請用此 Handle URI 來引用此文件:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/91780
完整後設資料紀錄
DC 欄位 | 值 | 語言 |
---|---|---|
dc.contributor.advisor | 蘇國棟 | zh_TW |
dc.contributor.advisor | Guo-Dung Su | en |
dc.contributor.author | 林晉霆 | zh_TW |
dc.contributor.author | Jin-Ting Lin | en |
dc.date.accessioned | 2024-02-22T16:41:44Z | - |
dc.date.available | 2024-02-23 | - |
dc.date.copyright | 2024-02-22 | - |
dc.date.issued | 2023 | - |
dc.date.submitted | 2024-02-05 | - |
dc.identifier.citation | [1] "IDF Diabetes Atlas, 10th edition," International Diabetes Federation, 2021. [Online]. Available: https://diabetesatlas.org/atlas/tenth-edition/, Accessed on September 8, 2023.
[2] "國民營養健康狀況變遷調查成果報告2017-2020年," 衛生福利部國民健康署, 2022.[Online].Available: https://www.hpa.gov.tw/EngPages/Detail.aspx?nodeid=3999&pid=15562, Accessed on September 8, 2023. [3] R. H. Chung, S. Y. Chuang, Y. E. Chen, G. H. Li, C. H. Hsieh, H. Y. Chiou, and C. A. Hsiung, "Prevalence and predictive modeling of undiagnosed diabetes and impaired fasting glucose in Taiwan: a Taiwan Biobank study," BMJ Open Diabetes Research & Care, vol. 11, no. 3, e003423, 2023. [4] M. D. Brundage, D. Davies, and W. J. Mackillop, "Prognostic factors in non-small cell lung cancer: a decade of progress," Chest, vol. 122, no. 3, pp. 1037–1057, 2002. [5] W. Villena Gonzales, A. T. Mobashsher, and A. Abbosh, "The Progress of Glucose Monitoring—A Review of Invasive to Minimally and Non-Invasive Techniques, Devices and Sensors," Sensors, vol. 19, no. 4, p. 800, 2019. [6] L. Silva, and N. Patel, "How Much Does A Continuous Glucose Monitor Cost?" Forbes Health, [Online]. Available: https://www.forbes.com/health/conditions/diabetes/continuous-glucose-monitor-cost/. Accessed on September 8. [7] T. Tamura, Y. Maeda, M. Sekine, and M. Yoshida, "Wearable Photoplethysmographic Sensors—Past and Present," Electronics, vol. 3, no. 2, pp. 282-302, 2014. [8] J. Park, H. S. Seok, S.-S. Kim, and H. Shin, "Photoplethysmogram Analysis and Applications: An Integrative Review," Frontiers in Physiology, vol. 12, 2022. [9] L. Antonelli, W. Ohley, and R. Khamlach, "Dicrotic notch detection using wavelet transform analysis," Proceedings of 16th Annual International Conference of the IEEE Engineering in Medicine and Biology Society, vol. 2, pp. 1216-1217, 1994. [10] D. Biswas, N. Simões-Capela, C. Van Hoof, and N. Van Helleputte, "Heart Rate Estimation From Wrist-Worn Photoplethysmography: A Review," IEEE Sensors Journal, vol. 19, no. 16, pp. 6560-6570, 2019. [11] J. E. Sinex, "Pulse oximetry: Principles and limitations," The American Journal of Emergency Medicine, vol. 17, no. 1, pp. 59-66, 1999. [12] A. L. Samuel, "Some Studies in Machine Learning Using the Game of Checkers," IBM J. Res. Dev., vol. 44, pp. 206-227, 1967. [13] J. R. Quinlan, "Induction of decision trees," Mach Learn, vol. 1, pp. 81–106, 1986. [14] B. E. Boser, I. M. Guyon, and V. N. Vapnik, "A training algorithm for optimal margin classifiers," in Proceedings of the fifth annual workshop on Computational learning theory (COLT ''92), New York, NY, USA, 1992, pp. 144–152. [15] D. Rumelhart, G. Hinton, and R. Williams, "Learning representations by back-propagating errors," Nature, vol. 323, pp. 533–536, 1986. [16] K. Ogurtsova, L. Guariguata, N. C. Barengo, P. L. Ruiz, J. W. Sacre, S. Karuranga, H. Sun, E. J. Boyko, and D. J. Magliano, "IDF diabetes Atlas: Global estimates of undiagnosed diabetes in adults for 2021," Diabetes Research and Clinical Practice, vol. 183, p. 109118, 2022. [17] E. Susana and K. Ramli, "Review of Non-Invasive Blood