本篇論文透過深度學習研究4種主題，分別為人類活動識別，血壓與心率估算，新型冠狀病毒肺炎胸部X光影像辨識與加護病房住院時間預測。
人類活動識別研究，參考爾灣加州大學人類活動識別數據集的蒐集方式，將具有陀螺儀與加速度計的慣性感測器，放置於腰部蒐集走路、上樓梯、下樓梯、坐、站與躺6種動作，使用1維卷積神經網路從原始數據中擷取特徵，在透過歸一化指數函數分類，實驗數據部分，分別使用爾灣加州大學人類活動識別數據集與實驗室數據集，準確率分別為95.99%和93.77%。
血壓與心率估算，將 8秒長度的光體積變化描記圖法訊號作為輸入，透過深度學習網路模型估算連續的人體收縮壓、舒張壓、心率與平均動脈壓，實驗數據使用加護病房醫學訊息中心大型數據集進行訓練、驗證與測試，該模型是卷積神經網路結合長短期記憶的混合模型，實驗結果於10折交叉驗證收縮壓、舒張壓、心率與平均動脈壓之平均絕對誤差與標準差分別為2.54±3.88毫米汞柱、1.59±2.45毫米汞柱、1.62±2.55次/分鐘與1.59±2.34毫米汞柱。
新型冠狀病毒肺炎胸部X光影像辨識，將透過4種深度學習模型，對胸部X光圖像進行辨識，模型將會判斷是否有新型冠狀病毒肺炎。提出將原始圖片與經過限制對比度自適應直方圖均衡處理後的圖片進行疊加的特徵融合方法，探討各模型之間以及有無特徵融合的準確率。使用的數據集為版本3，具有1200筆新型冠狀病毒的圖像，實驗結果以DenseNet201的準確率最高，於2分類具有99.22%的準確率，3分類則是99.74%的準確率。
加護病房住院時間預測，利用21種時間序列特徵以及其6種統計特徵，透過深度學習，來做加護病房住院天數的預測，2分類與3分類分別採用Focal Loss與SMOTE解決數據不平衡問題，其中以住院時間是否大於7天作為2分類，以及住院時間小於等於10天，住院時間大於10天、住院時間小於等於30天，住院時間大於30天作為3分類，其接收者操作特徵曲線下面積於2分類為0.845，3分類為0.997。

This paper studies 4 topics through deep learning, respectively human activity recognition, blood pressure and heart rate estimation, the identification of chest X-ray images of coronavirus disease 2019 (COVID-19) and the prediction of the length of stay in the intensive care unit.
Human activity recognition, refer to the collection method of the human activity recognition dataset of the University of California, Irvine, and place the inertial sensor with gyroscope and accelerometer on the waist, to collect 6 kinds of actions: walking, walking up stairs, walking down stairs, sitting, standing and laying, use a one-dimensional convolutional neural network to extract features from the original data, classified by Softmax function. The experimental data uses the human activity recognition dataset of the University of California, Irvine, and the laboratory dataset, the accuracy rates are 95.99% and 93.77% respectively.
Blood pressure and heart rate estimation, take the 8-second photoplethysmography signal as input, and use the deep learning network model to estimate continuous human systolic blood pressure, diastolic blood pressure, heart rate and mean arterial pressure, the experimental data is trained, verified and tested using the large dataset of medical information mart for intensive care.This model is a hybrid model of convolutional neural network combined with LSTM, the results of the experiment were cross-validated with a 10-fold cross-validation of the mean absolute error and standard deviation of systolic blood pressure, diastolic blood pressure, heart rate, and mean arterial pressure, respectively 2.54±3.88 mmHg, 1.59±2.45 mmHg, 1.62±2.55 BPM and 1.59±2.34 mmHg.
Identification of chest X-ray images of COVID-19, using 4 deep learning models to identify chest X-ray images, the model will determine whether there is COVID-19. A feature fusion method that superimposes the original image and the image processed by the CLAHE, and discuss the accuracy of the model and with or without feature fusion. The version of the dataset used has 1200 chest X-ray images of the COVID-19. The experimental result is that DenseNet201 has the highest accuracy rate, the accuracy of binary classification is 99.22%, and the accuracy of three-class classification is 99.74%.
