睡眠呼吸中止症是一種高盛行率的睡眠障礙，患者在睡眠當中會反覆地停止呼吸，而一段呼吸停止的片段被稱為一個睡眠呼吸中止事件。睡眠呼吸中止事件可分為兩種類型：阻塞型睡眠呼吸中止症(OSA)事件、及中樞型睡眠呼吸中止(CSA)事件。阻塞型呼吸中止事件起因於患者在睡眠當中上呼吸道逐漸塌陷，導致上呼吸道阻塞使病患無法呼吸。中樞型呼吸中止症則是源於患者腦部在睡眠時對於血液中的高碳酸(CO2)的反應性下降，大腦認定血氧濃度足夠而發送減少呼吸的訊號至呼吸系統，使患者逐漸暫停呼吸。臨床醫師在判斷OSA及CSA事件時除了參考鼻腔氣流判斷事件發生外，也利用胸腔和腹腔的移動訊號判定事件乃OSA或CSA事件。睡眠呼吸中止症常導致患者因頻繁地的夜間覺醒、日間頭痛、過度疲倦嗜睡、及注意力不集中等而生活品質下降，但令人擔憂的是許多患者並未察覺自身患有睡眠呼吸中止症、且目前診斷睡眠呼吸中止症主要依據昂貴且耗費人力的睡眠多項生理檢查(Polysomnography, PSG)。因此，在此研究中提出了能夠只利用胸腔(THO)和腹腔(ABD)位移訊號偵測睡眠呼吸中止症的演算法希望能簡化睡眠呼吸中止症的檢查。演算法開發分為兩個階段。
第一階段中，先使用長度為2秒即5秒的長度分割THO和ABD訊號，接著對每個分割出的2秒和5秒的訊號片段中運用了互相關(cross-correlation)、Chirp-Z轉換(chirp z-transform)、及最大振幅(maximum amplitude)的訊號特徵萃取結合狀態機(state machine)判斷睡眠呼吸狀態建立睡眠呼吸中止症偵測演算法，對於嚴重呼吸中止症患者有100%的偵測靈敏度 (sensitivity)、對於輕微患者則有73.7%的辨識度 (specificity)，整體而演準確度(accuracy)為86.1%。此階段亦建立了對應演算法的硬體架構，提供此演算法未來整合入居家照護系統的可能性。
第二階段的演算法開發希望達到更佳的OSA和CSA事件偵測的準確度和分辨度。首先使用自適應非諧波模型(adaptive non-harmonic model)量化PSG檢查量測所得的THO和ABD訊號，並使用synchrosqueezing的方式去除THO和ABD訊號中的雜訊。接著從THO和ABD訊號中萃取出振幅比例、頻率比例、及共變異數(covariance)訊號特徵，接著利用支持向量機(support vector machine)找出最佳分類正常與睡眠中止(OSA和CSA)及區別OSA和CSA的兩個分類器(classifier)，並將這兩個分類器用在狀態機(state machine)的設計中用以判斷OSA和CSA事件的發生與否。此外提出了兩種評估事件偵測準確度的指標：指標S(index S)和指標I(index I)，並驗證所提出的演算法能夠達到平均80%以上的準確度。

Sleep apnea syndrome (SAS) is a prevalent sleep disorder well-known nowadays. People with SAS cease breathing intermittently in sleeping and an episode without breathing is called a sleep apnea event. SAS often deteriorates life quality by frequent nocturnal awakenings, morning headache, excessive daytime sleepiness, and attention deficiency. Unfortunately, the suffering people are usually unconscious of it and diagnosis nowadays relies on expensive and labor-intensive Polysomnography (PSG).
