請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74252
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 闕志達(Tzi-Dar Chiueh) | |
dc.contributor.author | Jen-Wem Hou | en |
dc.contributor.author | 侯人文 | zh_TW |
dc.date.accessioned | 2021-06-17T08:26:24Z | - |
dc.date.available | 2022-08-20 | |
dc.date.copyright | 2019-08-20 | |
dc.date.issued | 2019 | |
dc.date.submitted | 2019-08-12 | |
dc.identifier.citation | [1] A. Rechtschaffen, and A Kales, “A manual of standardized terminology, techniques and scoring system for sleep stages of human subject.” Washington DC: US Government Printing Office, National Institute of Health Publication, 1968.
[2] Oral Surgery, Sleep Disorder & Implant studio. Available: https://chicagosleepapneasnoring.com /polysomnography/ [3] WIKIPEDIA Sleep apnea. Available: http://en.wikipedia.org/wiki/Sleep_apnea [4] R. Ruehland, D. Rochford, and J. O'Donoghue, “The new AASM criteria for scoring hypopneas: impact on the apnea hypopnea index,” Sleep, Vol.32(2), pp.150–157,Feb 2009. [5] Surgical Sleep Solutions, “Obstructive Sleep Apnea,” [Online]. Available: http://surgicalsleepsolutions.com/obstructive-sleep-apnea/ [6] Dae Y. Kang, Pamela N. DeYoung, Atul Malhotra, Robert L.Owens, and Todd P. Coleman, “A State Space and Density Estimation Framework for Sleep Staging in Obstructive Sleep Apnea” IEEE Trans Biomed Eng. 2018 June ; 65(6): 1201–1212. [7] Kun Chen, Cheng Zhang, Jing Ma, Guangfa Wang, and Jue Zhang, “Sleep staging from single-channel EEG with multi-scale feature and contextual information,” Sleep Breath. 2019 Mar 12. doi: 10.1007/s11325-019-01789-4. [8] Stanislas Chambon , Mathieu N. Galtier, Pierrick J. Arnal, Gilles Wainrib, and Alexandre Gramfort, “A Deep Learning Architecture for Temporal Sleep Stage Classification Using Multivariate and Multimodal Time Series,” IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, VOL. 26, NO. 4, APRIL 2018 [9] Hao Dong, Akara Supratak, Wei Pan, Chao Wu, Paul M. Matthews, and Yike Guo, “Mixed Neural Network Approach for Temporal Sleep Stage Classification,” IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, VOL. 26, NO. 2, FEBRUARY 2018 [10] The Sleep-EDF Database. Available: https://physionet.org/physiobank/database/sleep-edfx/ [11] J. N. Knight, “Signal Fraction Analysis and Artifact Removal in EEG,” THESIS for the Degree of Master of Science Colorado State University. [12] C. Levkov, G. Mihov, and R. Ivanov, “Removal of power-line interference from the ECG: a review of subtraction procedure,” BioMedical Engineering OnLine, Vol.4, 4:50, August 2005. [13] B. Mozaffary, and M.A.Tinati, “ECG Baseline Wander Elimination using Wavelet Packets,” World Academy of Science Engineering and Technology, vol. 3, pp. 14–16, August 2005. [14] S.-H. Liu, “Motion artifact reduction in electrocardiogram using adaptive filter,” Medical and Biological Engineering, vol. 31, pp. 64–72, November 2011. [15] M. Kaur, B. Singh, and Seema, “Comparisons of Different Approaches for Removal of baseline wander from ECG signal,” in Proc. of IEEE Conf. on International Conference and Workshop on Emerging Trend (ICWET), Mumbai, Maharashtra, India, February 2011, pp. 30-34. [16] K.