請用此 Handle URI 來引用此文件：
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89877完整後設資料紀錄
| DC 欄位 | 值 | 語言 |
|---|---|---|
| dc.contributor.advisor | 林永松 | zh_TW |
| dc.contributor.advisor | Frank Yeong-Sung Lin | en |
| dc.contributor.author | 呂文楷 | zh_TW |
| dc.contributor.author | Jonathan Lu | en |
| dc.date.accessioned | 2023-09-22T16:30:22Z | - |
| dc.date.available | 2023-11-09 | - |
| dc.date.copyright | 2023-09-22 | - |
| dc.date.issued | 2023 | - |
| dc.date.submitted | 2023-08-09 | - |
| dc.identifier.citation | [1] G. Savarese, P. M. Becher, L. H. Lund, P. Seferovic, G. M. C. Rosano, and A. Coats, “Global burden of heart failure: A comprehensive and updated review of epidemi- ology,” Cardiovasc Research, 2022.
[2] G. Savarese and L. H. Lund, “Global public health burden of heart failure,” Cardiac Failure Review, vol. 3, no. 1, pp. 7–11, 2017. [3] F. Laricchia, “Number of connected wearable devices worldwide from 2016 to 2022,” 2022. (Accessed on Dec. 2, 2022). [4] AHA, “What is heart failure?,” May 31 2017. (Accessed on Dec. 2, 2022). [5] A. Z. e. a. Tsao CW, Aday AW, “Heart disease and stroke statistics-2022 update: A report from the american heart association,” Circulation, vol. 145, no. 8, pp. e153– e639, 2022. [6] N. Y. H. Association, “Nomenclature and criteria for diagnosis of diseases of the heart and blood vessels,” Journal of the American Medical Association, vol. 153, no. 9, p. 891, 1953. [7] R. Zhang, S. Ma, L. Shanahan, J. Munroe, S. Horn, and S. Speedie, “Discovering and identifying new york heart association classification from electronic health records,” BMC Med Inform Decis Mak, vol. 18, no. Suppl 2, p. 48, 2018. [8] D. Zhang, W. Wang, and F. Li, “Association between resting heart rate and coro- nary artery disease, stroke, sudden death and noncardiovascular diseases: a meta- analysis,” CMAJ, vol. 188, no. 15, pp. E384–E392, 2016. [9] K. Fox, I. Ford, P. G. Steg, M. Tendera, M. Robertson, R. Ferrari, and B. investiga- tors, “Heart rate as a prognostic risk factor in patients with coronary artery disease and left-ventricular systolic dysfunction (beautiful): a subgroup analysis of a ran- domised controlled trial,” Lancet, vol. 372, no. 9641, pp. 817–21, 2008. [10] N. Sydo, T. Sydo, K. A. Gonzalez Carta, N. Hussain, S. Farooq, J. G. Murphy, B. Merkely, F. Lopez-Jimenez, and T. G. Allison, “Prognostic performance of heart rate recovery on an exercise test in a primary prevention population,” J Am Heart Assoc, vol. 7, no. 7, 2018. [11] N. Singh, K. J. Moneghetti, J. W. Christle, D. Hadley, V. Froelicher, and D. Plews, “Heart rate variability: An old metric with new meaning in the era of using mhealth technologies for health and exercise training guidance. part two: Prognosis and train- ing,” Arrhythm Electrophysiol Rev, vol. 7, no. 4, pp. 247–255, 2018. [12] K. Bayoumy, M. Gaber, A. Elshafeey, O. Mhaimeed, E. H. Dineen, F. A. Marvel, S. S. Martin, E. D. Muse, M. P. Turakhia, K. G. Tarakji, and M. B. Elshazly, “Smart wearable devices in cardiovascular care: where we are and how to move forward,” Nat Rev Cardiol, vol. 18, no. 8, pp. 581–599, 2021. [13] S. Chatterjee, R. S. Thakur, R. N. Yadav, L. Gupta, and D. K. Raghuvanshi, “Review of noise removal techniques in ecg signals,” Iet Signal Processing, vol. 14, no. 9, pp. 569–590, 2020. [14] W. Li, “Wavelets for electrocardiogram: Overview and taxonomy,” IEEE Access, vol. 7, pp. 25627–25649, 2019. [15] P. Gouda, P. Brown, B. H. Rowe, F. A. McAlister, and J. A. Ezekowitz, “Insights into