This thesis proposed a sleep apnea event detection algorithm which detects sleep apnea events based on solely thoracic (THO) and abdominal (ABD) movement signals during sleep. The algorithm is developed in two stages. In the first stage, the THO and ABD movement signals are segmented by 2-second and 5-second time window and then four features, cross-correlation, fundamental frequency, and maximum THO and ABD amplitude values, are extracted from the THO and ABD segments. Then, a state machine is designed to use the calibration signal information and the features to count the number of sleep apnea events in overnight THO and ABD movement signals. Hardware architecture is also built up in this stage. Based on the structure built in stage one, in stage two adaptive non-harmonic model is used to quantify the THO and ABD signals, more features are included, and support vector machine is introduced to construct classifiers for the state machine. To assess the event-by-event detection accuracy, two indexes, I and S, are proposed to evaluates the performance of the proposed sleep apnea event detection algorithm.

1 Introduction
1.1 Sleep Apnea Syndrome
1.2 Research Motivation
1.3 Thesis Organization

2 Medical Diagnosis of Sleep Apnea Syndrome
2.1 Polysomnography Examination
2.2 Sleep Apnea Syndrome Severity and Sleep Apnea Event Types

3 Sleep Apnea Event Detection Algorithm
3.1 Filtering
3.2 Signal Calibration
3.3 Signal Segmentation
3.4 Feature Extraction
3.4.1 Cross-correlation
3.4.2 Maximal Amplitude Detection
3.4.3 Fundamental Frequency Analysis with Chirp Z-transform
3.4.4 Feature Extraction Results
3.5 Event Detection
3.6 Detection Results
3.6.1 Parameter Optimization
3.6.2 Sleep Apnea Event Detection Result
3.6.3 Overnight Signal Analysis
3.7 Hardware Architecture Design
3.7.1 System Architecture
3.7.2 Implementation Result

4 Sleep Apnea Event Detection Algorithm Improved by Advanced Data Analysis
4.1 Adaptive non-Harmonic Model
4.2 Material and Method
4.2.1 Subject Database
4.2.2 Adaptive denoise by the synchrosqueezing transform
4.2.3 Feature Extraction
4.2.4 Support Vector Machine Approach to Classifier Training
4.2.5 State Machine Approach to Event Detection
4.2.6 Assessment of Event Detection Accuracy
4.2.7 Tap number selection
4.3 Results
4.3.1 Support Vector Machine Classification Performance
4.3.2 State Machine Detection Performance
4.3.3 Cross-Subject Performance

5 Discussion

6 Conclusion and Future Work

[1] N. S. F. of USA. How much sleep do we really need? [Online]. Available:
http://sleepfoundation.org/how-sleep-works/how-much-sleep-do-we-really-need
[2] A. A. of Sleep Medicine (AASM) Task Force, “Sleep related breathing disorders in
adults: Recommendations for syndrome definition and measurement techniques in
clinical research,” Sleep, vol. 22, pp. 667–689, Augest 1999.
[3] N. Punjabi, “The epidemiology of adult obstructive sleep apnea,” Proc Am Thorac
Soc, pp. 5:136–143, 2008.
[4] P. Carney, J. Geyer, and R. Berry, Clinical Sleep Disorders. Philadelphia: Lippincott
Williams & Wilkins, 2012.
[5] T. Young, L. Evans, L. Finn, and M. Palta, “Estimation of the clinically diagnosed
portion of sleep apnea syndrome in middle-aged men and women,” Sleep, vol. 20,
pp. 705–706, 1997.
[6] C. Iber, S. Ancoli-Isreal, A. Chesson Jr., and S. Quan, The AASM Manual for Scor-
ing of Sleep and Associated Events-Rules: Terminology and Technical Specification.
American Academy of Sleep Medicine, 2007.
[7] H. Nakano, T. Tanigawa, T. Furukawa, and S. Nishima, “Automatic detection of
sleep-disordered breathing from a single-channel airflow record,” Eur. Respir. J.,
vol. 29, no. 4, pp. 728–736, Apr 2007.
