睡眠對生活品質的影響是非常重要的，人們的睡眠時間約佔一天的三分之一。然而並非每個人都擁有良好的睡眠品質，有些人卻深受睡眠相關疾病的影響。在臨床診斷上常以PSG收錄病患整晚的睡眠生理訊號，並以此來觀察病患的睡眠品質來輔助醫師的診斷。因此睡眠判讀在臨床診斷上顯得非常重要。睡眠判讀通常是經由受過訓練的專家根據1968年發表的Rechtschaffen & Kales (R&K) 法則分成五個睡眠階段：Wake, S1, S2, SWS, REM。然而，使用人工方法判讀睡眠訊號通常非常費時。所以本研究目標主要開發出一套可靠且準確度高的自動睡眠判讀演算法。
在本論文中主要開發結合基因演算法與模糊推論之睡眠判讀系統，利用睡眠記錄器(Polysomnography, PSG) 記錄32位受測者睡眠時的腦電圖、肌動圖和眼動的訊號；並對收錄訊號進行時間和頻譜特徵分析。為減少判讀時個體間差異性的影響，分類前針對每一個特徵進行正規化前處理。我們先以基因演算法訓練出適當的隸屬函數已定義出本系統的模糊集。我們的模糊推論系統總共有8個輸入變數，9條模糊規則，判別所有30秒睡眠訊號片段所屬的睡眠階段。此外，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，將模糊推論系統判斷後的結果再做微調，以得到最後自動睡眠判讀的結果。針對16筆整晚多重睡眠生理記錄訊號判讀的結果，我們的方法與專家判讀結果有87.93%的一致性。本系統未來可與不同睡眠量測系統結合，應用於臨床與居家照護。

It is well-known that sleep is very important in our daily life. Human beings spend approximately 1/3 of the time a day to sleep. However, sleep diseases seriously affect some people’s quality of life. For the diagnosis, all night polysomnographic (PSG) recordings are usually taken from the patients. The doctor needs to realize the sleep quality and quantity of them. Therefore, sleep stages scoring is one of the most important steps in sleep diagnosis. The present sleep scoring method is usually done by expert according to Rechtschaffen & Kales rules presented in 1968. Sleep could be divided into Wake, S1, S2, SWS, REM stage. However, visual sleep scoring is a time consuming and subjective process. Therefore, the objective of the study is developed a high accuracy and reliable automatic sleep staging method.
In this paper, a genetic fuzzy inference system for sleep staging was developed. Eight input variables including temporal and spectrum analyses of the EEG, EOG, and EMG signals were extracted and normalization was applied to these variables to reduce the effect of individual variability. The fuzzy inference system used the genetic algorithm to construct optimal fuzzy sets and nine fuzzy rules was designed to classify the 30-s sleep epochs as five sleep stages. Finally, a smoothing process was applied to the scoring results for fine-tuning. The average accuracy of the proposed method applied to 16 all-night polysomnography (PSG) recordings compared with the manual scorings can reach 87.93 %. This method can integrate with various PSG systems for sleep monitoring in clinical or homecare applications

Agarwal R. and J. Gotman, "Computer-assisted sleep staging," Biomedical Engineering, IEEE Transactions on, vol. 48, pp. 1412-1423, 2001.
Altman D. G., Practical statistics for medical research: Chapman & Hall/CRC, 1991.
Berthomier C., X. Drouot, et al., "Automatic analysis of single-channel sleep EEG: validation in healthy individuals," Sleep, vol. 30, p. 1587, 2007.
Berthomier C., J. Prado, et al., "Automatic sleep EEG analysis using filter banks," Biomedical sciences instrumentation, vol. 35, p. 241, 1999.
Cohen J., "A coefficient of agreement for nominal scales," Educational and psychological measurement, 1960.
Davis L., "Handbook of genetic algorithms," 1991.
Duman F., A. Erdamar, et al., "Efficient sleep spindle detection algorithm with decision tree," Expert Systems with Applications, vol. 36, pp. 9980-9985, 2009.
Flexer A., G. Gruber, et al., "A reliable probabilistic sleep stager based on a single EEG signal," Artificial intelligence in Medicine, vol. 33, pp. 199-207, 2005.
Fogel S. M. and C. T. Smith, "Learning dependent changes in sleep spindles and Stage 2 sleep," Journal of sleep research, vol. 15, pp. 250-255, 2006.
Fraiwan L., K. Lweesy, et al., "Classification of sleep stages using multi-wavelet time frequency entropy and LDA," Methods of Information in Medicine, vol. 49, pp. 467-472, 2010.
Gais S., M. Molle, et al., "Learning-dependent increases in sleep spindle density," The Journal of neuroscience, vol. 22, p. 6830, 2002.
Gen M. and R. Cheng, Genetic algorithms and engineering design: Wiley-Interscience, 1997.
Goldberg D. E., "Genetic algorithms in search, optimization, and machine learning," 1989.
Hanaoka M., M. Kobayashi, et al., "Automatic sleep stage scoring based on waveform recognition method and decision tree learning," Systems and Computers in Japan, vol. 33, pp. 1-13, 2002.