the importance of the electrocardiogram in patients with acute heart failure,” Eur J Heart Fail, vol. 18, no. 8, pp. 1032–1040, 2016. [16] M. A. Cobos Gil, “Standard and precordial leads obtained with an apple watch,” Ann Intern Med, vol. 172, no. 6, pp. 436–437, 2020. [17] L. Dagher, H. Shi, Y. Zhao, and N. F. Marrouche, “Wearables in cardiology: Here to stay,” Heart Rhythm, vol. 17, no. 5 Pt B, pp. 889–895, 2020. [18] P. A. Kyriacou, “Introduction to photoplethysmography photoplethysmography,” in Photoplethysmography (J. A. Panicos A. Kyriacou, ed.), book chapter 1, pp. 1–16, Elsevier, 2022. [19] M. Elgendi, “On the analysis of fingertip photoplethysmogram signals,” Curr Car- diol Rev, vol. 8, no. 1, pp. 14–25, 2012. [20] M. AlMahamdy and H. B. Riley, “Performance study of different denoising methods for ecg signals,” Procedia Computer Science, vol. 37, pp. 325–332, 2014. [21] B. Mishra and N. S. Nirala, “A survey on denoising techniques of ppg signal,” pp. 1– 8, 2020. [22] H.-T. Chiang, Y.-Y. Hsieh, S.-W. Fu, K.-H. Hung, Y. Tsao, and S.-Y. Chien, “Noise reduction in ecg signals using fully convolutional denoising autoencoders,” IEEE Access, vol. 7, pp. 60806–60813, 2019. [23] G. Han, B. Lin, and Z. Xu, “Electrocardiogram signal denoising based on empirical mode decomposition technique: an overview,” Journal of Instrumentation, vol. 12, no. 3, p. P03010, 2017. [24] E. M.-M. et al., “Photoplethysmography signal processing and syntheses,” in Pho- toplethysmography (J. A. Panicos A. Kyriacou, ed.), book chapter 4, pp. 69–146, Elsevier, 2022. [25] G. Georgieva-Tsaneva, E. Gospodinova, and K. Cheshmedzhiev, “Cardiodiagnostics based on photoplethysmographic signals,” Diagnostics (Basel), vol. 12, no. 2, 2022. [26] E. Mejia-Mejia, K. Budidha, T. Y. Abay, J. M. May, and P. A. Kyriacou, “Heart rate variability (hrv) and pulse rate variability (prv) for the assessment of autonomic responses,” Front Physiol, vol. 11, p. 779, 2020. [27] E. Mejia-Mejia, J. M. May, M. Elgendi, and P. A. Kyriacou, “Differential effects of the blood pressure state on pulse rate variability and heart rate variability in critically ill patients,” NPJ Digit Med, vol. 4, no. 1, p. 82, 2021. [28] S. R. Stahlschmidt, B. Ulfenborg, and J. Synnergren, “Multimodal deep learning for biomedical data fusion: a review,” Brief Bioinform, vol. 23, no. 2, 2022. [29] Y. Cheng, F. Wang, P. Zhang, and J. Hu, Risk Prediction with Electronic Health Records: A Deep Learning Approach, pp. 432–440. 2016. [30] A. Sargolzaei, K. Faez, and S. Sargolzaei, “A new robust wavelet based algorithm for baseline wandering cancellation in ecg signals,” in 2009 IEEE International Con- ference on Signal and Image Processing Applications, pp. 33–38, 2009. [31] G. Lee, R. Gommers, F. Waselewski, K. Wohlfahrt, and A. O’Leary, “Pywavelets: A python package for wavelet analysis,” Journal of Open Source Software, vol. 4, no. 36, 2019. [32] J. Nunez, X. Otazu, O. Fors, A. Prades, V. Pala, and R. Arbiol, “Multiresolution- based image fusion with additive wavelet decomposition,” IEEE Transactions on Geoscience and Remote Sensing, vol. 37, no. 3, pp. 1204–1211, 1999. [33] P. van Gent, H. Farah, N. van Nes, and B. van Arem, “Heartpy: A novel heart rate algorithm for the analysis of noisy signals,” Transportation Research Part F: Traffic Psychology and Behaviour, vol. 66, pp. 368–378, 2019. [34] S. A. Dyer and J. S. Dyer, “Cubic-spline interpolation. 