Predict the length of stay in the intensive care unit, using 21 time series features and 6 statistical features use deep learning to predict the length of stay in the intensive care unit, binary classification and three-class classification use Focal Loss and SMOTE respectively to solve the problem of data imbalance, whether the length of stay is greater than 7 days is binary classification, the length of stay is less than or equal to 10 days, the length of stay is greater than 10 days and the number of hospitalization days is less than or equal to 30 days, the length of stay is greater than 30 days is three-class classification, the area under the receiver operating characteristic curve at binary classification is 0.845, and the three-class classification is 0.997.

摘要..................i
Abstract..................ii
誌謝..................iv
目錄..................v
表目錄..................viii
圖目錄..................ix
第一章 緒論..................1
1.1 研究背景..................1
1.1.1 人類活動識別研究..................1
1.1.2 血壓與心率估算..................3
1.1.3 新型冠狀病毒肺炎胸部X光影像辨識..................5
1.1.4 加護病房住院時間預測..................7
1.2 研究動機與目的..................8
1.2.1 人類活動識別研究..................8
1.2.2 血壓與心率估算..................8
1.2.3 新型冠狀病毒肺炎胸部X光影像辨識..................9
1.2.4 加護病房住院時間預測..................9
1.3 章節架構與貢獻..................10
第二章 文獻探討..................12
2.1 卷積神經網路..................12
2.2 激活函數..................14
2.3 損失函數..................16
2.4 長短期記憶..................17
2.5 合成少數過採樣技術..................18
2.6 光體積變化描記圖法..................18
2.7 限制對比度自適應直方圖均衡..................18
2.8 評估指標..................19
2.8.1 人類活動識別研究..................19
2.8.2 血壓與心率預測..................21
2.8.3 新型冠狀病毒肺炎胸部X光影像辨識..................21
2.8.4 加護病房住院時間預測..................22
第三章 人類活動識別研究..................24
3.1 數據集..................24
3.1.1 爾灣加州大學人類活動識別數據集..................24
3.1.2 實驗室數據集..................25
3.2 硬體與人類活動識別演算法..................27
3.2.1 硬體介紹..................27
3.2.2 網路架構與超參數..................28
3.3 實驗結果..................29
3.3.1 UCI HAR數據集之各項評估指標..................29
3.3.2 UCI HAR數據集之混淆矩陣..................29
3.3.3 UCI HAR數據集之模型訓練曲線圖..................30
3.3.4 實驗室數據集之各項評估指標..................30
3.3.5 實驗室數據集之混淆矩陣..................31
3.3.6 實驗室數據集之模型訓練曲線圖..................31
3.3.7 UCI HAR數據集與其他文獻比較..................32
3.4 結論..................33
第四章 血壓與心率估算..................34
4.1 數據集..................34
4.2 血壓與心率估算演算法..................34
4.2.1 預處理..................34
4.2.2 網路架構與超參數..................35
4.3 實驗結果..................37
4.3.1 損失函數曲線圖..................37
4.3.2 評估指標..................37
4.3.3 相關文獻比較..................39
4.4 結論..................40
第五章 新型冠狀病毒肺炎胸部X光影像辨識..................41
5.1 數據集..................41
5.2 新型冠狀病毒肺炎胸部X光演算法..................42
5.2.1 預處理..................42
5.2.2 特徵融合..................43
5.2.3 網路超參數設置..................43
5.2.4 實驗流程..................44
5.3 實驗結果..................45
5.3.1 數據集A實驗結果..................45
5.3.2 數據集B實驗結果..................47
5.3.3 相關文獻比較..................49
5.4 結論..................51
第六章 加護病房住院時間預測..................52
6.1 數據集..................52
6.2 預測加護病房住院時間演算法..................52
6.2.1 預處理..................52
6.2.2 預測目標..................54
6.2.3 網路架構與超參數設置..................55
6.3 實驗結果..................56
6.3.1 住院時間2分類實驗結果..................56
6.3.2 住院時間3分類實驗結果..................57
6.3.3 住院時間相關文獻比較..................59
6.4 結論..................60
總結論..................61
參考文獻..................62
Extended Abstract..................71

[1]M. Cornacchia, K. Ozcan, Y. Zheng and S. Velipasalar, "A Survey on Activity Detection and Classification Using Wearable Sensors", in IEEE Sens. J., vol. 17, no. 2, pp. 386-403, Jan. 2017, 10.1109/JSEN.2016.2628346.
