require experts and laboratory personnel to monitor all night, it takes a lot of manpower and time-consuming. To save more time and manpower costs, we will apply our method to related studies and experiments for automation in the future.

Agarwal, R., and Gotman, J. (2001). Computer-assisted sleep staging. IEEE Trans Biomed Eng, 48(12), 1412-1423.
Agnew, H Webb, Webb, Wilse B, and Williams, Robert L. (1966). THE FIRST NIGHT EFFECT: AN EEG STUDYOF SLEEP. Psychophysiology, 2(3), 263-266.
Altman, Duglas G. (1991). Practical statistics for medical research (Vol. 12): Chapman & Hall/CRC.
Anderer, P., Gruber, G., Parapatics, S., Woertz, M., Miazhynskaia, T., Klosch, G., et al. (2005). An E-health solution for automatic sleep classification according to Rechtschaffen and Kales: validation study of the Somnolyzer 24 x 7 utilizing the Siesta database. Neuropsychobiology, 51(3), 115-133.
Andre, David, Pelletier, Ray, Farringdon, Jonny, Safier, Scott, Talbott, Walter, Stone, Ron, et al. (2006). The Development of the SenseWear® armband, a Revolutionary Energy Assessment Device to Assess Physical Activity and Lifestyle. BodyMedia Inc.
Bach, Veronique, Telliez, Frédéric, and Libert, Jean-Pierre. (2002). The interaction between sleep and thermoregulation in adults and neonates. Sleep Medicine Reviews, 6(6), 481-492.
Bauer, Jared, Consolvo, Sunny, Greenstein, Benjamin, Schooler, Jonathan, Wu, Eric, Watson, Nathaniel F, et al. (2012). ShutEye: encouraging awareness of healthy sleep recommendations with a mobile, peripheral display. Paper presented at the Proceedings of the 2012 ACM annual conference on Human Factors in Computing Systems.
Berthomier, C., Drouot, X., Herman-Stoica, 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.
Berthomier, C., Prado, J., and Benoit, O. (1999). Automatic sleep EEG analysis using filter banks. Biomed Sci Instrum, 35, 241-246.
Bloch, Boaz, Reshef, Alon, Vadas, Limor, Haliba, Yamit, Ziv, Naomi, Kremer, Ilana, et al. (2010). The effects of music relaxation on sleep quality and emotional measures in people living with schizophrenia. Journal of music therapy, 47(1), 27.
Bonnet, Michael H. (1989). The effect of sleep fragmentation on sleep and performance in younger and older subjects. Neurobiology of aging, 10(1), 21-25.
Brawn, Timothy P, Fenn, Kimberly M, Nusbaum, Howard C, and Margoliash, Daniel. (2010). Consolidating the effects of waking and sleep on motor-sequence learning. The Journal of Neuroscience, 30(42), 13977-13982.
Burioka, N., Miyata, M., Cornelissen, G., Halberg, F., Takeshima, T., Kaplan, D. T., et al. (2005). Approximate entropy in the electroencephalogram during wake and sleep. Clin EEG Neurosci, 36(1), 21-24.
Chan, Moon Fai, Wong, Zi Yang, Onishi, Hideaki, and Thayala, Naidu Vellasamy. (2012). Effects of music on depression in older people: a randomised controlled trial. Journal of Clinical Nursing, 21(5‐6), 776-783.
Chang, Da-Wei, Liu, You-De, Young, Chung-Ping, Chen, Jing-Jhong, Chen, Ying-Huang, Chen, Chun-Yu, et al. (2012). Design and Implementation of a Modularized Polysomnography System. Instrumentation and Measurement, IEEE Transactions on, 61(7), 1933-1944.
Chialvo, D. R. (2002). Physiology: unhealthy surprises. Nature, 419(6904), 263.
Choe, Eun Kyoung, Consolvo, Sunny, Watson, Nathaniel F., and Kientz, Julie A. (2011). Opportunities for computing technologies to support healthy sleep behaviors. Paper presented at the Proceedings of the SIGCHI Conference on Human Factors in Computing Systems, Vancouver, BC, Canada.
Cohen, Jacob. (1960). A coefficient of agreement for nominal scales. Educational and psychological measurement, 20(1), 37-46.
Costa, M., Goldberger, A. L., and Peng, C. K. (2002). Multiscale entropy analysis of complex physiologic time series. Phys Rev Lett, 89(6), 068102.
Costa, M., Goldberger, A. L., and Peng, C. K. (2005). Multiscale entropy analysis of biological signals. Phys Rev E Stat Nonlin Soft Matter Phys, 71(2 Pt 1), 021906.
Costa, M., Peng, C. K., L. Goldberger, Ary, and Hausdorff, Jeffrey M. (2003). Multiscale entropy analysis of human gait dynamics. Physica A: Statistical Mechanics and its Applications, 330(1–2), 53-60.