1,” IEEE Instrumentation Measurement Magazine, vol. 4, no. 1, pp. 44–46, 2001. [35] S. Hanyu and C. Xiaohui, “Motion artifact detection and reduction in ppg signals based on statistics analysis,” in 2017 29th Chinese Control And Decision Conference (CCDC), pp. 3114–3119, May 2017. [36] S. Heo, S. Kwon, and J. Lee, “Stress detection with single ppg sensor by orchestrating multiple denoising and peak-detecting methods,” IEEE Access, vol. 9, pp. 47777– 47785, 2021. [37] Evolutionary Algorithms for Solving Multi-Objective Problems. Genetic and Evolu- tionary Computation Series, 2007. [38] P. W. Kamen, H. Krum, and A. M. Tonkin, “Poincare plot of heart rate variability allows quantitative display of parasympathetic nervous activity in humans,” Clin Sci (Lond), vol. 91, no. 2, pp. 201–8, 1996. [39] R. A. Hoshi, C. M. Pastre, L. C. Vanderlei, and M. F. Godoy, “Poincare plot in- dexes of heart rate variability: relationships with other nonlinear variables,” Auton Neurosci, vol. 177, no. 2, pp. 271–4, 2013. [40] O. Faust and M. G. Bairy, “Nonlinear analysis of physiological signals: A review,” Journal of Mechanics in Medicine and Biology, vol. 12, no. 04, 2012. [41] W. Karlen, S. Raman, J. M. Ansermino, and G. A. Dumont, “Multiparameter res- piratory rate estimation from the photoplethysmogram,” IEEE Trans Biomed Eng, vol. 60, no. 7, pp. 1946–53, 2013. [42] H. Liu, F. Chen, V. Hartmann, S. G. Khalid, S. Hughes, and D. Zheng, “Compari- son of different modulations of photoplethysmography in extracting respiratory rate: from a physiological perspective,” Physiol Meas, vol. 41, no. 9, p. 094001, 2020. [43] F. Pedregosa, G. Varoquaux, A. Gramfort, V. Michel, B. Thirion, O. Grisel, M. Blon- del, P. Prettenhofer, R. Weiss, V. Dubourg, J. Vanderplas, A. Passos, D. Courna- peau, M. Brucher, M. Perrot, and E. Duchesnay, “Scikit-learn: Machine learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [44] T. F. o. t. E. S. o. C. t. N. Electrophysiology, “Heart rate variability,” Circulation, vol. 93, no. 5, pp. 1043–1065, 1996. | - |
| dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/89877 | - |
| dc.description.abstract | 心臟衰竭是由於心臟輸血能力和充血能力降低所導致的主要公共衛生問題。在所有解決心臟衰竭問題的技術中，通過早期識別來預防心血管疾病是一種更成功的策略，用於降低疾病的盛行率。近年來為了應對心臟衰竭，穿戴式健康監測設備的使用有了顯著的增加。遠程監測有風險的病人是提供治療和保護他們的健康的有效方式。我們希望通過利用穿戴式設備提供的大量數據，包含 PPG 以及三軸加速度，使用數學方法來幫助心臟衰竭病患和醫生。在這項研究中，我們提供了一個集成的智能穿戴設備框架，可以提供可靠的分類結果，以通知有危險的病人。 | zh_TW |
| dc.description.abstract | Heart failure (HF) is a major public health problem caused by the heart's diminished capacity to pump and fill with blood. Among all techniques for addressing HF issues, prevention of cardiovascular disease by early identification is a more successful strategy for decreasing illness prevalence. To cope with HF, there has been a significant increase in the usage of wearable gadgets that measure health in recent years. Remote monitoring of at-risk patients is an efficient way to provide treatment and protect their health. We want to use mathematical approaches to help HF patients and clinicians by utilizing the massive amounts of data supplied by wearable devices. In this research, we offer an integrated framework for smart-wearing devices that can deliver reliable classification results to inform patients in danger. | en |
| dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2023-09-22T16:30:22Z No. of bitstreams: 0 | en |
| dc.description.provenance | Made available in DSpace on 2023-09-22T16:30:22Z (GMT). No. of bitstreams: 0 | en |
| dc.description.tableofcontents | 誌謝 i