-M. Chang, “Arrhythmia ECG noise reduction by ensemble empirical mode decomposition,” Sensors, vol. 10, pp. 6063–6080, April 2010. [17] N. E. Huang, Z. Shen, S. R. Long, et al., “The empirical mode decomposition method and the Hilbert spectrum for non-stationary time series analysis,” in Proc. of Roy. Soc. Conf. on Proceedings A, London, March 1998, pp. 903–995. [18] N. E. Huang, and S. S. P. Shen, Hilbert–Huang Transform and Its Applications. Singapore: World Scientific, Interdisciplinary Mathematical Sciences, 2005. [19] Time-Frequency Analysis and Wavelet Transform Available: http://djj.ee.ntu.edu.tw/TFW.htm [20] Z. Wu, and N. E. Huang, “Ensemble empirical mode decomposition: A noise-assisted data analysis method,” Advanced Adaptive Data Analysis, vol. 1, pp. 1–41, January 2009. [21] I. Conrad, A.-I. Sonia, L. Andrew, et al., “The AASM Manual for the Scoring of Sleep and Associated Events: Rules, Terminology and Technical Specifications,” Westchester: American Academy of Sleep Medicine, 2007. [22] kes on a plane, “Pwasa Problems,” [Online]. Available: http://akesonaplane.blogspot.tw/2012/08/pwasa-problems.html [23] HEAL YOURSELF AT HOME,” Different Stages of Sleep,” [Online]. Available: http://healyourselfathome.com/ [24] Akes on a plane, “Pwasa Problems,” [Online]. Available: http://akesonaplane.blogspot.tw/2012/08/pwasa-problems.html [25] T.-B. Kuo , C.-Y. Chen, and Y.-C. Hsu, “Performance of the frequency domain indices with respect to sleep staging,” Elsevier Clinical Neurophysiology, Vol. 123, No. 7, July 2012. [26] Petrosian. A, “Kolmogorov complexity of finite sequences and recognition of different preictal EEG patterns,” In Proceedings of the Eighth IEEE Symposium on Computer-Based Medical Systems (pp. 212–217). doi: 10.1109/CBMS.1995.465426. [27] Accardo, A., Affinito, M., Carrozzi, M., and Bouquet, F., “Use of the fractal dimen- sion for the analysis of electroencephalographic time series,” Biological Cybernet- ics, 77 , 339–350. doi: 10.10 07/s0 04220 050394 . [28] Hjorth, B. (1970). “EEG analysis based on time domain properties,” Electroencephalog- raphy and Clinical Neurophysiology, 29 (3), 306–310. doi: 10.1016/0013-4694(70) 90143-4 . [29] M. Costa, A. L. Goldberger, and C.-K. Peng, “Multiscale entropy analysis of biological signals,” Physical Review, Vol. E, No. 71, February 2005. [30] M. Costa, A. L. Goldberger, and C.-K. Peng, “Multiscale Entropy Analysis of Complex Physiologic Time Series,” Physical Review Lett., Vol. 89, No. 6, August 2002. [31] Pei-Lin Lee. et al. “Automatic sleep staging in patients with obstructive sleep apnea using single-channel frontal EEG” Journal of clinical sleep medicine: JCSM: official publication of the American Academy of Sleep Medicine · May 2019 [32] WIKIPEDIA K-means clustering. Available: http://en.wikipedia.org/wiki/K-means_clustering [33] I. Hubara, M. Courbariaux, D. Soudry, R. El-Yaniv, and