[2]Y. Chen and C. Shen, "Performance Analysis of Smartphone-Sensor Behavior for Human Activity Recognition", in IEEE Access, vol. 5, pp. 3095-3110, 2017, 10.1109/ACCESS.2017.2676168.
[3]J. Margarito, R. Helaoui, A. M. Bianchi, F. Sartor and A. G. Bonomi, "User-Independent Recognition of Sports Activities From a Single Wrist-Worn Accelerometer: A Template-Matching-Based Approach", in IEEE Trans. Biomed. Eng., vol. 63, no. 4, pp. 788-796, Apr. 2016, 10.1109/TBME.2015.2471094.
[4]L. Cantelli, G. Muscato, M. Nunnari and D. Spina, "A Joint-Angle Estimation Method for Industrial Manipulators Using Inertial Sensors", in IEEE ASME Trans. Mechatron., vol. 20, no. 5, pp. 2486-2495, Oct. 2015, 10.1109/TMECH.2014.2385940.
[5]N. Tüfek and O. Özkaya, "A Comparative Research on Human Activity Recognition Using Deep Learning", 27th Signal Processing and Communications Applications Conference (SIU), 2019, pp. 1-4, 10.1109/SIU.2019.8806395.
[6]A. Jain and V. Kanhangad, "Human Activity Classification in Smartphones Using Accelerometer and Gyroscope Sensors", in IEEE Sens. J., vol. 18, no. 3, pp. 1169-1177, Feb. 2018, 10.1109/JSEN.2017.2782492.
[7]N. B. Gaikwad, V. Tiwari, A. Keskar and N. C. Shivaprakash, "Efficient FPGA Implementation of Multilayer Perceptron for Real-Time Human Activity Classification", in IEEE Access, vol. 7, pp. 26696-26706, 2019, 10.1109/ACCESS.2019.2900084.
[8]N. Tufek, M. Yalcin, M. Altintas, F. Kalaoglu, Y. Li and S. K. Bahadir, "Human Action Recognition Using Deep Learning Methods on Limited Sensory Data", in IEEE Sens. J., vol. 20, no. 6, pp. 3101-3112, Mar. 2020, 10.1109/JSEN.2019.2956901.
[9]A. S. A. Sukor, A. Zakaria and N. A. Rahim, "Activity recognition using accelerometer sensor and machine learning classifiers", IEEE 14th International Colloquium on Signal Processing & Its Applications (CSPA), 2018, pp. 233-238, 10.1109/CSPA.2018.8368718.
[10]S.-M. Lee, S. M. Yoon and H. Cho, "Human activity recognition from accelerometer data using Convolutional Neural Network", IEEE International Conference on Big Data and Smart Computing (BigComp), 2017, pp. 131-134, 10.1109/BIGCOMP.2017.7881728.
[11]T. Zebin, P. J. Scully and K. B. Ozanyan, "Human activity recognition with inertial sensors using a deep learning approach", IEEE SENSORS, 2016, pp. 1-3, 10.1109/ICSENS.2016.7808590.
[12]W. Xu, Y. Pang, Y. Yang and Y. Liu, "Human Activity Recognition Based On Convolutional Neural Network", 24th International Conference on Pattern Recognition (ICPR), 2018, pp. 165-170, 10.1109/ICPR.2018.8545435.
[13]H. Zhang, Z. Xiao, J. Wang, F. Li and E. Szczerbicki, "A Novel IoT-Perceptive Human Activity Recognition (HAR) Approach Using Multihead Convolutional Attention", in IEEE Internet of Things J., vol. 7, no. 2, pp. 1072-1080, Feb. 2020, 10.1109/JIOT.2019.2949715.
[14]T. Zebin, P. J. Scully, N. Peek, A. J. Casson and K. B. Ozanyan, "Design and Implementation of a Convolutional Neural Network on an Edge Computing Smartphone for Human Activity Recognition", in IEEE Access, vol. 7, pp. 133509-133520, 2019, 10.1109/ACCESS.2019.2941836.