[8] J. Han, H. Shin, D. Jeong, and K. Park, “Detection of apneic events from single
channel nasal airflow using 2nd derivative method,” Comput. Meth. Prog. Bio.,
vol. 91, no. 3, pp. 199–207, Sep 2008.
[9] R. Ragette, Y. Wang, G. Weinreich, and H. Teschler, “Diagnostic performance of
single airflow channel recording (apnealink) in home diagnosis of sleep apnea,” Sleep
Breath, vol. 14, no. 2, pp. 109–114, Jun 2010.
[10] S. Rathnayake, I. Wood, U. Abeyratne, and C. Hukins, “Nonlinear features
for single-channel diagnosis of sleep-disordered breathing diseases,” IEEE Trans.
Biomed. Eng., vol. 57, no. 8, pp. 1973–1981, Aug 2010.
[11] B. Koley and D. Dey, “Real-time adaptive apnea and hypopnea event detection
methodology for portable sleep apnea monitoring devices,” IEEE Trans. Biomed.
Eng., vol. 60, no. 12, pp. 3354–3363, Dec 2013.
[12] J. Jin and E. Sanchez-Sinencio, “A home sleep apnea screening device with timedomain signal processing and autonomous scoring capability,” Biomedical Circuits and Systems, IEEE Transactions on, vol. 9, no. 1, pp. 96–104, Feb 2015.
[13] R. Thomas, J. Mietus, C. Peng, G. Gilmartin, R. Daly, A. Goldberger, and D. Gottlieb,“Differentiating obstructive from central and complex sleep apnea using an
automated electrocardiogram-based method,” Sleep, vol. 30, no. 12, pp. 1756–1769,
Dec 2007.
[14] A. Khandoker, M. Palaniswami, and C. Karmakar, “Support vector machines for automated recognition of obstructive sleep apnea syndrome from ecg recordings,”
IEEE Trans. Inf. Technol. B., vol. 13, no. 1, pp. 37–48, 2009.
[15] A. H. Khandoker, J. Gubbi, and M. Palaniswami, “Automated scoring of obstructive sleep apnea and hypopnea events using short-term electrocardiogram recordings,” IEEE Trans. Inf. Technol. B., vol. 13, no. 6, pp. 1057–67, 2009.
[16] M. Bsoul, H. Minn, and L. Tamil, “Apnea medassist: Real-time sleep apnea monitor using single-lead ecg,” IEEE Trans. Inf. Technol. B., vol. 15, no. 3, pp. 416–427, May 2011.
[17] A. Burgos, A. Goni, A. Illarramendi, and J. Bermudez, “Real-time detection of
apneas on a pda,” IEEE Trans. Inf. Technol. B., vol. 14, no. 4, pp. 995–1002, July
2010.
[18] D. Alvarez, R. Hornero, J. Marcos, and F. del Campo, “Multivariate analysis of
blood oxygen saturation recordings in obstructive sleep apnea diagnosis,” IEEE Trans. Biomed. Eng., vol. 57, no. 12, pp. 2816–2824, Dec 2010.
[19] H. Alshaer, M. Garcia, M. Radfar, G. Fernie, and T. Bradley, “Detection of upper
airway narrowing via classification of lpc coefficients: Implications for obstructive
sleep apnea diagnosis,” in Acoustics, Speech and Signal Processing (ICASSP), 2011
IEEE International Conference on, May 2011, pp. 681–684.
[20] L. Lee, J. Yu, Y. Lo, Y. Chen, D. Wang, C. Cho, Y. Ni, N. Chen, F. T.J., C. Huang,
and H. Li, “Energy types of snoring sounds in patients with obstructive sleep apnea
syndrome: a preliminary observation,” PLoS One, vol. 7, no. 12, p. e53481, 2012.
[21] B. Xie and H. Minn, “Real-time sleep apnea detection by classifier combination,”
IEEE Trans. Inf. Technol. B., vol. 16, no. 3, pp. 469–477, May 2012.