Y. Bengio, “Quantized neural networks: training neural networks with low precision weights and activation,” ArXiv:1609.07061v1 [cs.NE], 2016. [34] Batch gradient descent. https://www.coursera.org/learn/machine-learning/lecture/9zJUs/mini-batch-gradient-descent [35] Stochastic gradient descent. http://ufldl.stanford.edu/tutorial/supervised/OptimizationStochasticGradient Descent/ [36] Geoffrey Hinton, “A Practical Guide to Training Restricted Boltzmann Machines,” Lecture Notes in Computer Science, Vol. 7700, pp. 599-619, August 2010. [37] Y. Yuan and M.J. Shaw, “Induction of fuzzy decision trees,” Fuzzy Sets and Systems 69 (1995), pp. 125–139. [38] Y. LeCun, Y. Bengio, and G. Hinton, “Deep learning,” Nature, vol. 521, pp. 436–444, May 2015. [39] Y. LeCun, L. Bottou, Y. Bengio, and P. Haffner. “Gradient-based learning applied to document recognition,” in Proc. of the IEEE, vol. 86, no.11, pp. 2278-2324, November 1998. [40] Y. Yuan and M.J. Shaw, “Induction of fuzzy decision trees,” Fuzzy Sets and Systems 69 (1995), pp. 125–139. [41] Zhifei Zhang. “Derivation of Backpropagation in Convolutional Neural Network (CNN)” October 18, 2016 [42] WIKIPEDIA Markov chain. Available: http://en.wikipedia.org/wiki/Markov_chain [43] S. P. Meyn, and R.L. Tweedie, Markov Chains and Stochastic Stability, London, Springer-Verlag, 1993. [44] Kingma, D.P. and Welling, M.,“Auto-Encoding Variational Bayes,” ArXiv e-prints, 2013 arxiv.org/abs/1312.6114 [45] WIKIPEDIA Sensitivity and specificity. https://en.wikipedia.org/wiki/Sensitivity_and_specificity [46] WIKIPEDIA Cohen's kappa https://en.wikipedia.org/wiki/Cohen%27s_kappa [47] Sim J, and Wright CC, “The kappa statistic in reliability studies: use, interpretation, and sample size requirements,” Phys Ther. 2005;85:257–268. [48] Lucey, B. P. et al. “Comparison of a single-channel EEG sleep study to polysomnography,” J Sleep Res 25, 625-635, doi:10.1111/jsr.12417 (2016). [49] Djordje Popovic, Michael Khoo, and Philip Westbrook, “Automatic scoring of sleep stages and cortical arousals using two electrodes on the forehead: validation in healthy adults,” J Sleep Res. 2014 April ; 23(2): 211–221. doi:10.1111/jsr.12105 [50] Daniel J. Levendowski, Luigi Ferini- Strambi and Charlene Gamaldo, “the Accuracy, Night-to-Night Variability, and Stability of Frontopolar Sleep Electroencephalography Biomarkers,” J Clin Sleep Med. 2017;13(6):791–803. [51] Magdy Younes, Jill Raneri and Patrick Hanly, “Staging Sleep in Polysomnograms: Analysis of Inter-Scorer Variability” J Clin Sleep Med. 2016;12(6):885–894. [52] Somayeh Raiesdana, “Automated sleep staging of OSAs based on ICA preprocessing and consolidation of temporal correlations,” Australasian Physical & Engineering Sciences in Medicine (2018) 41:161–176 [53] Christoph Kalkbrenner, Rainer Brucher, Tibor Kesztyüs, Manuel Eichenlaub, Wolfgang Rottbauer, and Dominik Scharnbeck, “ Automated sleep stage classification based on tracheal body sound and actigraphy” Ger Med Sci. 2019; 17: Doc02.Published