Heiss J., C. Held, et al., "Classification of sleep stages in infants: A neuro fuzzy approach," Engineering in Medicine and Biology Magazine, IEEE, vol. 21, pp. 147-151, 2002.
Holland J. H., "Adaptation in natural and artificial systems," 1975.
Holland J. H., "Genetic algorithms and the optimal allocation of trials," SIAM Journal on Computing, vol. 2, p. 88, 1973.
Iber C., S. Ancoli-Israel, et al., "The AASM Manual for the Scoring of Sleep and Associated Events: Rules," Terminology and Technical Specifications, 2007.
Jansen B. and B. Dawant, "Knowledge-based approach to sleep EEG analysis-a feasibility study," Biomedical Engineering, IEEE Transactions on, vol. 36, pp. 510-518, 1989.
Kohavi R. and F. Provost, "Glossary of terms," Machine Learning, vol. 30, pp. 271-274, 1998.
Kulkarni A. D., Computer vision and fuzzy-neural systems: Prentice Hall PTR, 2001.
Landis J. R. and G. G. Koch, "The measurement of observer agreement for categorical data," Biometrics, vol. 33, p. 159, 1977.
Linkens D. A. and H. O. Nyongesa, "Learning systems in intelligent control: an appraisal of fuzzy, neural and genetic algorithm control applications," 1996, pp. 367-386.
Mahowald M. W. and C. H. Schenck, "Insights from studying human sleep disorders," NATURE-LONDON-, vol. 7063, p. 1279, 2005.
Malmivuo J. and R. Plonsey, Bioelectromagnetism: principles and applications of bioelectric and biomagnetic fields: Oxford University Press, USA, 1995.
Michalewicz Z., Genetic algorithms+ data structures: Springer, 1996.
Ohayon M. M., "Epidemiology of insomnia: what we know and what we still need to learn," Sleep Medicine Reviews, vol. 6, pp. 97-111, 2002.
Park H., K. S. Park, et al., "Hybrid neural-network and rule-based expert system for automatic sleep stage scoring," 2000, pp. 1316-1319 vol. 2.
PETERS K. R., L. Ray, et al., "Changes in the density of stage 2 sleep spindles following motor learning in young and older adults," Journal of sleep research, vol. 17, pp. 23-33, 2008.
Piryatinska A., G. Terdik, et al., "Automated detection of neonate EEG sleep stages," Computer methods and programs in biomedicine, vol. 95, pp. 31-46, 2009.
Principe J. C., S. K. Gala, et al., "Sleep staging automaton based on the theory of evidence," Biomedical Engineering, IEEE Transactions on, vol. 36, pp. 503-509, 1989.
Rechtschaffen A., A. Kales, et al., A manual of standardized terminology, techniques and scoring system for sleep stages of human subjects: US Dept. of Health, Education, and Welfare Bethesda, Md., 1968.
Schabus M., K. Hodlmoser, et al., "Sleep spindle related activity in the human EEG and its relation to general cognitive and learning abilities," European Journal of Neuroscience, vol. 23, pp. 1738-1746, 2006.
Schaltenbrand N., R. Lengelle, et al., "Sleep stage scoring using the neural network model: comparison between visual and automatic analysis in normal subjects and patients," Sleep, vol. 19, p. 26, 1996.
Schulz H., "Rethinking sleep analysis: comment on the AASM manual for the scoring of sleep and associated events," Journal of clinical sleep medicine: JCSM: official publication of the American Academy of Sleep Medicine, vol. 4, p. 99, 2008.
Smith J., M. Negin, et al., "Automatic analysis of sleep electroencephalograms by hybrid computation," Systems Science and Cybernetics, IEEE Transactions on, vol. 5, pp. 278-284, 1969.
Staniforth A., W. Kinnear, et al., "Effect of oxygen on sleep quality, cognitive function and sympathetic activity in patients with chronic heart failure and Cheyne¡VStokes respiration," European heart journal, vol. 19, p. 922, 1998.
Steriade M., "Corticothalamic resonance, states of vigilance and mentation," Neuroscience, vol. 101, pp. 243-276, 2000.
Steriade M., D. A. McCormick, et al., "Thalamocortical oscillations in the sleeping and aroused brain," Science, vol. 262, p. 679, 1993.
Sywerda G., "Uniform crossover in genetic algorithms," 1989, pp. 2-9.
Thierens D. and D. Goldberg, "Convergence models of genetic algorithm selection schemes," Parallel Problem Solving from Nature¡XPPSN III, pp. 119-129, 1994.
Tian J. and J. Liu, "Automated Sleep Staging by a Hybrid System Comprising Neural Network and Fuzzy Rule-based Reasoning," 2005, pp. 4115-4118.
Virkkala J., J. Hasan, et al., "Automatic sleep stage classification using two-channel electro-oculography," Journal of neuroscience methods, vol. 166, pp. 109-115, 2007.
Wetzel A., "Evaluation of the effectiveness of genetic algorithms in combinatorial optimization," 1983.
Zadeh L. A., "Fuzzy sets*," Information and control, vol. 8, pp. 338-353, 1965.