隨著人工智慧迅速發展，深度學習演算法被廣泛研究，在本論文當中，使用深度學習方法於四種領域研究，分別為人類活動識別、血壓估算、新型冠狀病毒肺炎辨識與加護病房死亡率預測。
人類活動識別當中，提出一個多尺度並行卷積神經網路模型，利用不同的卷積核大小來進行特徵提取，將其特徵串接，用於辨識爾灣加州大學人類活動識別數據庫與實驗室數據庫，實驗結果準確率分別為97.49%與96.27%，10折交叉驗證準確率分別為99.56%與97.46%。
血壓估算當中，提出一種深度學習之血壓估算模型，利用雙光體積變化描記圖法訊號轉換之特徵與歐姆龍手臂型血壓計所量測之實驗室數據庫來進行訓練所提出之網路，實驗結果採用全部數據進行訓練與測試，收縮壓、舒張壓與平均動脈壓之平均絕對誤差與標準差分別為0.17±0.46毫米汞柱、0.27±0.52毫米汞柱與0.16±0.40毫米汞柱。
新型冠狀病毒肺炎辨識當中，提出一種圖像通道串接之特徵融合技術，應用於胸部X光圖像進行辨識新型冠狀病毒肺炎，當中採用三種開源之深度學習模型來進行訓練與測試，實驗結果由Xception結合特徵融合技術之準確率最佳，三分類準確率為99.74%，5折交叉驗證準確率為99.19%，二分類準確率為99.74%，5折交叉驗證準確率為99.50%。
加護病房死亡率預測當中，使用加護病房醫學訊息中心之資料庫進行研究，獲取24小時數據，從中提取21種特徵，將其轉為時間序列特徵與其6種統計特徵，作為所提出之深度學習輸入，實驗結果加護病房死亡率預測之接收者操作特徵曲線下面積為0.878，精確召回曲線下面積為0.535。

With the rapid development of artificial intelligence, deep learning algorithms are widely studied. In this paper, deep learning methods are used in four studies, namely human activity recognition, blood pressure estimation, coronavirus disease 2019 identification, and intensive care unit mortality prediction.
Human activity recognition, a multiscale parallel convolutional neural network model is proposed, which uses different kernel sizes for feature extraction and concatenated features to identify the human activity recognition database and laboratory database of the University of California, Irvine. The accuracy of the experimental results is 97.49% and 96.27%, respectively, and the accuracy of the 10-fold cross-validation is 99.56% and 97.46%, respectively.
Blood pressure estimation, a deep learning blood pressure estimation model is proposed, which uses the features converted by dual photoplethysmography signal and the laboratory database measured by omron blood pressure monitor to train the proposed network, and uses all data for training and testing. The mean absolute error and standard deviation of systolic blood pressure, diastolic blood pressure and mean arterial pressure were 0.17±0.46 mmHg, 0.27±0.52 mmHg and 0.16±0.40 mmHg, respectively.
Coronavirus disease 2019 identification, a feature fusion technology of image channel concatenation is proposed, which is applied to chest X-ray images to identify coronavirus disease 2019, and uses three open source deep learning models for training and testing. The experimental result is the best accuracy of Xception combined with feature fusion technology. The accuracy of three classifications is 99.74%, the accuracy of 5-fold cross-validation is 99.19%, the accuracy of two classifications is 99.74%, and the accuracy of 5-fold cross-validation is 99.50%.
Intensive care unit mortality prediction, using the Medical Information Mart for Intensive Care database for research, obtaining 24-hour data, and extracting 21 features from it, converting them into time series features and 6 statistical features, as the proposed deep learning input. In the experimental results, the area under the receiver operating characteristic curve of the intensive care unit mortality is 0.878, and the area under the precision recall curve is 0.535.