[22] D. Morillo, J. Ojeda, L. Foix, and A. Jimenez, “An accelerometer-based device for
sleep apnea screening,” IEEE Trans. Inf. Technol. B., vol. 14, no. 2, pp. 491–499,
March 2010.
[23] P. Varady, S. Bongar, and Z. Benyo, “Detection of airway obstructions and sleep apnea by analyzing the phase relation of respiration movement signals,” IEEE Trans.
Instrum. Meas., vol. 52, no. 1, pp. 2–6, Feb 2003.
[24] H. Al-Angari and A. Sahakian, “Automated recognition of obstructive sleep apnea
syndrome using support vector machine classifier,” IEEE Trans. Inf. Technol. B.,
vol. 16, no. 3, pp. 463–468, May 2012.
[25] T. Morgenthaler, V. Kagramanov, V. Hanak, and D. P.A., “Complex sleep apnea
syndrome: is it a unique clinical syndrome?” Sleep, vol. 29, no. 9, pp. 1203–9,
September 2006.
[26] W. Cochran, J. Cooley, D. Favin, H. Helms, R. Kaenel, W. Lang, G. Maling, D. Nelson, C. Rader, and P.Welch, “What is the fast fourier transform?” IEEE transaction
on Audio and Electronics, vol. 15, no. 2, Augest 1967.
[27] L. Rabiner, R. Schafer, and C. Rader, “The chirp z-transform algorithm and its
application,” IEEE transaction on Audio and Electronics, vol. 48, pp. 1249–1292,
1969.
[28] T. Lee-Chiong, Sleep Medicine: Essentials and Review. Oxford, 2008.
[29] H.-T.Wu, R. Talmon, and Y.-L. Lo, “Assess sleep stage by modern signal processing
techniques,” IEEE Transactions on Biomedical Engineering, p. in press, 2015.
[30] I. Daubechies, J. Lu, and H.-T. Wu, “Synchrosqueezed Wavelet Transforms: an
empirical mode decomposition-like tool,” Appl. Comput. Harmon. Anal., pp. 243–
261, 2011.
[31] Y.-C. Chen, M.-Y. Cheng, and H.-T. Wu, “Nonparametric and adaptive modeling
of dynamic seasonality and trend with heteroscedastic and dependent errors,” J.
Roy. Stat. Soc. B, vol. 76, pp. 651–682, 2014.
[32] H.-T. Wu, “Instantaneous frequency and wave shape functions (I),” Appl. Comput. Harmon. Anal., vol. 35, pp. 181–199, 2013.
[33] I. Daubechies, Ten Lectures on Wavelets. Philadelphia: SIAM, 1992.
[34] C. K. Chui, Y.-T. Lin, and H.-T. Wu, “Real-time dynamics acquisition from irregular
samples – with application to anesthesia evaluation,” Analysis and Applications,
accepted for publication, 2015.
[35] B. Scholkopf and A. Smola, Learning with Kernels. MIT Press, 2002.
[36] R. Rifkin and A. Klautau, “In Defense of One-Vs-All Classification,” Journal of
Machine Learning Research, vol. 5, pp. 101–141, 2004.
[37] P. Bridevaux, J. Fitting, J. Fellrath, and J. Aubert, “Inter-observer agreement on apnoea hypopnoea index using portable monitoring of respiratory parameters,” Swiss Med. Wkly., vol. 3, no. 137, pp. 602–607, 2007.
[38] S. Akselrod, S. Eliash, O. Oz, and S. Cohen, “Hemodynamic regulation in shr:
investigation by spectral analysis,” Am. J. Physiol., vol. 253, pp. H176–H183, 1987.
[39] P. Varady, T. Micsik, S. Benedek, and Z. Benyo, “A novel method for the detection
of apnea and hypopnea events in respiration signals,” IEEE Trans. Biomed. Eng.,
vol. 49, no. 9, pp. 936–942, Sept 2002.