Danker-Hopfe, H., Anderer, P., Zeitlhofer, J., Boeck, M., Dorn, H., Gruber, G., et al. (2009). Interrater reliability for sleep scoring according to the Rechtschaffen & Kales and the new AASM standard. J Sleep Res, 18(1), 74-84.
Danker-Hopfe, H., Kunz, D., Gruber, G., Klosch, G., Lorenzo, J. L., Himanen, S. L., et al. (2004). Interrater reliability between scorers from eight European sleep laboratories in subjects with different sleep disorders. J Sleep Res, 13(1), 63-69.
Deshmukh, Abhijeet D, Sarvaiya, Avani A, Seethalakshmi, R, and Nayak, Ajita S. (2009). Effect of Indian classical music on quality of sleep in depressed patients: a randomized controlled trial. Nordic Journal of Music Therapy, 18(1), 70-78.
Diekelmann, Susanne, Wilhelm, Ines, and Born, Jan. (2009). The whats and whens of sleep-dependent memory consolidation. Sleep medicine reviews, 13(5), 309-321.
Duman, Fazil, Erdamar, Aykut, Erogul, Osman, Telatar, Ziya, and Yetkin, Sinan. (2009). Efficient sleep spindle detection algorithm with decision tree. Expert Systems with Applications, 36(6), 9980-9985.
Escudero, J, Abásolo, D, Hornero, R, Espino, P, and López, M. (2006). Analysis of electroencephalograms in Alzheimer's disease patients with multiscale entropy. Physiological Measurement, 27(11), 1091.
Esteller, Rosana, Echauz, Javier, Tcheng, T, Litt, Brian, and Pless, Benjamin. (2001). Line length: an efficient feature for seizure onset detection. Paper presented at the Engineering in Medicine and Biology Society, 2001. Proceedings of the 23rd Annual International Conference of the IEEE.
Fischer, Stefan, Hallschmid, Manfred, Elsner, Anna Lisa, and Born, Jan. (2002). Sleep forms memory for finger skills. Proceedings of the National Academy of Sciences, 99(18), 11987-11991.
Flexer, A., Gruber, G., and Dorffner, G. (2005). A reliable probabilistic sleep stager based on a single EEG signal. Artif Intell Med, 33(3), 199-207.
Fogel, Stuart M, and Smith, Carlyle T. (2011). The function of the sleep spindle: a physiological index of intelligence and a mechanism for sleep-dependent memory consolidation. Neuroscience & Biobehavioral Reviews, 35(5), 1154-1165.
Fontana Gasio, P., Krauchi, K., Cajochen, C., Someren, Ev, Amrhein, I., Pache, M., et al. (2003). Dawn-dusk simulation light therapy of disturbed circadian rest-activity cycles in demented elderly. Exp Gerontol, 38(1-2), 207-216.
Fromm, Evantina, Horlebein, Christina, Meergans, Alexandra, Niesner, Marianne, and Randler, Christoph. (2011). Evaluation of a dawn simulator in children and adolescents. Biological Rhythm Research, 42(5), 417-425.
Gimenez, M. C., Hessels, M., van de Werken, M., de Vries, B., Beersma, D. G., and Gordijn, M. C. (2010). Effects of artificial dawn on subjective ratings of sleep inertia and dim light melatonin onset. Chronobiol Int, 27(6), 1219-1241.
Goldberger, Ary L, Amaral, Luis AN, Glass, Leon, Hausdorff, Jeffrey M, Ivanov, Plamen Ch, Mark, Roger G, et al. (2000). PhysioBank, PhysioToolkit, and PhysioNet: Components of a new research resource for complex physiologic signals. Circulation, 101(23), e215-e220.
Guo, Ling, Rivero, Daniel, Dorado, Julián, Rabunal, Juan R, and Pazos, Alejandro. (2010). Automatic epileptic seizure detection in EEGs based on line length feature and artificial neural networks. Journal of neuroscience methods, 191(1), 101-109.
Haejeong, Park, Kwangsuk, Park, and Do-Un, Jeong. (2000, 2000). Hybrid neural-network and rule-based expert system for automatic sleep stage scoring. Paper presented at the Engineering in Medicine and Biology Society, 2000. Proceedings of the 22nd Annual International Conference of the IEEE.
Hernández-Ruiz, Eugenia. (2005). Effect of music therapy on the anxiety levels and sleep patterns of abused women in shelters. Journal of music therapy, 42(2), 140.
Himanen, Sari-Leena, and Hasan, Joel. (2000). Limitations of rechtschaffen and kales. Sleep Medicine Reviews, 4(2), 149-167.