摘要....................i
Abstract....................ii
誌謝....................iv
目錄....................v
表目錄....................vii
圖目錄....................ix
第一章 緒論....................1
1.1 研究背景....................1
1.1.1 人類活動識別....................1
1.1.2 血壓估算....................3
1.1.3 新型冠狀病毒肺炎辨識....................5
1.1.4 加護病房死亡率預測....................7
1.2 研究動機與目的....................9
1.2.1 人類活動識別....................9
1.2.2 血壓估算....................9
1.2.3 新型冠狀病毒肺炎辨識....................10
1.2.4 加護病房死亡率預測....................10
1.3 論文架構與貢獻....................11
第二章 文獻探討....................12
2.1 數據挖掘....................12
2.2 深度學習....................12
2.2.1 卷積神經網路....................12
2.2.2 長短期記憶....................14
2.2.3 激活函數....................15
2.2.4 損失函數....................17
2.2.5 InceptionV3....................18
2.2.6 Xception....................18
2.2.7 MobileNetV2....................18
2.3 光體積變化描記圖法....................18
2.3.1 心率....................18
2.3.2 脈波傳遞時間....................19
2.3.3 脈波傳導速率....................19
2.3.4 灌流指標....................19
2.3.5 平均動脈壓....................19
2.4 限制對比度自適應直方圖均衡....................19
2.5 評估指標....................20
第三章 人類活動識別....................23
3.1數據庫....................23
3.1.1 UCI HAR數據庫....................23
3.1.2 實驗室數據庫....................24
3.2 人類活動識別演算法....................26
3.3 實驗結果....................29
3.3.1 UCI HAR數據庫....................29
3.3.2 實驗室數據庫....................30
3.3.3 相關文獻比較....................32
3.4 章節結論....................32
第四章 血壓估算....................33
4.1 實驗室數據庫....................33
4.2 血壓估算演算法....................36
4.3 實驗結果....................38
4.4 章節結論....................39
第五章 新型冠狀病毒肺炎辨識....................40
5.1 數據庫....................40
5.2 新型冠狀病毒肺炎辨識演算法....................40
5.2.1 預處理....................40
5.2.2 特徵融合....................41
5.2.3 實驗流程....................42
5.2.4 深度學習模型....................43
5.3 實驗結果....................44
5.3.1 數據集A....................44
5.3.2 數據集B....................46
5.3.3 相關文獻比較....................48
5.4 章節結論....................50
第六章 加護病房死亡率預測....................51
6.1 數據庫....................51
6.2 加護病房死亡率預測演算法....................51
6.2.1 預處理....................51
6.2.2 深度學習模型....................53
6.3 實驗結果....................54
6.4 章節結論....................57
第七章 結論....................58
參考文獻....................59
Extended Abstract....................66

[1]K. Chen, D. Zhang, L. Yao, B. Guo, Z. Yu and Y. Liu, "Deep learning for sensor-based human activity recognition: Overview challenges and opportunities", ACM Comput. Surv., vol. 54, no. 4, pp. 1-40, Jul. 2021, 10.1145/3447744.
[2]I. Bisio, A. Delfino, F. Lavagetto and A. Sciarrone, "Enabling IoT for In-Home Rehabilitation: Accelerometer Signals Classification Methods for Activity and Movement Recognition", IEEE Internet Things J., vol. 4, no. 1, pp. 135-146, Feb. 2017, 10.1109/JIOT.2016.2628938.
[3]S. Mekruksavanich and A. Jitpattanakul, "Biometric user identification based on human activity recognition using wearable sensors: An experiment using deep learning models", Electronics, vol. 10, no. 3, 2021, 10.3390/electronics10030308.
[4]J. Huang, S. Lin, N. Wang, G. Dai, Y. Xie and J. Zhou, "TSE-CNN: A Two-Stage End-to-End CNN for Human Activity Recognition", IEEE J. Biomed. Health Informat., vol. 24, no. 1, pp. 292-299, Jan. 2020, 10.1109/JBHI.2019.2909688.
[5]D. Anguita, A. Ghio, L. Oneto, X. Parra and J. L. Reyes-Ortiz, "A public domain dataset for human activity recognition using smartphones", Proc. ESANN, pp. 437-442, 2013.
[6]R. Mutegeki and D. S. Han, "A CNN-LSTM Approach to Human Activity Recognition", Proc. ICAIIC, pp. 362-366, 2020, 10.1109/ICAIIC48513.2020.9065078.
