臺灣博碩士論文加值系統

據2017年台灣睡眠醫學學會統計，全台約11.3%的人口擁有睡眠障礙或曾經受其所苦[37]，然而睡眠障礙的成因和睡眠品質之度量都十分複雜，以往需要多導睡眠圖(Polysomnography ,PSG) 來記錄受試者睡眠過程之電生理信號，而根據紀錄來判斷睡眠型態也需要受訓過的醫療人員來執行，PSG的多導程電極對受測者睡眠中的舒適性也有不小的影響，量測期間花費的金錢及人力成本是非常可觀的。
本研究旨在開發一種睡眠品質評估系統，其量測裝置以單導程之心電量測裝置進行數據採集。除了進行心律變異性(Heart Rate Variability, HRV)分析，此系統演算法也使用美國麻省理工學院資料庫(MIT-BIH) 之心電數據預處理後，使用決策樹和支持向量機技術進行建模，並以此模型進行睡眠狀態的判斷與解析，資料庫的測試集中此演算法的架構獲得61.75%的全局準確度和52%的解碼準確度，其性能相較其他常用模型更符合本研究需求，以此系統實驗並分析極低頻電磁場對人體睡眠狀態和HRV的影響。從模型分析的結果可以發現7.83±0.3Hz的極低頻電磁場暴露會使受試者的睡眠階段分部受到改變，其睡眠時的心律變異性參數中高頻部分功率比重提升，總和結果揭示極低頻電磁場具有改善睡眠品質的效果。

According to the 2017 Taiwan Society of Sleep Medicine, about 11.3% of people in Taiwan have sleep disorders or have suffered from it. [37] However, the causes of sleep disorders and the measurement of sleep quality are very complicated. In the past, polysomnography (PSG) was needed to record the electrophysiological signal of the tester's sleep process, and the sleep pattern according to the record also needs to be performed by the trained medical personnel. The multi-lead electrode of the PSG also has a significant influence on the comfort of the subject during sleep. The money and labor costs incurred during the period are very substantial.
The purpose of this study was to develop a sleep quality assessment system in which the measurement device performs data acquisition with a single-lead heart-powered device. In addition to heart rate variability (HRV) analysis, this system algorithm is also pre-processed using the MIT-BIH database, using decision tree and support vector machine technology. The model is used to judge and analyze the sleep state. The database test concentrates on the architecture of this algorithm to obtain 61.75% overall accuracy and 52% decoding accuracy. The system experiments and analyzes the effects of extremely low frequency electromagnetic fields on human sleep state and HRV. From the results of the model analysis, it can be found that the exposure of the very low frequency electromagnetic field of 7.83±0.3 Hz will change the sleep stage of the subject, and the power of the high frequency part will increase in the heart rhythm variability parameter during sleep. The sum result reveals the extremely low frequency electromagnetic field has the effect of improving sleep quality.

中文摘要 ..............................................I
ABSTRACT..............................................II
ACKNOWLEDGEMENT.......................................IV
CONTENTS..............................................V
LIST OF FIGURES.......................................VII
LIST OF FIGURES.......................................VII
CHAPTER 1 Introduction................................1
1-1 Background and motivation..........................1
1-1-1 Background.......................................1
1-1-2 Motivation.......................................4
1-2 Introduction of HRV................................6
1-3 Introduction of ELF-EMF............................9
1-4 Introduction of Parasympathetic Nervous System.....11
CHAPTER 2 MATERIAL AND METHOD.........................12
2-1 ECG Sampling system................................12
2-2 ECG Signal processing..............................14
2-2-1 ECG Signal resampling............................16
2-2-2 ECG Signal detrending............................17
2-2-3 ECG Signal detect R peak position................20
2-3 HRV frequency domain analysis......................21
2-4 Sleep stage classification.........................23
2-4-1 Decision tree architecture.......................24
2-4-2 Feature selection................................25
2-5 ELF EMF device design..............................26
2-5-1 Frequency parameter of signal....................27
CHAPTER 3 EXPERIMENTAL SETUP..........................29
3-1 Experiment of ELF EMF effect on sleep..............29
CHAPTER 4 EXPERIMENT RESULTS AND DISCUSSION...........32
4-1 Experiment results.................................32
4-1-1 Experiment results of the sleep stage classification.........................................32
4-1-2 Experiment results of ELF EMF effect on HRV during
sleep..................................................37
4-1-3 Long-term experiment results of ELF EMF effect on HRV during sleep.......................................40
4-2 Discussions of experiment results..................44
CHAPTER 5 CONCLUSION..................................48
REFERENCES.............................................49