Hussain, MS, and Mamun, Md. (2012). Effectiveness of the wavelet transform on the surface EMG to understand the muscle fatigue during walk. Measurement Science Review, 12(1), 28-33.
Jansen, B. H., and Dawant, B. M. (1989). Knowledge-based approach to sleep EEG analysis--a feasibility study. IEEE Trans Biomed Eng, 36(5), 510-518.
Jespersen, Kira V, Koenig, Julian, Jennum, Poul, and Vuust, Peter. (2013). Listening to music for improving sleep in adults with insomnia. The Cochrane Library.
Jespersen, Kira Vibe, and Vuust, Peter. Music for improvement of trauma-related sleep problems. group (t (13), 2, 05.
Kang, X., Jia, X., Geocadin, R. G., Thakor, N. V., and Maybhate, A. (2009). Multiscale entropy analysis of EEG for assessment of post-cardiac arrest neurological recovery under hypothermia in rats. IEEE Trans Biomed Eng, 56(4), 1023-1031.
Kay, Matthew, Choe, Eun Kyoung, Shepherd, Jesse, Greenstein, Benjamin, Watson, Nathaniel, Consolvo, Sunny, et al. (2012). Lullaby: a capture & access system for understanding the sleep environment. Paper presented at the Proceedings of the 2012 ACM Conference on Ubiquitous Computing.
Kelly, Jessica M, Strecker, Robert E, and Bianchi, Matt T. (2012). Recent Developments in Home Sleep-Monitoring Devices. ISRN neurology, 2012.
King, Andrew C, Belenky, Gregory, and Van Dongen, Hans PA. (2009). Performance impairment consequent to sleep loss: determinants of resistance and susceptibility. Current opinion in pulmonary medicine, 15(6), 559-564.
Kuo, Bor-Chen, and Landgrebe, David A. (2004). Nonparametric weighted feature extraction for classification. Geoscience and Remote Sensing, IEEE Transactions on, 42(5), 1096-1105.
Kuwahara, H., Higashi, H., Mizuki, Y., Matsunari, S., Tanaka, M., and Inanaga, K. (1988). Automatic real-time analysis of human sleep stages by an interval histogram method. Electroencephalogr Clin Neurophysiol, 70(3), 220-229.
Lai, Hui‐Ling, and Good, Marion. (2005). Music improves sleep quality in older adults. Journal of advanced nursing, 49(3), 234-244.
Liang, Sheng-Fu, Kuo, Chin-En, Hu, Yu-Han, and Cheng, Yu-Shian. (2012a). A rule-based automatic sleep staging method. Journal of Neuroscience Methods, 205(1), 169-176.
Liang, Sheng-Fu, Kuo, Chin-En, Hu, Yu-Han, Pan, Yu-Hsiang, and Wang, Yung-Hung. (2012b). Automatic Stage Scoring of Single-Channel Sleep EEG by Using Multiscale Entropy and Autoregressive Models. Instrumentation and Measurement, IEEE Transactions on, 61(6), 1649-1657.
Lin, Chin-Teng, Ko, Li-Wei, Chiou, Jin-Chern, Duann, Jeng-Ren, Huang, Ruey-Song, Liang, Sheng-Fu, et al. (2008a). Noninvasive neural prostheses using mobile and wireless EEG. Proceedings of the IEEE, 96(7), 1167-1183.
Lin, Chin-Teng, Lin, Ken-Li, Ko, Li-Wei, Liang, Sheng-Fu, Kuo, Bor-Chen, and Chung, I-Fang. (2008b). Nonparametric Single-Trial EEG Feature Extraction and Classification of Driver's Cognitive Responses. EURASIP Journal on Advances in Signal Processing, 2008(1), 849040.
Lopez, Nadia, Previc, Fred H, Fischer, Joseph, Heitz, Richard P, and Engle, Randall W. (2012). Effects of sleep deprivation on cognitive performance by United States Air Force pilots. Journal of Applied Research in Memory and Cognition, 1(1), 27-33.
Mahowald, Mark W., and Schenck, Carlos H. (2005). Insights from studying human sleep disorders. Nature, 437(7063), 1279-1285.
Maquet, Pierre. (2001). The role of sleep in learning and memory. Science, 294(5544), 1048-1052.
McGinty, Dennis, and Szymusiak, Ronald. (1990). Keeping cool: a hypothesis about the mechanisms and functions of slow-wave sleep. Trends in neurosciences, 13(12), 480-487.
Moser, D., Anderer, P., Gruber, G., Parapatics, S., Loretz, E., Boeck, M., et al. (2009). Sleep classification according to AASM and Rechtschaffen & Kales: effects on sleep scoring parameters. Sleep, 32(2), 139-149.