[15]K. Xia, J. Huang and H. Wang, "LSTM-CNN Architecture for Human Activity Recognition", in IEEE Access, vol. 8, pp. 56855-56866, 2020, 10.1109/ACCESS.2020.2982225.
[16]Prospective Studies Collaboration., "Age-specific relevance of usual blood pressure to vascular mortality: A meta-analysis of individual data for one million adults in 61 prospective studies", The Lancet, vol. 360, no. 9349, pp. 1903-1913, Dec. 2002, 10.1016/s0140-6736(02)11911-8.
[17]M. Panwar, A. Gautam, D. Biswas and A. Acharyya, "PP-Net: A Deep Learning Framework for PPG-Based Blood Pressure and Heart Rate Estimation", in IEEE Sens. J., vol. 20, no. 17, pp. 10000-10011, Sept. 2020, 10.1109/JSEN.2020.2990864.
[18]A. Gaurav, M. Maheedhar, V. N. Tiwari and R. Narayanan, "Cuff-less PPG based continuous blood pressure monitoring — A smartphone based approach", 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, pp. 607-610, 10.1109/EMBC.2016.7590775.
[19]M. Kachuee, M. M. Kiani, H. Mohammadzade and M. Shabany, "Cuffless Blood Pressure Estimation Algorithms for Continuous Health-Care Monitoring", in IEEE Trans. Biomed. Eng., vol. 64, no. 4, pp. 859-869, Apr. 2017, 10.1109/TBME.2016.2580904.
[20]S. C. Gao, P. Wittek, L. Zhao and W. J. Jiang, "Data-driven estimation of blood pressure using photoplethysmographic signals", 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, pp. 766-769, 10.1109/EMBC.2016.7590814.
[21]Zhang, Yue and Zhimeng Feng, "A SVM method for continuous blood pressure estimation from a PPG signal", 9th International Conference on Machine Learning and Computing., 2017, pp. 128-132, 10.1145/3055635.3056634.
[22]K. Duan, Z. Qian, M. Atef and G. Wang, "A feature exploration methodology for learning based cuffless blood pressure measurement using photoplethysmography", 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, pp. 6385-6388, 10.1109/EMBC.2016.7592189.
[23]S. S. Mousavi, M. Firouzmand, M. Charmi, M. Hemmati, M. Moghadam and Y. Ghorbani, "Blood pressure estimation from appropriate and inappropriate PPG signals using A whole-based method", Biomed. Signal Process. Control, vol. 47, Jun. 2019, pp. 196-206, 10.1016/j.bspc.2018.08.022.
[24]T. Athaya and S. Choi, "An estimation method of continuous non-invasive arterial blood pressure waveform using photoplethysmography: A U-Net architecture-based approach", Sensors, val.21, no. 5, pp. 1867, Mar. 2021, 10.3390/s21051867.
[25]P. Li and T. -M. Laleg-Kirati, "Central Blood Pressure Estimation From Distal PPG Measurement Using Semiclassical Signal Analysis Features", in IEEE Access, vol. 9, pp. 44963-44973, 2021, 10.1109/ACCESS.2021.3065576.
[26]J. F.-W. Chan et al., "A familial cluster of pneumonia associated with the 2019 novel coronavirus indicating person-to-person transmission: a study of a family cluster", The Lancet, vol. 395, no. 10223, pp. 514-523, Feb. 2020, 10.1016/S0140-6736(20)30154-9.
[27]N. ZHU et al., "A novel coronavirus from patients with pneumonia in China", N. Engl. J. Med., Feb. 2020, 10.1056/NEJMoa2001017.
[28]M. Hammad, A. M. Iliyasu, A. Subasi, E. S. L. Ho and A. A. A. El-Latif, "A Multitier Deep Learning Model for Arrhythmia Detection", in IEEE Trans. Instrum. Meas., vol. 70, pp. 1-9, 2021, Art no. 2502809, 10.1109/TIM.2020.3033072.
[29]W. Liu, X. Liu, H. Li, M. Li, X. Zhao and Z. Zhu, "Integrating Lung Parenchyma Segmentation and Nodule Detection With Deep Multi-Task Learning", in IEEE J. Biomed. Health Inform., vol. 25, no. 8, pp. 3073-3081, Aug. 2021, 10.1109/JBHI.2021.3053023.