[1] National Highway Traffic Safety Administration. NHTSA Drowsy Driving Research and Program Plan. (2016).

[2] Baglioni, Chiara, et al. Insomnia as a predictor of depression: a meta-analytic evaluation of longitudinal epidemiological studies. Journal of affective disorders 135.1-3 (2011): 10-19.

[3] Vozoris, Nicholas T. The relationship between insomnia symptoms and hypertension using United States population-level data. Journal of hypertension 31.4 (2013): 663-671.

[4] Tai, Shu-Yu, Wen-Fu Wang, and Yuan-Han Yang. Current status of sleep quality in Taiwan: a nationwide walk-in survey. Annals of general psychiatry 14.1 (2015): 36.

[5] 國家衛生福利部,食品藥物管理署“國人安眠藥統計使用量
https://www.mohw.gov.tw/cp-2624-19491-1.html

[6] Vaughn, Bradley V., and Peterson Giallanza. Technical review of polysomnography. Chest 134.6 (2008): 1310-1319.

[7] Kripke, Daniel F., et al. Short and long sleep and sleeping pills: is increased mortality associated?. Archives of general psychiatry 36.1 (1979): 103-116.

[8] Palmer, S. J., M. J. Rycroft, and M. Cermack. Solar and geomagnetic activity, extremely low frequency magnetic and electric fields and human health at the Earth’s surface. Surveys in Geophysics 27.5 (2006): 557-595.

[9] Camm, A. John, et al. Heart rate variability: standards of measurement, physiological interpretation and clinical use. Task Force of the European Society of Cardiology and the North American Society of Pacing and Electrophysiology. (1996): 1043-1065.


[10] Kamath, Markad V., and Ernest L. Fallen. Power spectral analysis of heart rate variability: a noninvasive signature of cardiac autonomic function. Critical reviews in biomedical engineering 21.3 (1993): 245-311.

[11] Werner, Gabriela G., et al. Cardiac vagal control and depressive symptoms: the moderating role of sleep quality. Behavioral sleep medicine 15.6 (2017): 451-465.

[12] Toscani, L., et al. Human heart rate variability and sleep stages. The Italian Journal of Neurological Sciences 17.6 (1996): 437-439.

[13] Werner, Gabriela G., et al. High cardiac vagal control is related to better subjective and objective sleep quality. Biological psychology 106 (2015): 79-85.

[14] Burton, A. R., et al. Reduced heart rate variability predicts poor sleep quality in a case–control study of chronic fatigue syndrome. Experimental brain research 204.1 (2010): 71-78.

[15] Markov, Marko S. Angiogenesis, magnetic fields and'window effects'. Cardiology 117.1 (2010): 54.

[16] Simko, M., et al. Effects of 50 Hz EMF exposure on micronucleus formation and apoptosis in transformed and nontransformed human cell lines. Bioelectromagnetics: Journal of the Bioelectromagnetics Society, The Society for Physical Regulation in Biology and Medicine, The European Bioelectromagnetics Association 19.2 (1998): 85-91.

[17] Lisi, Antonella, et al. Extremely low frequency electromagnetic field exposure promotes differentiation of pituitary corticotrope‐derived AtT20 D16V cells. Bioelectromagnetics: Journal of the Bioelectromagnetics Society, The Society for Physical Regulation in Biology and Medicine, The European Bioelectromagnetics Association 27.8 (2006): 641-651.