[7]F. Hernández, L. F. Suárez, J. Villamizar and M. Altuve, "Human Activity Recognition on Smartphones Using a Bidirectional LSTM Network", Proc. STSIVA, pp. 1-5, 2019, 10.1109/STSIVA.2019.8730249.
[8]M. Ullah, H. Ullah, S. D. Khan and F. A. Cheikh, "Stacked Lstm Network for Human Activity Recognition Using Smartphone Data", Proc. EUVIP, pp. 175-180, 2019, 10.1109/EUVIP47703.2019.8946180.
[9]C. Xu, D. Chai, J. He, X. Zhang and S. Duan, "InnoHAR: A Deep Neural Network for Complex Human Activity Recognition", IEEE Access, vol. 7, pp. 9893-9902, Jan. 2019, 10.1109/ACCESS.2018.2890675.
[10]K. Xia, J. Huang and H. Wang, "LSTM-CNN Architecture for Human Activity Recognition", IEEE Access, vol. 8, pp. 56855-56866, Mar. 2020, 10.1109/ACCESS.2020.2982225.
[11]X. Yang, Y. Lyu, Y. Sun and C. Zhang, "A New Residual Dense Network for Dance Action Recognition From Heterogeneous View Perception", Front. Neurorobotics, vol. 15, pp. 89, 2021, 10.3389/fnbot.2021.698779.
[12]C. -T. Yen, J. -X. Liao and Y. -K. Huang, "Human Daily Activity Recognition Performed Using Wearable Inertial Sensors Combined With Deep Learning Algorithms", IEEE Access, vol. 8, pp. 174105-174114, Sep. 2020, 10.1109/ACCESS.2020.3025938.
[13]N. Dua, S. N. Singh and V. B. Semwal, "Multi-input CNN-GRU based human activity recognition using wearable sensors", Computing, vol. 103, pp. 1461-1478, Mar. 2021, 10.1007/s00607-021-00928-8.
[14]O. Nafea, W. Abdul, G. Muhammad and M. Alsulaiman, "Sensor-Based Human Activity Recognition with Spatio-Temporal Deep Learning", Sensors, vol. 21, no. 6, pp. 2141, Mar. 2021, 10.3390/s21062141.
[15]D. Thakur and S. Biswas, "Feature fusion using deep learning for smartphone based human activity recognition", Int. J. Inf. Technol., pp. 1-10, Jun. 2021, 10.1007/s41870-021-00719-6.
[16]C. Avilés-Cruz, A. Ferreyra-Ramírez, A. Zúñiga-López and J. Villegas-Cortéz, "Coarse-Fine Convolutional Deep-Learning Strategy for Human Activity Recognition", Sensors, vol. 19, no. 7, pp. 1556, Mar. 2019, 10.3390/s19071556.
[17]A. Avolio, "The finger volume pulse and assessment of arterial properties", J. Hypertens., vol. 20, no. 12, pp. 2341-2343, Dec. 2002, 10.1097/00004872-200212000-00007.
[18]J. M. Padilla, E. J. Berjano, J. Saiz, L. Facila, P. Diaz and S. Merce, "Assessment of relationships between blood pressure, pulse wave velocity and digital volume pulse", Proc. Computers in Cardiology, pp. 893-896, 2006.
[19]J. Allen, "Photoplethysmography and its application in clinical physiological measurement", Physiol. Meas., vol. 28, no.3, pp. R1-39, Mar. 2007, 10.1088/0967-3334/28/3/R01.
[20]A. Chakraborty, D. Goswami, J. Mukhopadhyay and S. Chakrabarti, "Measurement of Arterial Blood Pressure Through Single-Site Acquisition of Photoplethysmograph Signal", IEEE Trans. Instrum. Meas., vol. 70, pp. 1-10, Jul. 2021, 10.1109/TIM.2020.3011304.
[21]X. Chen, S. Yu, Y. Zhang, F. Chu and B. Sun, "Machine Learning Method for Continuous Noninvasive Blood Pressure Detection Based on Random Forest", IEEE Access, vol. 9, pp. 34112-34118, Feb. 2021, 10.1109/ACCESS.2021.3062033.