[30]H. Hu, Q. Li, Y. Zhao and Y. Zhang, "Parallel Deep Learning Algorithms With Hybrid Attention Mechanism for Image Segmentation of Lung Tumors", in IEEE Trans. Ind. Informat., vol. 17, no. 4, pp. 2880-2889, Apr. 2021, 10.1109/TII.2020.3022912.
[31]D. I. Apostoloplulos and A. T. Mpesiana, "Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks", Phys. Eng. Sci. Med., vol. 43, no. 2, pp. 635-640, Jun. 2020, 10.1007/s13246-020-00865-4.
[32]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.
[33]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, Oct. 2020, 10.1016/j.media.2020.101794.
[34]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, Jun. 2020, 10.1016/j.compbiomed.2020.103805.
[35]J. Redmon and A. Farhadi, "YOLO9000: Better, Faster, Stronger", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 6517-6525, 10.1109/CVPR.2017.690.
[36]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, Jun. 2020, 10.1016/j.compbiomed.2020.103792.
[37]E. H. Chowdhury et al., "Can AI Help in Screening Viral and COVID-19 Pneumonia? ", in IEEE Access, vol. 8, pp. 132665-132676, 2020, 10.1109/ACCESS.2020.3010287.
[38]E. F. Ohata et al., "Automatic detection of COVID-19 infection using chest X-ray images through transfer learning", in IEEE/CAA J. Autom. Sinica, vol. 8, no. 1, pp. 239-248, Jan. 2021, 10.1109/JAS.2020.1003393.
[39]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, 2020, 10.1016/j.asoc.2020.106859.
[40]A. I. Khan, J. Shah and 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, Nov. 2020, 10.1016/j.cmpb.2020.105581.
[41]R. Bhadra and S. Kar, "Covid Detection from CXR Scans using Deep Multi-layered CNN", 2020 IEEE Bombay Section Signature Conference (IBSSC), 2020, pp. 214-218, 10.1109/IBSSC51096.2020.9332210.
[42]M. R. Karim, T. Döhmen, M. Cochez, O. Beyan, D. Rebholz-Schuhmann and S. Decker, "DeepCOVIDExplainer: Explainable COVID-19 Diagnosis from Chest X-ray Images", 2020 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2020, pp. 1034-1037, 10.1109/BIBM49941.2020.9313304.
[43]A. Abbas, M.M. Abdelsamea and M. M. Gaber, "Classification of COVID-19 in chest X-ray images using DeTraC deep convolutional neural network", Appl. Intell., vol. 51, pp. 854-864, Sept. 2021, 10.1007/s10489-020-01829-7.
[44]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 Dataset (MIMIC III) ", 2020, [Online] Available: https://arxiv.org/abs/2009.01366 (2021).
[45]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, Jun. 2021, 10.1016/j.jbi.2021.103778.
[46]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", Proceedings of the ACM Conference on Health Inference and Learning, 2020, pp. 222235, 10.1145/3368555.3384469.
[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, no. 96, Jun. 2019, 10.1038/s41597-019-0103-9.
[48]B. Bardak and M. Tan, "Improving clinical outcome predictions using convolution over medical entities with multimodal learning", Artif. Intell. Med., vol. 117, Jul. 2021, 10.1016/j.artmed.2021.102112.
[49]R. Poppe, "Vision-Based Human Motion Analysis: An Overview", Comput. Vis. Image Underst., vol. 108, pp. 4-18, Oct.-Nov. 2007, 10.1016/j.cviu.2006.10.016.
[50]J.-L. Reyes-Ortiz, L. Oneto, A. Ghio, A. Samà, D. Anguita and X. Parra, "Human activity recognition on smartphones with awareness of basic activities and postural transitions", Artificial Neural Networks and Machine Learning-ICANN 2014-International Conference on Artificial Neural Networks. Proceedings, 2014, pp. 177-184, 10.1007/978-3-319-11179-7_23.