[18] Buckner, Carly A., et al. Inhibition of cancer cell growth by exposure to a specific time-varying electromagnetic field involves T-type calcium channels. PLoS One 10.4 (2015): e0124136.

[19] Catterall, William A. Voltage-gated calcium channels. Cold Spring Harbor perspectives in biology 3.8 (2011): a003947.
[20] Olshansky, Brian, et al. Parasympathetic nervous system and heart failure: pathophysiology and potential implications for therapy. Circulation 118.8 (2008): 863-871.
[21] McCorry, Laurie Kelly. Physiology of the autonomic nervous system. American journal of pharmaceutical education 71.4 (2007): 78.

[22] Stein, Phyllis K., and Yachuan Pu. Heart rate variability, sleep and sleep disorders. Sleep medicine reviews 16.1 (2012): 47-66.

[23] Cortes, Corinna, and Vladimir Vapnik. Support-vector networks. Machine learning 20.3 (1995): 273-297.

[24] Huang, Chengquan, L. S. Davis, and J. R. G. Townshend. An assessment of support vector machines for land cover classification. International Journal of remote sensing 23.4 (2002): 725-749.

[25] Melgani, Farid, and Lorenzo Bruzzone. Classification of hyperspectral remote sensing images with support vector machines. IEEE Transactions on geoscience and remote sensing 42.8 (2004): 1778-1790.

[26] Ćosić, Irena, et al. Human electrophysiological signal responses to ELF Schumann resonance and artificial electromagnetic fields. FME Transactions 34.2 (2006): 93-103.

[27] Zhadin, Mikhail N. Review of Russian literature on biological action of DC and low‐frequency AC magnetic fields. Bioelectromagnetics: Journal of the Bioelectromagnetics Society, The Society for Physical Regulation in Biology and Medicine, The European Bioelectromagnetics Association 22.1 (2001): 27-45.

[28] Füllekrug, Martin. Schumann resonances in magnetic field components. Journal of Atmospheric and Terrestrial Physics 57.5 (1995): 479-484.

[29] Pomeranz, Bruce, et al. Assessment of autonomic function in humans by heart rate spectral analysis. American Journal of Physiology-Heart and Circulatory Physiology 248.1 (1985): H151-H153.

[30] Malliani, Alberto, et al. Cardiovascular neural regulation explored in the frequency domain. Circulation 84.2 (1991): 482-492.


[31] Montano, Nicola, et al. Power spectrum analysis of heart rate variability to assess the changes in sympathovagal balance during graded orthostatic tilt. Circulation 90.4 (1994): 1826-1831.

[32] Fang, Su-Chang, et al. Heart rate variability and daytime functioning in insomniacs and normal sleepers: preliminary results. Journal of Psychosomatic Research 65.1 (2008): 23-30.

[33] Cvetkovic, Dean, Elif Derya Übeyli, and Irena Cosic. Wavelet transform feature extraction from human PPG, ECG, and EEG signal responses to ELF PEMF exposures: A pilot study. Digital signal processing 18.5 (2008): 861-874.

[34] Bell, Glenn B., Andrew A. Marino, and Andrew L. Chesson. Alterations in brain electrical activity caused by magnetic fields: detecting the detection process. Electroencephalography and clinical Neurophysiology 83.6 (1992): 389-397.

[35] Yuda, E., Y. Yoshida, and J. Hayano. Relationship Between Subjective Assessment of Sleep Quality and Heart Rate Variability During Sleep. 2018 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW). IEEE, 2018.

[36] Brzezinski, Amnon, et al. Effects of exogenous melatonin on sleep: a meta-analysis. Sleep medicine reviews 9.1 (2005): 41-50.

[37] 台灣睡眠醫學學會 2017 台灣常見睡眠問題盛行率的變化趨勢 http://www.tssm.org.tw/file/1494489550.pdf