[22]J. Liu et al., "PCA-Based Multi-Wavelength Photoplethysmography Algorithm for Cuffless Blood Pressure Measurement on Elderly Subjects", IEEE J. Biomed. Health Inform., vol. 25, no. 3, pp. 663-673, Mar. 2021, 10.1109/JBHI.2020.3004032.
[23]C. El-Hajj and P. A. Kyriacou, "Deep learning models for cuffless blood pressure monitoring from PPG signals using attention mechanism", Biomed. Signal Process. Control, vol. 65, pp. 102301, Mar. 2021, 10.1016/j.bspc.2020.102301.
[24]C. El-Hajj and P. A. Kyriacou, "Cuffless and Continuous Blood Pressure Estimation From PPG Signals Using Recurrent Neural Networks", Proc. EMBC, pp. 4269-4272, 2020, 10.1109/EMBC44109.2020.9175699.
[25]S. Kılıçkaya, A. Güner and B. Dal, "Comparison of Different Machine Learning Techniques for the Cuffless Estimation of Blood Pressure using PPG Signals", Proc. HORA, pp. 1-6, 2020, 10.1109/HORA49412.2020.9152602.
[26]R. K. Nath and H. Thapliyal, "PPG Based Continuous Blood Pressure Monitoring Framework for Smart Home Environment", Proc. WF-IoT, pp. 1-6, 2020, 10.1109/WF-IoT48130.2020.9221386.
[27]S. Baek, J. Jang, S. -H. Cho, J. M. Choi and S. Yoon, "Blood Pressure Prediction by a Smartphone Sensor using Fully Convolutional Networks", Proc. EMBC, pp. 188-191, 2020, 10.1109/EMBC44109.2020.9175902.
[28]M. Panwar, A. Gautam, D. Biswas and A. Acharyya, "PP-Net: A Deep Learning Framework for PPG-Based Blood Pressure and Heart Rate Estimation", IEEE Sens. J., vol. 20, no. 17, pp. 10000-10011, Sep. 2020, 10.1109/JSEN.2020.2990864.
[29]O. Schlesinger, N. Vigderhouse, D. Eytan and Y. Moshe, "Blood Pressure Estimation From PPG Signals Using Convolutional Neural Networks And Siamese Network", Proc. ICASSP, pp. 1135-1139, 2020, 10.1109/ICASSP40776.2020.9053446.
[30]M. Singla, P. Sistla and S. Azeemuddin, "Cuff-less Blood Pressure Measurement Using Supplementary ECG and PPG Features Extracted Through Wavelet Transformation", Proc. EMBC, pp. 4628-4631, 2019, 10.1109/EMBC.2019.8857709.
[31]A. Chatterjee, M. Mitra and S. Pal, "Cuffless Systolic Blood Pressure Estimation Using Photoplethysmography Signal", Proc. GUCON, pp. 424-427, 2019.
[32]C. Yan et al., "Novel Deep Convolutional Neural Network for Cuff-less Blood Pressure Measurement Using ECG and PPG Signals", Proc. EMBC, pp. 1917-1920, 2019, 10.1109/EMBC.2019.8857108.
[33]S. Shimazaki, H. Kawanaka, H. Ishikawa, K. Inoue and K. Oguri, "Cuffless Blood Pressure Estimation from only the Waveform of Photoplethysmography using CNN", Proc. EMBC, pp. 5042-5045, 2019, 10.1109/EMBC.2019.8856706.
[34]W. -J. Guan et al., "Clinical characteristics of coronavirus disease 2019 in China", N. Engl. J. Med., vol. 382, pp. 1708-1720, 2020, 10.1056/NEJMoa2002032.
[35]I. D. Apostolopoulos and T. A. Mpesiana, "Covid-19: automatic detection from X-ray images utilizing transfer learning with convolutional neural networks", Phys. Eng. Sci. Med., vol. 43, pp. 635-640, 2020, 10.1007/s13246-020-00865-4.
[36]M. E. H. Chowdhury et al., "Can AI Help in Screening Viral and COVID-19 Pneumonia?", IEEE Access, vol. 8, pp. 132665-132676, Jul. 2020, 10.1109/ACCESS.2020.3010287.