摘要 iv Abstract v Contents vi List of Figures x List of Tables xi Denotation xiii Chapter 1 Introduction 1 1.1 Background 1 1.2 Motivation 1 1.3 Objective 2 1.4 Clinical Implication 2 1.5 Contribution 3 1.6 Thesis Organization 4 Chapter 2 Literature Review 5 2.1 Congestive Heart Failure (CHF) 5 2.2 Detection of HF 6 2.3 Signals From Smart Wearing Devices 7 2.3.1 Electrocardiogram (ECG) 8 2.3.2 Photoplethysmography (PPG) 8 2.3.3 Noises in ECG & PPG 9 2.3.3.1 Miscellaneous Noises 11 2.3.4 Signal Denoising Methods 11 2.4 Signal Related Physiological Features 12 2.5 Machine Learning (ML) and Deep Learning (DL) 13 2.6 Data Fusion 14 Chapter 3 Proposed Methods 16 3.1 Problem Formulation 16 3.2 Framework Overview 16 3.3 Signal Denoising 17 3.3.1 Noise Filtering 21 3.3.2 Signal Calibration 23 3.3.3 Noise Reduction 24 3.3.4 Segment Evaluation Criteria 26 3.3.5 Denoise Process Evaluation 28 3.4 Denoising Algorithm Selection and Permutation 30 3.5 Feature Engineering 31 3.6 Classification Model 34 3.6.1 Tree-Based Model - XGBoost 34 3.6.2 Utilizing Deep Neural Networks 36 3.6.2.1 Convolutional Neural Networks (CNN) 36 3.6.2.2 Recurrent Neural Networks (RNN) 37 3.6.2.3 Training Deep Neural Network Models 38 3.6.3 Multi-Model Deep Learning 39 3.7 Evaluation Metrics 41 3.7.1 Accuracy 41 3.7.2 Specificity, Precision, and Recall 42 3.7.3 F1 Score 42 3.7.4 Area Under the Curve (AUC) 43 3.7.5 Geometric Mean (GM) 43 3.7.6 Matthews Correlation Coefficient (MCC) 43 3.8 Evaluation Strategy 44 3.8.1 Model Implementation 45 Chapter 4 Experiment Materials 47 4.1 Private Dataset 47 4.2 Preprocessing 50 Chapter 5 Experiments and Results 52 5.1 Denoise Experiment 52 5.2 Segment Classification Experiment 56 5.2.1 Baseline 56 5.2.2 Discrete Data Classification 58 5.2.3 Continuous Data Classification 60 5.2.4 Fusion Data Classification 62 5.3 Additional Experiments 65 5.3.1 Proximity of Event Occurrence 65 5.3.2 Variation of Event and NYHA Measurement Times 67 5.3.3 Comparison of Different Seq2Seq Models 68 5.4 Model Explanation 69 5.4.1 Numerical Ablation Study 69 5.5 SHAP Value 72 5.6 Comparison with previous work 73 5.7 Training and Execution Time 76 Chapter 6 Conclusions 77 6.1 Conclusions 77 6.2 Future work 78 References 80 | - |
| dc.language.iso | en | - |
| dc.subject | 深度學習 | zh_TW |
| dc.subject | 特徵工程 | zh_TW |
| dc.subject | 訊號去噪 | zh_TW |
| dc.subject | 心臟衰竭分類 | zh_TW |
| dc.subject | Heart failure classification | en |
| dc.subject | Signal denoising | en |
| dc.subject | Feature engineering | en |
| dc.subject | Deep learning | en |
| dc.title | 基於穿戴式裝置之即時鬱血性心臟衰竭預警系統 | zh_TW |
| dc.title | Real-time Congestive Heart Failure Warning System using Wearable Devices | en |
| dc.type | Thesis | - |
| dc.date.schoolyear | 111-2 | - |
| dc.description.degree | 碩士 | - |
| dc.contributor.oralexamcommittee | 呂俊賢;黃彥男;鄭浩民;廖辰中 | zh_TW |
| dc.contributor.oralexamcommittee | Chun-Hsien Lu;Yennun Huang;Hao-Min Cheng;Chen-Chung Liao | en |
| dc.subject.keyword | 心臟衰竭分類,訊號去噪,特徵工程,深度學習, | zh_TW |
| dc.subject.keyword | Heart failure classification,Signal denoising,Feature engineering,Deep learning, | en |
| dc.relation.page | 85 | - |
| dc.identifier.doi | 10.6342/NTU202303668 | - |
| dc.rights.note | 同意授權(限校園內公開) | - |
| dc.date.accepted | 2023-08-12 | - |
| dc.contributor.author-college | 管理學院 | - |
| dc.contributor.author-dept | 資訊管理學系 | - |
| dc.date.embargo-lift | 2028-08-09 | - |
| 顯示於系所單位： | 資訊管理學系 | |
文件中的檔案：
| 檔案 | 大小 | 格式 | |
|---|---|---|---|
| ntu-111-2.pdf 未授權公開取用 | 2.56 MB | Adobe PDF | 檢視/開啟 |
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。