online 2019 Feb 22. doi: 10.3205/000268 [54] Akara Supratak, Hao Dong, Chao Wu, and Yike Guo, “DeepSleepNet: A Model for Automatic Sleep Stage Scoring Based on Raw Single-Channel EEG,” IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING, VOL. 25, NO. 11, NOVEMBER 2017 [55] WIKIPEDIA Cross-validation (statistics) https://en.wikipedia.org/wiki/Cross-validation_(statistics) [56] Koo TK, Li MY (June 2016). “A Guideline of Selecting and Reporting Intraclass Correlation Coefficients for Reliability Research”. Journal of Chiropractic Medicine. 15 (2): 155–63. doi:10.1016/j.jcm.2016.02.012. PMC 4913118. PMID 27330520. | |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/74252 | - |
dc.description.abstract | 對睡眠障礙者而言,可以透過全通道多導睡眠圖(PSG)來做診斷,PSG利用多種方式測量生理訊號,包括腦電圖(EEG),眼電圖(EOG),心電圖(ECG),肌電圖(EMG)和呼吸頻率,透過整夜的檢查,可以診斷各式睡眠疾病,例如阻塞型睡眠呼吸中止症(Obstructive sleep apnea),然而PSG檢查有許多問題,包括高昂的成本、評估的可變性、手動判讀相當耗時等缺點,為了讓評估標準一致,技術人員通常會遵守美國睡眠醫學會(AASM)以及Rechtschaffen和Kales(R&K)制定的判讀標準,通過這些標準對五個睡眠階段(Wake,N1,N2,N3,REM)進行分類。由於以上這些原因,準確測量睡眠階段的系統對於了解臨床研究中的睡眠是非常有價值的。
近幾年,深度神經網路(Deep Neural Network)與人工智慧研究因進步的電腦科技而再度被廣泛研究。 神經網路有數種類型,包括: 多層感知器(MLP),卷積神經網路(CNN),遞歸神經網路(RNN)等,其中卷積神經網路又被廣泛地應用在影像處理上,諸如影像辨識,物件偵測,甚至自然語言處理;到了最近,卷積神經網路深度已經可含有百層以上,能解決困難的任務,但是同時,計算上複雜度與傳統多層感知器相比也提高許多。 本論文提出一種方式,使用單通道前額的腦電訊號(F4-M1)對睡眠階段的進行自動判讀,其中還包括了相當高比例睡眠呼吸中止症的患者。透過深度神經網路對腦電訊號的特徵分成五種睡眠階段,並利用決策樹,搭配馬可夫模型的概念,即可將睡眠正確分期。 | zh_TW |
dc.description.abstract | Sleep disorders can be diagnosed by full-channel polysomnography (PSG), which utilizes multiple sensing modalities to measure biophysiological signals, including electroencephalogram (EEG), electrooculography (EOG), electrocardiography (ECG), electromyography (EMG) and respiratory rate. By taking a whole-night examination, the sleep laboratory can diagnose several kinds of sleep diseases such as obstructive sleep apnea (OSA). However, PSG has many problems, including high cost, considerable inter-rater variability and time-consuming in manual scoring. In order to maintain the evaluation criteria consistent, technicians adhere to rules delineated by American Academy of Sleep Medicine (AASM) and the Rechtschaffen and Kales (R&K). Five sleep stages (Wake, N1, N2, N3, REM) are visually categorize by these rules. For all these reasons, a robust system that accurately measure sleep stages is valuable for sleep in clinical studies.
In recent years, deep neural networks and AI research have attracted much attention. There are several types of neural networks, including multilayer perceptrons (MLPs), convolution neural networks (CNNs), recurrent neural networks (RNNs). Among these architectures, convolution neural networks have been widely used in image processing tasks, including image classification, object detection, even natural language processing. Recently, it has been showed that CNNs can be built with hundreds of layers in order to solve tough tasks, at the same time require much more computing effort compare to traditional MLP. We present an algorithm to scoring sleep using a single-channel frontal EEG (F4-M1) comprising a high percentage of participants with OSA. This work adopted multiple features of EEG generated via the deep neural networks to classify five sleep stages. By using a decision tree and the Markov Model technique, our system can recognize sleep stage effectively. | en |