[37]A. Gupta, Anjum, S. Gupta and R. Katarya, "InstaCovNet-19: A deep learning classification model for the detection of COVID-19 patients using Chest X-ray", Appl. Soft Comput., vol. 99, pp. 106859, 2021, 10.1016/j.asoc.2020.106859.
[38]A. I. Khan, J. L. Shah and M. M. Bhat, "CoroNet: A deep neural network for detection and diagnosis of COVID-19 from chest x-ray images", Comput. Methods Programs Biomed., vol. 196, pp. 105581, Nov. 2020, 10.1016/j.cmpb.2020.105581.
[39]F. Ucar and D. Korkmaz, "COVIDiagnosis-Net: Deep Bayes-SqueezeNet based diagnosis of the coronavirus disease 2019 (COVID-19) from X-ray images", Med. Hypotheses, vol. 140, Jul. 2020, 10.1016/j.mehy.2020.109761.
[40]R. Bhadra and S. Kar, "Covid Detection from CXR Scans using Deep Multi-layered CNN", Proc. IBSSC, pp. 214-218, 2020, 10.1109/IBSSC51096.2020.9332210.
[41]T. Ozturk, M. Talo, E. A. Yildirim, U. B. Baloglu, O. Yildirim and U. Rajendra Acharya, "Automated detection of COVID-19 cases using deep neural networks with X-ray images", Comput. Biol. Med., vol. 121, pp. 103792, Jun. 2020, 10.1016/j.compbiomed.2020.103792.
[42]M. Toğaçar, B. Ergen and Z. Cömert, "COVID-19 detection using deep learning models to exploit Social Mimic Optimization and structured chest X-ray images using fuzzy color and stacking approaches", Comput. Biol. Med., vol. 121, pp. 103805, Jun. 2020, 10.1016/j.compbiomed.2020.103805.
[43]S. Minaee, R. Kafieh, M. Sonka, S. Yazdani and G. J. Soufi, "Deep-COVID: Predicting COVID-19 from chest X-ray images using deep transfer learning", Med. Image Anal., vol. 65, pp. 101794, Jul. 2020, 10.1016/j.media.2020.101794.
[44]E. F. Ohata et al., "Automatic detection of COVID-19 infection using chest X-ray images through transfer learning", IEEE/CAA J. Autom. Sin., vol. 8, no. 1, pp. 239-248, Jan. 2021, 10.1109/JAS.2020.1003393.
[45]B. Bardak and M. Tan, "Improving clinical outcome predictions using convolution over medical entities with multimodal learning", Artif. Intell. Med., vol. 117, pp. 102112, Jul. 2021, 10.1016/j.artmed.2021.102112.
[46]G. Harerimana, J. W. Kim and B. Jang, "A deep attention model to forecast the Length Of Stay and the in-hospital mortality right on admission from ICD codes and demographic data", J. Biomed. Inform., vol. 118, pp. 103778, 2021, 10.1016/j.jbi.2021.103778.
[47]H. Harutyunyan, H. Khachatrian, D. C. Kale, G. V. Steeg and A. Galstyan, "Multitask Learning and Benchmarking with Clinical Time Series Data", Sci. Data, vol. 6, Jun. 2019, 10.1038/s41597-019-0103-9.
[48]A. R. Nallabasannagari, M. Reddiboina, R. Seltzer, T. Zeffiro, A. Sharma and M. Bhandari, "All Data Inclusive, Deep Learning Models to Predict Critical Events in the Medical Information Mart for Intensive Care III Database (MIMIC III)", 2020. [Online]. Available: arXiv:2009.01366.
[49]S. Purushotham, C. Meng, Z. Che and Y. Liu, "Benchmarking deep learning models on large healthcare datasets", J. Biomed. Inform., vol. 83, pp. 112-134, Jul. 2018, 10.1016/j.jbi.2018.04.007.
[50]S. Wang, M. B. A. McDermott, G. Chauhan, M. Ghassemi, M. C. Hughes and T. Naumann, "MIMIC-Extract: a data extraction, preprocessing, and representation pipeline for MIMIC-III", 2020. [Online]. Available: arXiv:1907.08322v2.