Glucose Level Estimation based on Photoplethysmography and Artificial Intelligent Technology," 2021 17th International Conference on Quality in Research (QIR): International Symposium on Electrical and Computer Engineering, Depok, Indonesia, pp. 158-163, 2021. [18] N. M. H. Long and W. -Y. Chung, "Wearable Wrist Photoplethysmography for Optimal Monitoring of Vital Signs: A Unified Perspective on Pulse Waveforms," IEEE Photonics Journal, vol. 14, no. 2, pp. 1-17, April 2022. [19] A. A. Kamshilin and N. B. Margaryants, "Origin of photoplethysmographic waveform at green light," Phys. Procedia, vol. 86, pp. 72–80, 2017. [20] A. V. Moço, S. Stuijk, and G. de Haan, "Motion robust PPG-imaging through color channel mapping," Biomed. Opt. Exp., vol. 7, no. 5, pp. 1737–1754, 2016. [21] A. V. Mocco, S. Stuijk, and G. de Haan, "Skin inhomogeneity as a source of error in remote PPG-imaging," Biomed. Opt. Exp., vol. 7, no. 11, pp. 4718–4733, 2016. [22] A. V. Moco, S. Stuijk, and G. De Haan, "Ballistocardiographic artifacts in PPG imaging," IEEE Trans. Biomed. Eng., vol. 63, no. 9, pp. 1804–1811, Sep. 2016. [23] C. Toh, "Understanding Sample Rate, Bit Depth, and Bit Rate," 2023. [Online]. Available: https://www.headphonesty.com/2019/07/sample-rate-bit-depth-bit-rate/. Accessed on September 9, 2023. [24] D. Fujita and A. Suzuki, "Evaluation of the Possible Use of PPG Waveform Features Measured at Low Sampling Rate," in IEEE Access, vol. 7, pp. 58361-58367, 2019. [25] E. Monte-Moreno, "Non-invasive estimate of blood glucose and blood pressure from a photoplethysmograph by means of machine learning techniques," Artificial Intelligence in Medicine, vol. 53, no. 2, pp. 127-138, 2011. [26] S. S. Gupta, T.-H. Kwon, S. Hossain, K.-D. Kim, "Towards non-invasive blood glucose measurement using machine learning: An all-purpose PPG system design," Biomedical Signal Processing and Control, vol. 68, 2021, pp. 102706, ISSN 1746-8094. [27] S. Habbu, M. Dale, R. Ghongade, "Estimation of blood glucose by non-invasive method using photoplethysmography," Sādhanā, vol. 44, p. 135, 2019. [28] A. Chakraborty, D. Sadhukhan, and M. Mitra, "A Robust PPG Time Plane Feature Extraction Algorithm for Health Monitoring Application," in 2018 15th IEEE India Council International Conference (INDICON), Coimbatore, India, 2018, pp. 1-6. [29] W. T. Cochran et al., "What is the fast Fourier transform?," in Proceedings of the IEEE, vol. 55, no. 10, pp. 1664-1674, Oct. 1967. [30] J. F. Kaiser, "On a simple algorithm to calculate the ''energy'' of a signal," International Conference on Acoustics, Speech, and Signal Processing, Albuquerque, NM, USA, 1990, pp. 381-384 vol.1. [31] P. Welch, "The use of fast Fourier transform for the estimation of power spectra: A method based on time averaging over short, modified periodograms," in IEEE Transactions on Audio and Electroacoustics, vol. 15, no. 2, pp. 70-73, June 1967. [32] S. Lopez and R. T. A. C. Americas, "Pulse oximeter fundamentals and design," Free scale semiconductor, 2012, p. 23. [33] L. A. Castro-Pimentel, A. d. Téllez-Anguiano, O. I. Coronado-Reyes, et al., "Three-wavelength PPG and support vector machine for non-invasive estimation of blood glucose," Opt Quant Electron, vol. 55, p. 708, 2023. [34] D. G. Jang, U. Farooq, S. H. Park, and M. Hahn, "A robust method for pulse peak determination in a digital volume pulse waveform with a wandering baseline," IEEE Transactions on Biomedical Circuits and Systems, vol. 8, no. 5, pp. 729–737, 2014. [35] M. Elgendi, "Optimal Signal Quality Index for Photoplethysmogram Signals," Bioengineering (Basel), vol. 3, no. 4, article 21, Sep. 22, 2016 [36] J. T. Lin et al., "Non-invasive SpO2 Monitoring Using Reflective PPG: A Low-Cost Calibration Method," 2023 International Conference on Consumer Electronics-Taiwan (ICCE-Taiwan), IEEE, 2023. [37] ISO 15197:2013. "In vitro diagnostic test systems — Requirements for blood-glucose monitoring systems for self-testing in managing diabetes mellitus." International Organization for Standardization, 2013. [38] Chouinard, J.