[40] F. de Almeida, N. Ayas, R. Otsuka, H. Ueda, P. Hamilton, F. Ryan, and A. Lowe,
“Nasal pressure recordings to detect obstructive sleep apnea,” Sleep Breath, vol. 10, no. 2, pp. 62–69, Jun 2006.
[41] P. de Chazal, C. Heneghan, E. Sheridan, R. Reilly, P. Nolan, and M. O’Malley,
“Automated processing of the single-lead electrocardiogram for the detection of
obstructive sleep apnoea,” IEEE Trans. Biomed. Eng., vol. 50, no. 6, pp. 686–696,
June 2003.
[42] M. Cabrero-Canosa, M. Castro-Pereiro, M. Graa-Ramos, E. Hernndez-Pereira,
V. Moret-Bonillo, M. Martin-Egana, and H. Verea-Hernando, “An intelligent system
for the detection and interpretation of sleep apneas,” Expert Systems With
Applications, vol. 24, no. 4, pp. 335–349, 2003.
[43] C. Held, L. Causa, F. Jaillet, R. Chamorro, M. Garrido, C. Algarin, and P. Peirano,
“Automated detection of apnea/hypopnea events in healthy children polysomnograms: Preliminary results,” in Engineering in Medicine and Biology Society (EMBC), 2013 35th Annual International Conference of the IEEE, July 2013, pp. 5373–5376.
[44] P. Peppard, T. Young, M. Palta, and J. Skatrud, “Prospective study of the association between sleep-disordered breathing and hypertension,” N. Engl. J. Med., vol. 342, pp. 3378–3384, 2000.
[45] G. Hamilton, P. Solin, and M. Naughton, “Obstructive sleep apnea and cardiovascular disease,” Intern. Med. J., vol. 34, pp. 420–426, 2004.
[46] C. Bassetti and M. Aldrich, “Sleep apnea in acute cerebrovascular diseases: final
report on 128 patients,” Sleep, vol. 22, pp. 217–223, 1999.
[47] E. Phillipson, “Sleep apnea – a major public health problem,” N. Engl. J. Med.,
vol. 328, pp. 1271–1273, 1993.
[48] H. R. Colten and B. M. Altevogt, “Functional and economic impact of sleep loss and sleep-related disorders,” in Sleep Disorders and Sleep Deprivation: An Unmet Public Health Problem, H. R. Colten and B. M. Altevogt, Eds. The National Academies
Press, 2006.
[49] F. Baudin, H.-T. Wu, A. Bordessoule, J. Beck, P. Jouvet, M. Frasch, and G. Emeriaud,“Impact of ventilatory modes on the breathing variability in mechanically
ventilated infants’,” Frontiers in Pediatrics, section Neonatology, p. accepted for publication, 2014.
[50] M. Kowalski, A. Meynard, and H.-T.Wu, “Convex Optimization approach to signals with fast varying instantaneous frequency,” ArXiv e-prints 1503.07591, 2015.
[51] G. S. Chung, B. H. Choi, K. K. Kim, Y. G. Lim, J. W. Choi, D.-U. Jeong, and
K.-S. Park, “REM sleep classification with respiration rates,” in Information Tech-
nology Applications in Biomedicine, 2007. ITAB 2007. 6th International Special Topic Conference on, 2007, pp. 194–197.
[52] G. Guerrero-Mora, P. Elvia, A. Bianchi, J. Kortelainen, M. Tenhunen, S. Himanen, M. Mendez, E. Arce-Santana, and O. Gutierrez-Navarro, “Sleep-wake detection based on respiratory signal acquired through a pressure bed sensor,” in Engineering in Medicine and Biology Society (EMBC), 2012 Annual International Conference of the IEEE, 2012, pp. 3452–3455.
[53] J. Sloboda and M. Das, “A simple sleep stage identification technique for incorporation in inexpensive electronic sleep screening devices,” in Aerospace and Electronics Conference (NAECON), Proceedings of the 2011 IEEE National, 2011, pp. 21–24.