[51]K. Alghatani, N. Ammar, A. Rezgui and A. Shaban-Nejad, "Predicting Intensive Care Unit Length of Stay and Mortality Using Patient Vital Signs: Machine Learning Model Development and Validation", JMIR Med. Inform., vol. 9, 2021, 10.2196/21347.
[52]L. Li and G. Liu, "In-hospital Mortality Prediction for ICU Patients on Large Healthcare MIMIC Datasets Using Class Imbalance Learning", Proc. ICBDA, pp. 90-93, 2020, 10.1109/ICBDA49040.2020.9101272.
[53]R. Yu, Y. Zheng, R. Zhang, Y. Jiang and C. C. Y. Poon, "Using a Multi-Task Recurrent Neural Network With Attention Mechanisms to Predict Hospital Mortality of Patients", IEEE J. Biomed. Health Inform., vol. 24, no. 2, pp. 486-492, Feb. 2020, 10.1109/JBHI.2019.2916667.
[54]S. M. Azar, M. G. Atigh, A. Nickabadi and A. Alahi, "Convolutional Relational Machine for Group Activity Recognition", Proc. CVPR, pp. 7884-7893, 2019, 10.1109/CVPR.2019.00808.
[55]A. Voulodimos, N. Doulamis, A. Doulamis and E. Protopapadakis, "Deep Learning for Computer Vision: A Brief Review", Comput. Intell. Neurosci., vol. 2018, 2018, 10.1155/2018/7068349.
[56]A. S. Panayides et al., "AI in Medical Imaging Informatics: Current Challenges and Future Directions", IEEE J. Biomed. Health Inform., vol. 24, no. 7, pp. 1837-1857, Jul. 2020, 10.1109/JBHI.2020.2991043.
[57]L. Xu, C. Jiang, J. Wang, J. Yuan and Y. Ren, "Information Security in Big Data: Privacy and Data Mining", IEEE Access, vol. 2, pp. 1149-1176, Oct. 2014, 10.1109/ACCESS.2014.2362522.
[58]G. E. Hinton, S. Osindero and Y. -W. Teh, "A fast learning algorithm for deep belief nets", Neural Comput., vol. 18, no. 7, pp. 1527-1554, Jul. 2006, 10.1162/neco.2006.18.7.1527.
[59]S. Hochreiter and J. Schmidhuber, "Long Short-Term Memory", Neural Comput., vol. 9, no. 8, pp. 1735-1780, Nov. 1997, 10.1162/neco.1997.9.8.1735.
[60]C. Olah, "Understanding LSTM Networks", 2015. [Online]. Available: https://colah.github.io/posts/2015-08-Understanding-LSTMs (2021).
[61]T.-Y. Lin, P. Goyal, R. Girshick, K. He and P. Dollár, "Focal Loss for Dense Object Detection", 2018. [Online]. Available: arXiv:1708.02002.
[62]C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens and Z. Wojna, "Rethinking the Inception Architecture for Computer Vision", Proc. CVPR, pp. 2818-2826, 2016, 10.1109/CVPR.2016.308.
[63]F. Chollet, "Xception: Deep Learning with Depthwise Separable Convolutions", Proc. CVPR, pp. 1800-1807, 2017, 10.1109/CVPR.2017.195.
[64]M. Sandler, A. Howard, M. Zhu, A. Zhmoginov and L. Chen, "MobileNetV2: Inverted Residuals and Linear Bottlenecks", Proc. CVPR, pp. 4510-4520, 2018, 10.1109/CVPR.2018.00474.
[65]K. Nakajima, T. Tamura and H. Miike, "Monitoring of heart and respiratory rates by photoplethysmography using a digital filtering technique", Med. Eng. Phys., vol. 18, pp. 365-372, Jul. 1996, 10.1016/1350-4533(95)00066-6.
[66]T. Vandenberk et al., "Clinical Validation of Heart Rate Apps: Mixed-Methods Evaluation Study", JMIR mHealth uHealth, vol. 5, no.8, pp. e129, Aug. 2017, 10.2196/mhealth.7254.