-C. (2022). "Decision Trees in Machine Learning, with Examples (Python)." [Online]. Available: https://www.jcchouinard.com/decision-trees-in-machine-learning/. Accessed on September 13, 2023. [39] Breiman, L. "Random Forests." Machine Learning, vol. 45, pp. 5–32, 2001. [40] Chen, T.Q. and Guestrin, C. "XGBoost: A Scalable Tree Boosting System," 2016. [41] L. Heinemann et al., "Benefits and Limitations of MARD as a Performance Parameter for Continuous Glucose Monitoring in the Interstitial Space," Journal of Diabetes Science and Technology, vol. 14, no. 1, pp. 135–150, 2020. [42] T. S. Bailey, "Clinical Implications of Accuracy Measurements of Continuous Glucose Sensors," Diabetes Technol Ther, vol. 19, no. S2, pp. S51-S54, May 2017. [43] W. L. Clarke, D. Cox, L. A. Gonder-Frederick, W. Carter, and S. L. Pohl, "Evaluating clinical accuracy of systems for self-monitoring of blood glucose," Diabetes Care, vol. 10, no. 5, pp. 622–628, 1987. | - |
dc.identifier.uri | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/91780 | - |
dc.description.abstract | 根據國際糖尿病聯盟(IDF)的統計,全球有約5.37億人口患有糖尿病,且患病人口預估在2030年及2045年分別達到6.43億及7.83億,而台灣的糖尿病盛行率又高於全球平均,平均十人之中就有一人患病,且據估計全台已患病卻未診斷的人數約占全台人口的1%。通常從罹患糖尿病開始,各種慢性病也會隨之併發,然而糖尿病初期通常沒有明顯症狀,所以對其的預防及檢測不容忽視。血糖的量測不管是對糖尿病患者的健康監控或對未患病者的預防檢測都非常重要,然而現行的量測方法大多是採用侵入式量測或高成本的儀器,這使得對血糖的日常監控變得不方便,因此許多團隊開始研究非侵入式且低成本的血糖量測方法,隨著穿戴式裝置的發展,近年透過光體積變化描記圖(PPG)量測血糖的方法開始被廣泛研究,透過對量測光訊號並提取出相關特徵,並搭配機器學習對血糖做出預測,相關的技術日益成熟中。
本研究提出了一個可量測紅光、紅外光及綠光等三波長的反射式PPG量測系統,透過濾波、訊號切割及一個基於支持向量機(SVM)的訊號品質分類器進行訊號處理,接著從訊號中萃取出與血糖相關之特徵並訓練隨機森林及XGBoost等機器學習模型對血糖進行回歸預測,藉此實現非侵入式且低成本的血糖估算。研究中使用了來自10名受試者的訓練資料,對模型進行訓練之後,以平均絕對相對差(MARD)及Clark’s error grid對模型進行評估,根據評估的結果再優化模型參數並分析各個特徵對於血糖估計的重要性及彼此的相關性。 | zh_TW |
dc.description.abstract | According to statistics from the International Diabetes Federation (IDF), approximately 537 million people worldwide suffer from diabetes. This number is projected to rise to 643 million by 2030 and 783 million by 2045. Taiwan''s diabetes prevalence rate surpasses the global average, with an average of one in ten individuals diagnosed with the disease. It is estimated that around 1% of Taiwan''s population has undiagnosed diabetes. Once diagnosed with diabetes, patients often subsequently develop other chronic diseases. However, initial stages of diabetes usually lack overt symptoms, emphasizing the importance of its prevention and detection. Monitoring blood sugar levels is vital, both for those diagnosed with diabetes and for prevention in non-diabetic individuals. Contemporary measurement techniques often require invasive procedures or employ high-cost instruments, making routine monitoring challenging. As a result, many teams have begun researching non-invasive and cost-effective blood glucose measurement methods. With the rise of wearable technology, the utilization of Photoplethysmography (PPG) for estimating glucose levels has garnered significant attention. By analyzing the optical signals to extract relevant features and harnessing machine learning for glucose predictions, this technique is showing promising advancements.