[51]N. Davies, D. P. Siewiorek and R. Sukthankar, "Activity-Based Computing", in IEEE Pervasive Computing, vol. 7, no. 2, pp. 20-21, Apr.-Jun. 2008, 10.1109/MPRV.2008.26.
[52]N. Ravi, N. Dandekar, P. Mysore and M. L. Littman, "Activity recognition from accelerometer data", Proc. 20th Nat. Conf. Artif. Intell., 2005, pp. 1541-1546, vol. 5, no. 2005.
[53]D. Nachman et al., "Comparing blood pressure measurements between a photoplethysmography-based and a standard cuff-based manometry device", Sci. Rep., vol. 10, Dec. 2020, 10.1038/s41598-020-73172-3.
[54]D. Castaneda, A. Esparza, M. Ghamari, C. Soltanpur and H. Nazeran1, "A review on wearable photoplethysmography sensors and their potential future applications in health care", Int. J. Biosensors Bioelectron., vol. 4, no. 4, pp. 195-202, Aug. 2018, 10.15406/ijbsbe.2018.04.00125.
[55]M. Leone, P. Asfar, P. Radermacher, J.-L. Vincent and C. Martin, "Optimizing mean arterial pressure in septic shock: a critical reappraisal of the literature", Crit. Care, vol. 19, pp. 101, Dec. 2015, 10.1186/s13054-015-0794-z.
[56]W-J. Guan et al., "Clinical Characteristics of Coronavirus Disease 2019 in China", N. Engl. J. Med., vol. 382, no. 18, pp. 1708-1720, Apr. 2020, 10.1056/NEJMoa2002032.
[57]T. Ai et al., "Correlation of Chest CT and RT-PCR Testing for Coronavirus Disease 2019 (COVID-19) in China: A Report of 1014 Cases", Radiology, vol. 296, no. 2, pp. E32-E40, Feb. 2020, 10.1148/radiol.2020200642.
[58]G. D. Rubin et al., "The role of chest imaging in patient management during the COVID-19 pandemic: A multinational consensus statement from the fleischner society", Radiology, vol. 296, no. 1, pp. 172-180, Apr. 2020, 10.1148/radiol.2020201365.
[59]H. Y. F. Wong et al., “Frequency and Distribution of Chest Radiographic Findings in Patients Positive for COVID-19”, Radiology, vol. 296, no. 2, pp. E72-E78, Mar. 2020, 10.1148/radiol.2020201160.
[60]A. Bernheim et al., "Chest CT Findings in Coronavirus Disease-19 (COVID-19): Relationship to Duration of Infection", Radiology, vol. 295, no. 3, pp. 685-691, Feb. 2020, 10.1148/radiol.2020200463.
[61]S. Purushotham, C. Meng, Z. Che and Y. Liu, "Benchmarking deep learning models on large healthcare datasets", J. Biomed. Informat., vol. 83, pp. 112-134, Jul. 2018, 10.1016/j.jbi.2018.04.007.
[62]P. J. Huber, "Robust estimation of a location parameter", Ann. Math. Statist., vol. 35, no. 1, pp. 73-101, Mar. 1964, 10.1214/aoms/1177703732.
[63]T. Lin, P. Goyal, R. Girshick, K. He and P. Dollár, "Focal Loss for Dense Object Detection", in IEEE Trans. Pattern Anal. Mach. Intell., vol. 42, no. 2, pp. 318-327, Feb. 2020, 10.1109/TPAMI.2018.2858826.
[64]C. Olah, "Understanding LSTM Networks", 2015, [Online]. Available: https://colah.github.io/posts/2015-08-Understanding-LSTMs (2021).
[65]N. V. Chawla, K. W. Bowyer, L. O. Hall and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique", J. Artif. Intell. Res., vol. 16, pp. 321-357, Jun. 2002, 10.1613/jair.953.
[66]A. Ishaq et al., "Improving the Prediction of Heart Failure Patients’ Survival Using SMOTE and Effective Data Mining Techniques", in IEEE Access, vol. 9, pp. 39707-39716, 2021, 10.1109/ACCESS.2021.3064084.
[67]B. Baesens, S. Höppner, I. Ortner and T. Verdonck, "robROSE: A robust approach for dealing with imbalanced data in fraud detection", Stat. Methods Appl., vol. 30, pp. 841-861, Jun. 2021, 10.1007/s10260-021-00573-7.