dc.description.provenance | Made available in DSpace on 2021-06-17T08:26:24Z (GMT). No. of bitstreams: 1 ntu-108-R05943129-1.pdf: 7249045 bytes, checksum: 1d224c7e0cfb2d4869f4c1a4043522d1 (MD5) Previous issue date: 2019 | en |
dc.description.tableofcontents | 誌謝 i
摘要 ii ABSTRACT iii 圖目錄 vii 表目錄 ix 第一章 緒論 1 1.1研究動機 1 1.2呼吸中止症描述 2 1.3論文組織 4 第二章 睡眠階段介紹 5 2.1過往自動判讀之研究結果比較 5 2.2整體系統架構 6 2.3臨床資料來源 7 2.4睡眠階段的介紹 8 2.5各個睡眠階段特性 10 2.5.1清醒期 12 2.5.2 非快速眼動期第一期 12 2.5.3 非快速眼動期第二期 13 2.5.4 非快速眼動期第三期 13 2.5.5 快速眼動期 14 第三章 睡眠階段自動判讀系統架構 15 3.1訊號前處理介紹 15 3.1.1腦電圖雜訊簡介 15 3.1.2總體型經驗模態分解法去除雜訊 16 3.1.2.1經驗模態分解法 17 3.1.2.2 總體型經驗模態分解法 23 3.1.3雜訊片段去除 27 3.1.3.1 斷線訊號去除 27 3.1.3.2 頻帶 27 3.2特徵值介紹 29 3.2.1 腦電訊號頻帶特徵 29 3.2.2 腦電訊號波型特徵 32 3.2.3 腦電訊號時間訊號分析 33 3.2.3.1霍氏參數 33 3.2.3.2分形維度特徵 34 3.2.3.2.1 Petrosian分形維度 34 3.2.3.2.2 Higuchi分形維度 35 3.2.4多尺度熵分析 36 3.2.4.1 多尺度熵介紹 37 3.2.4.2 多尺度熵對於睡眠階段的特性 38 3.2.4.3 量化多尺度熵的方法 39 3.3睡眠階段分類與判讀 41 3.3.1 K-Means分群演算法 41 3.3.1.1 K-Means的概念 41 3.3.1.2 K-Means演算法的流程 42 3.3.2類神經網路 43 3.3.2.1多層感知器 43 3.3.2.1.1多層感之器概念 43 3.3.2.1.2 多層感之器訓練及推理 46 3.3.2.2深度學習類神經網路 49 3.3.2.2.1架構及演算法 50 3.3.2.3卷積神經網路 50 3.3.2.3.1卷積神經網路概念 50 3.3.2.3.2卷積神經網路訓練及推理 53 3.3.3決策樹 56 3.3.3.1決策樹概念 56 第四章 類神經網路為基礎的決策樹設計 58 4.1 先前論文的架構和演算法 58 4.2 本論文各層決策樹設計 62 4.2.1 多層感知器為基礎之決策樹 63 4.2.2 一維卷積神經網路為基礎之決策樹 65 4.2.2.1 自編碼器與K-means分群演算法 66 4.2.2.2 一維卷積神經網路 69 4.2.3 二維卷積神經網路為基礎之決策樹 70 4.2.3.1 二維卷積神經網路 71 4.3 本論文睡眠轉換經驗設計 72 4.3.1馬可夫模型 72 4.3.2 轉移矩陣與混淆矩陣 72 4.3.3 混淆矩陣時變與非時變 74 4.3.4 本論文馬可夫模型推導 74 4.4 本論文與先前論文[31]比較 76 第五章 睡眠階段自動判讀系統之表現與臨床實驗結果 79 5.1表徵分類效能參數介紹 79 5.1.1 診斷試驗真實性指標 79 5.1.2. Cohen’s Kappa 80 5.1.3 組內相關係數 82 5.2睡眠階段自動判讀系統之實驗結果 83 5.2.1 K次交叉驗證(K-Fold Cross-Validation) 83 5.2.2 預測結果與技師判斷比較 84 5.2.3 預測結果與技師判斷組內相關係數 85 5.3本論文結果與過往研究比較 88 5.3.1過往研究的特色比較 88 5.3.2過往研究的演算法比較 90 5.3.3過往研究的正確率比較 91 第六章 結論與展望 94 參考文獻 95 | |
dc.language.iso | zh-TW | |
dc.title | 使用深度神經網路之阻塞型睡眠呼吸中止症病人之自動化睡眠分期判讀 | zh_TW |
dc.title | Automated sleep stage classification in obstructive sleep apnea patients using deep neural networks | en |
dc.type | Thesis | |
dc.date.schoolyear | 107-2 | |
dc.description.degree | 碩士 | |
dc.contributor.oralexamcommittee | 李佩玲(Pei-Lin Lee),古博文(Bo-Wen Ku),劉宇庭(Yu-Ting Liu) | |
dc.subject.keyword | 睡眠階段分期,決策樹,類神經網路,馬可夫模型, | zh_TW |
dc.subject.keyword | sleep stage recognition,decision tree,Neural Network,Markov Model, | en |
dc.relation.page | 99 | |
dc.identifier.doi | 10.6342/NTU201903265 | |
dc.rights.note | 有償授權 | |
dc.date.accepted | 2019-08-13 | |
dc.contributor.author-college | 電機資訊學院 | zh_TW |
dc.contributor.author-dept | 電子工程學研究所 | zh_TW |
顯示於系所單位: | 電子工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-108-1.pdf 目前未授權公開取用 | 7.08 MB | Adobe PDF |
系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。