Norris, P. R., Anderson, S. M., Jenkins, J. M., Williams, A. E., and Morris, J. A., Jr. (2008). Heart rate multiscale entropy at three hours predicts hospital mortality in 3,154 trauma patients. Shock, 30(1), 17-22.
Ohayon, Maurice M. (2002). Epidemiology of insomnia: what we know and what we still need to learn. Sleep Medicine Reviews, 6(2), 97-111.
Olbrich, E., Achermann, P., and Meier, P. F. (2003). Dynamics of human sleep EEG. Neurocomputing, 52–54(0), 857-862.
Pardey, J., Roberts, S., and Tarassenko, L. (1996). A review of parametric modelling techniques for EEG analysis. Med Eng Phys, 18(1), 2-11.
Park, Jeong-Hyeon, Kim, Sooyong, Kim, Cheol-Hyun, Cichocki, Andrzej, and Kim, Kyungsik. (2007). MULTISCALE ENTROPY ANALYSIS OF EEG FROM PATIENTS UNDER DIFFERENT PATHOLOGICAL CONDITIONS. Fractals, 15(04), 399-404.
Philips. wake up light. from http://www.philips.co.uk/c/light-therapy/38702/cat/#2
Pincus, Steve. (1995). Approximate entropy (ApEn) as a complexity measure. Chaos: An Interdisciplinary Journal of Nonlinear Science, 5(1), 110-117.
Rechtschaffen, A., and Kales, A. (1968). A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects: US Government Printing Office, US Public Health Service.
Richman, Joshua S., and Moorman, J. Randall. (2000). Physiological time-series analysis using approximate entropy and sample entropy. American Journal of Physiology - Heart and Circulatory Physiology, 278(6), H2039-H2049.
Roenneberg, T., Kumar, C. J., and Merrow, M. (2007). The human circadian clock entrains to sun time. Curr Biol, 17(2), R44-45.
Rosenberg, R. S., and Van Hout, S. (2013). The American Academy of Sleep Medicine inter-scorer reliability program: sleep stage scoring. J Clin Sleep Med, 9(1), 81-87.
Schaltenbrand, N., Lengelle, R., Toussaint, M., Luthringer, R., Carelli, G., Jacqmin, A., et al. (1996). Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients. Sleep, 19(1), 26-35.
Schomer, Donald L, and Da Silva, Fernando Lopes. (2012). Niedermeyer's electroencephalography: basic principles, clinical applications, and related fields: LWW.
Shambroom, John R, Fábregas, Stephan E, and Johnstone, Jack. (2012). Validation of an automated wireless system to monitor sleep in healthy adults. Journal of Sleep Research, 21(2), 221-230.
Smith, Jack R., and Karacan, Ismet. (1971). EEG sleep stage scoring by an automatic hybrid system. Electroencephalography and clinical neurophysiology, 31(3), 231-237.
Smith, Jack R., Negin, M., and Nevis, A. H. (1969). Automatic Analysis of Sleep Electroencephalograms by Hybrid Computation. Systems Science and Cybernetics, IEEE Transactions on, 5(4), 278-284.
Stickgold, Robert. (2005). Sleep-dependent memory consolidation. Nature, 437(7063), 1272-1278.
Šušmáková, Kristína, and Krakovská, Anna. (2008). Discrimination ability of individual measures used in sleep stages classification. Artificial Intelligence in Medicine, 44(3), 261-277.
Takahashi, T., Cho, R. Y., Murata, T., Mizuno, T., Kikuchi, M., Mizukami, K., et al. (2009). Age-related variation in EEG complexity to photic stimulation: a multiscale entropy analysis. Clin Neurophysiol, 120(3), 476-483.
Thakor, N. V., and Tong, S. (2004). Advances in quantitative electroencephalogram analysis methods. Annu Rev Biomed Eng, 6, 453-495.
Van De Werken, M., Gimenez, M. C., De Vries, B., Beersma, D. G., Van Someren, E. J., and Gordijn, M. C. (2010). Effects of artificial dawn on sleep inertia, skin temperature, and the awakening cortisol response. J Sleep Res, 19(3), 425-435.
Van Someren, Eus JW. (2006). Mechanisms and functions of coupling between sleep and temperature rhythms. Progress in brain research, 153, 309-324.
Virkkala, J., Hasan, J., Varri, A., Himanen, S. L., and Muller, K. (2007). Automatic sleep stage classification using two-channel electro-oculography. J Neurosci Methods, 166(1), 109-115.
Walker, Matthew P, and Stickgold, Robert. (2010). Overnight alchemy: sleep-dependent memory evolution. Nature Reviews Neuroscience, 11(3), 218-218.
Wolfson, Amy R, and Carskadon, Mary A. (2003). Understanding adolescent's sleep patterns and school performance: a critical appraisal. Sleep medicine reviews, 7(6), 491-506.