This study introduces a reflective PPG system capable of detecting red, infrared, and green wavelengths. The system processes signals through filtering, segmentation, and a Signal Quality Index based on the Support Vector Machine (SVM). Subsequently, features related to blood sugar are extracted from these signals and used to train machine learning models like Random Forest and XGBoost for regression predictions on blood glucose levels. This aims to realize a non-invasive and cost-effective blood glucose estimation. After training models using data from ten participants, the models were evaluated based on the Mean Absolute Relative Difference (MARD) and Clark’s error grid. Based on these evaluation results, the hyperparameters were further optimized, and the importance of each feature was analyzed, along with the correlations between them. | en |
dc.description.provenance | Submitted by admin ntu (admin@lib.ntu.edu.tw) on 2024-02-22T16:41:44Z No. of bitstreams: 0 | en |
dc.description.provenance | Made available in DSpace on 2024-02-22T16:41:44Z (GMT). No. of bitstreams: 0 | en |
dc.description.tableofcontents | 摘要 i
Abstract ii 目次 iv 圖次 vii 表次 ix 第一章 緒論 1 1.1. 前言 1 1.2. 血糖量測方法 2 1.2.1. 侵入式血糖量測方法 2 1.2.2. 非侵入式血糖量測方法 3 1.2.3. 非侵入式血糖量測的挑戰 3 1.3. 光體積變化描記圖(Photoplethysmography) 4 1.3.1. PPG之原理 4 1.3.2. PPG之應用 6 1.4. 機器學習 7 1.5. 研究目的與研究內容 9 第二章 文獻探討 10 2.1. PPG的訊號特性 10 2.1.1. PPG的波型 10 2.1.2. PPG中的雜訊 11 2.1.3. 取樣頻率 12 2.2. 用於血糖估計的特徵工程 13 2.2.1. 時域特徵 13 2.2.2. 頻域特徵 15 2.2.3. 生理特徵 16 2.3. 文獻綜合比較 18 2.3.1. 對文獻的探討 18 2.3.2. 本研究的方向與架構 19 第三章 訊號處理與特徵萃取 20 3.1. PPG量測系統 20 3.1.1. 硬體設備 20 3.1.2. 系統架構 22 3.2. 訊號處理: 濾波 22 3.3. 訊號處理: 切割 24 3.3.1. Slope Sum Function方法 24 3.3.2. 切割結果 25 3.4. SQI分類器 26 3.4.1. 訓練資料的取得與特徵萃取 26 3.4.2. 模型訓練結果 28 3.5. 血糖特徵萃取 29 3.5.1. 時域特徵 29 3.5.2. 頻域特徵 30 3.5.3. 生理特徵 32 第四章 血糖回歸預測 35 4.1. 訓練資料蒐集 35 4.1.1. 量測環境 35 4.1.2. 量測步驟 36 4.1.3. 受測者資料 37 4.2. 機器學習模型 38 4.2.1. 隨機森林 39 4.2.2. XGBoost 40 4.3. 模型輸出結果 42 4.3.1. 評估模型的方法 42 4.3.2. 隨機森林的初步訓練結果 44 4.3.3. XGBoost的初步訓練結果 47 4.4. 結果討論與分析 49 4.4.1. 過擬合的討論與調整 49 4.4.2. 特徵分析及篩選 51 4.4.3. 結果討論 54 第五章 結論與未來展望 56 5.1. 結論 56 5.2. 未來展望 57 參考文獻 59 | - |
dc.language.iso | zh_TW | - |
dc.title | 基於機器學習與多波長PPG訊號之非侵入式血糖估計 | zh_TW |
dc.title | Machine Learning-Based Noninvasive Estimation of Blood Glucose Using Multi-Wavelength PPG | en |
dc.type | Thesis | - |
dc.date.schoolyear | 112-1 | - |
dc.description.degree | 碩士 | - |
dc.contributor.oralexamcommittee | 宋孔彬;于天立 | zh_TW |
dc.contributor.oralexamcommittee | Kung-Bin Sung;Tian-Li Yu | en |
dc.subject.keyword | 光體積變化描記圖,血糖,非侵入式量測,機器學習,隨機森林,XGBoost, | zh_TW |
dc.subject.keyword | Photoplethysmography,Glucose,Non-invasive,Machine Learning,Random Forest,XGBoost, | en |
dc.relation.page | 63 | - |
dc.identifier.doi | 10.6342/NTU202400475 | - |
dc.rights.note | 同意授權(限校園內公開) | - |
dc.date.accepted | 2024-02-06 | - |
dc.contributor.author-college | 電機資訊學院 | - |
dc.contributor.author-dept | 光電工程學研究所 | - |
顯示於系所單位: | 光電工程學研究所 |
文件中的檔案:
檔案 | 大小 | 格式 | |
---|---|---|---|
ntu-112-1.pdf 授權僅限NTU校內IP使用(校園外請利用VPN校外連線服務) | 5.11 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。