[68]A. Awad, M. Bader-El-Den, J. McNicholas, J. Briggs and Y. El-Sonbaty, "Predicting hospital mortality for intensive care unit patients: Time-series analysis", Health Informatics J., vol. 26, pp. 1043-1059, Jun. 2020, 10.1177/1460458219850323.
[69]K. Shelley and S. Shelley, "Pulse oximeter waveform: photoelectric plethysmography", Clinical Monitoring Carol Lake R. Hines and C. Blitt Eds.: WB Saunders Company, 2001, pp. 420-428.
[70]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, no. 5, pp. 365-372, Jul. 1996, 10.1016/1350-4533(95)00066-6.
[71]S. Rhee, B.-H. Yang and H. H. Asada, "Artifact-resistant power-efficient design of finger-ring plethysmographic sensors", in IEEE Trans. Biomed. Eng., vol. 48, no. 7, pp. 795-805, Jul. 2001, 10.1109/10.930904.
[72]A. M. Reza, "Realization of the Contrast Limited Adaptive Histogram Equalization (CLAHE) for Real-Time Image Enhancement", J. VLSI signal process. syst. signal image video technol. (Online), vol. 38, pp. 35-44, 2004, 10.1023/B:VLSI.0000028532.53893.82.
[73]D. Anguita, A. Ghio, L. Oneto, X. Parra and J. L. Reyes-Ortiz, "A public domain dataset for human activity recognition using smartphones", 21th European Symposium on Artificial Neural Networks (ESANN), 2013, pp. 437-442.
[74]C. -T. Yen, J. -X. Liao and Y. -K. Huang, "Human Daily Activity Recognition Performed Using Wearable Inertial Sensors Combined With Deep Learning Algorithms", in IEEE Access, vol. 8, pp. 174105-174114, 2020, 10.1109/ACCESS.2020.3025938.
[75]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", Proceedings of the Institution of Mechanical Engineers, Part B: Journal of Engineering Manufacture, Jul. 2020, 0.1177/0954405420937894.
[76]R. Mutegeki and D. S. Han, "A CNN-LSTM Approach to Human Activity Recognition", 2020 International Conference on Artificial Intelligence in Information and Communication (ICAIIC), 2020, pp. 362-366, 10.1109/ICAIIC48513.2020.9065078.
[77]S. Deep and X. Zheng, "Hybrid Model Featuring CNN and LSTM Architecture for Human Activity Recognition on Smartphone Sensor Data", 20th International Conference on Parallel and Distributed Computing, Applications and Technologies (PDCAT), 2019, pp. 259-264, 10.1109/PDCAT46702.2019.00055.
[78]S. Yu and L. Qin, "Human Activity Recognition with Smartphone Inertial Sensors Using Bidir-LSTM Networks", 3rd International Conference on Mechanical, Control and Computer Engineering (ICMCCE), 2018, pp. 219-224, 10.1109/ICMCCE.2018.00052.
[79]S. Dhanraj, S. De and D. Dash, "Efficient Smartphone-Based Human Activity Recognition Using Convolutional Neural Network", 2019 International Conference on Information Technology (ICIT), 2019, pp. 307-312, 10.1109/ICIT48102.2019.00061.
[80]X. Yang, Y. Lyu, Y. Sun and C. Zhang, "A New Residual Dense Network for Dance Action Recognition From Heterogeneous View Perception", Front. Neurorobot., vol. 15, pp. 89, Jun. 2021, doi: 10.3389/fnbot.2021.698779.
[81]D. Thakur and S. Biswas, "Feature fusion using deep learning for smartphone based human activity recognition", Int. j. inf. tecnol., vol. 13, pp. 1615-1624, Jun. 2021, 10.1007/s41870-021-00719-6.
[82]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.
[83]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.
[84]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.
[85]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.e25.
[86]M. Kachuee, M. M. Kiani, H. Mohammadzade and M. Shabany, "Cuff-less high-accuracy calibration-free blood pressure estimation using pulse transit time", IEEE International Symposium on Circuits and Systems (ISCAS), 2015, pp. 1006-1009, 10.1109/ISCAS.2015.7168806.