[67]R. Shriram, A. Wakankar, N. Daimiwal and D. Ramdasi, "Continuous cuffless blood pressure monitoring based on PTT", Proc. ICBBT, pp. 51-55, 2010, 10.1109/ICBBT.2010.5479013.
[68]A. Rasool, M. Rafiq, A. Nasir and F. M. Kashif, "Continuous and Noninvasive Blood Pressure Estimation by Two-Sensor Measurement of Pulse Transit Time", Proc. ICET, pp. 1-5, 2018, 10.1109/ICET.2018.8603612.
[69]W. Lin, H. Wang, O. W. Samuel and G. Li, "Using a new PPG indicator to increase the accuracy of PTT-based continuous cuffless blood pressure estimation", Proc. EMBC, pp. 738-741, 2017, 10.1109/EMBC.2017.8036930.
[70]X. Ding, B. P. Yan, Y. -T. Zhang, J. Liu, N. Zhao and H. K. Tsang, "Pulse Transit Time Based Continuous Cuffless Blood Pressure Estimation: A New Extension and A Comprehensive Evaluation", Sci. Rep., vol. 7, pp. 11554, 2017, 10.1038/s41598-017-11507-3.
[71]K. J. B. Noche, J. F. Villaverde and J. Lazaro, "Portable non-invasive blood pressure measurement using pulse transmit time", Proc. HNICEM, pp. 1-4, 2017, 10.1109/HNICEM.2017.8269546.
[72]J. -Q. Li et al., "Design of a Continuous Blood Pressure Measurement System Based on Pulse Wave and ECG Signals", IEEE J. Transl. Eng. Health Med., vol. 6, pp. 1-14, 2018, 10.1109/JTEHM.2017.2788885.
[73]D. B. McCombie, A. T. Reisner and H. H. Asada, "Adaptive blood pressure estimation from wearable PPG sensors using peripheral artery pulse wave velocity measurements and multi-channel blind identification of local arterial dynamics", Proc. EMBS, pp. 3521-3524, 2006, 10.1109/IEMBS.2006.260590.
[74]L. Peter, N. Noury and M. Cerny, "A review of methods for non-invasive and continuous blood pressure monitoring: Pulse transit time method is promising?", IRBM, vol. 35, no. 5, pp. 271-282, Oct. 2014, 10.1016/j.irbm.2014.07.002.
[75]D. DeMers and D. Wachs, "Physiology mean arterial pressure", in StatPearls [Internet], Treasure Island, FL, USA: StatPearls Publishing, 2021. [Online]. Available: https://www.ncbi.nlm.nih.gov/books/NBK538226/.
[76]G. Yadav, S. Maheshwari and A. Agarwal, "Contrast limited adaptive histogram equalization based enhancement for real time video system", Proc. ICACCI, pp. 2392-2397, 2014, 10.1109/ICACCI.2014.6968381.
[77]C. -T. Yen and J. -D. Lin, "Human body activity recognition using wearable inertial sensors integrated with a feature extraction-based machine-learning classification algorithm", Proc. Inst. Mech. Eng. B: J. Eng. Manuf., pp. 095440542093789, 2020, 10.1177/0954405420937894.
[78]C. -T. Yen, S. -N. Chang and C. Y. Cai, "Development of a Continuous Blood Pressure Measurement and Cardiovascular Multi-Indicator Platform for Asian Populations by Using a Back Propagation Neural Network and Dual Photoplethysmography Sensor Signal Acquisition Technology", J. Nanomater., vol. 2021, 2021, 10.1155/2021/6613817.
[79]A. E. W. Johnson et al., "MIMIC-III, a freely accessible critical care database", Sci. Data, vol. 3, 2016, 10.1038/sdata.2016.35.
[80]A. L. Goldberger et al., "PhysioBank, PhysioToolkit, and PhysioNet: components of a new research resource for complex physiologic signals", Circulation, vol. 101, no. 23, pp. E215-E220, Jun. 2000, 10.1161/01.cir.101.23.e215.
[81]T. Pollard et al., "MIT-LCP/mimic-code: MIMIC-III v1.4 (v1.4)", Zenodo, Jul. 2017, 10.5281/zenodo.821872.