[87]A. Pachauri and M. Bhuyan, "ABP peak detection using energy analysis technique", International Conference on Multimedia, Signal Processing and Communication Technologies, 2011, pp. 36-39, 10.1109/MSPCT.2011.6150514.
[88]S.A. Rankawat and R. Dubey, "Robust heart rate estimation from multimodal physiological signals using beat signal quality index based majority voting fusion method", Biomed. Signal Process. Control, vol. 33, pp. 201-212, Mar. 2017, 10.1016/j.bspc.2016.12.004.
[89]E. Khan, F. Al Hossain, S. Z. Uddin, S. K. Alam and M. K. Hasan, "A Robust Heart Rate Monitoring Scheme Using Photoplethysmographic Signals Corrupted by Intense Motion Artifacts", in IEEE Trans. Biomed. Eng., vol. 63, no. 3, pp. 550-562, Mar. 2016, 10.1109/TBME.2015.2466075.
[90]A. Temko, "Accurate Heart Rate Monitoring During Physical Exercises Using PPG", in IEEE Trans. Biomed. Eng., vol. 64, no. 9, pp. 2016-2024, Sept. 2017, 10.1109/TBME.2017.2676243.
[91]K. R. Arunkumar and M. Bhaskar, "Heart rate estimation from photoplethysmography signal for wearable health monitoring devices", Biomed. Signal Process. Control, vol. 50, pp. 1-9, Apr. 2019, 10.1016/j.bspc.2019.01.021.
[92]D. Biswas et al., "CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment", in IEEE Trans. Biomed. Circuits Syst., vol. 13, no. 2, pp. 282-291, Apr. 2019, 10.1109/TBCAS.2019.2892297.
[93]K. R. Arunkumar and M. Bhaskar, "Robust De-Noising Technique for Accurate Heart Rate Estimation Using Wrist-Type PPG Signals", in IEEE Sens. J., vol. 20, no. 14, pp. 7980-7987, Jul. 2020, 10.1109/JSEN.2020.2982540.
[94]H. Chung, H. Ko, H. Lee and J. Lee, "Deep Learning for Heart Rate Estimation From Reflectance Photoplethysmography With Acceleration Power Spectrum and Acceleration Intensity", in IEEE Access, vol. 8, pp. 63390-63402, 2020, 10.1109/ACCESS.2020.2981956.
[95]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/ (2021).
[96]Q. Zhang, C. Ge and Y. Xin, "Estimating Heart Rate during Steady-State Activities and Transitions Based on Signal of PPG and ACC", IEEE International Conference on Mechatronics and Automation (ICMA), 2020, pp. 279-283, 10.1109/ICMA49215.2020.9233764.
[97]S. Puranik and A. W. Morales, "Heart Rate Estimation of PPG Signals With Simultaneous Accelerometry Using Adaptive Neural Network Filtering", in IEEE Trans. Consum. Electron., vol. 66, no. 1, pp. 69-76, Feb. 2020, 10.1109/TCE.2019.2961263.
[98]M. Risso et al., "Robust and Energy-Efficient PPG-Based Heart-Rate Monitoring", IEEE International Symposium on Circuits and Systems (ISCAS), 2021, pp. 1-5, 10.1109/ISCAS51556.2021.9401282.
[99]K. He, X. Zhang, S. Ren and J. Sun, "Deep Residual Learning for Image Recognition", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 770-778, 10.1109/CVPR.2016.90.
[100]K. He, X. Zhang, S. Ren and J. Sun, "Identity Mappings in Deep Residual Networks", Springer, Cham, 2016, pp. 630-645, vol. 9908, 10.1007/978-3-319-46493-0_38.
[101]G. Huang, Z. Liu, L. Van Der Maaten and K. Q. Weinberger, "Densely Connected Convolutional Networks", IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 2261-2269, 10.1109/CVPR.2017.243.
[102]A. E. W. Johnson et al., "MIMIC-III, a freely accessible critical care dataset", Sci. Data, vol. 3, pp. 160035, May 2016, 10.1038/sdata.2016.35.
[103]T. Pollard, "MIT-LCP/mimic-code: MIMIC-III v1.4", Zenodo, Jul. 2017, 10.5281/zenodo.821872.