現今呼吸疾病是人們高度關注的問題，尤其是近期的新冠狀病毒對於哮喘疾病的影響。哮喘是需要長期控制的疾病，為了讓其得到有效治療而進行鑽研。數據分析在近年來具有新穎性，包括視覺化、資料探勘、類神經網路等。皆可以在不同領域中找出關鍵因素而進行分析。本研究主要對哮喘氣喘藥物顆粒沉積進行探討，內容可以分為兩個部分。第一部分為健康與哮喘患者之呼吸道吸入過程中的氣固兩相運動和氣膠沉積；第二部分則是透過數據分析方法研究藥物顆粒沉積預測和應用。
本研究的第一部分中，氣膠的吸入是人類呼吸道重要且實際的問題，例如藥物或病毒氣膠的吸收。為了弄清這些氣膠的物理特性，預測了健康和哮喘人類氣道的13至15代（G13-G15）中,顆粒直徑分別為1、3和5微米的氣膠之沉積分數（DFs）。使用數值方法求解了控制氣相的納維-史托克方程式和顆粒運動的離散相模型（DPM）。造成沉積的主要力量是慣性衝擊力和復雜的二次流動速度。哮喘幾何中的曲率和正弦褶皺導致形成複雜的二次流，從而導致更高的DF。在受哮喘影響的氣管中，複雜的二次流強度最強。健康氣道的DF為0％，哮喘氣道的DF為1.69％至52.93％。透過本研究，可以確定藥物氣霧劑粒徑對哮喘患者的治療效果，這有利於抑制哮喘氣道的炎症。此外，隨著引起肺炎的新冠狀病毒的最新發展，向哮喘患者遞送生物氣溶膠的預測的物理方法和有效的模擬方法對於防止慢性病和流行病的惡化至關重要。
本研究的第二部分主要目的集中在分析數據以找出研究中的關鍵因素這在工程領域很重要。本研究使用三種數據分析方法：田口方法，響應平面方法（RSM）和Polyanalyst統計數據分析方法。該數據基於使用計算流體力學（CFD）和離散顆粒運動（DPM）對哮喘患者下游氣道中藥物顆粒氣溶膠的氣流動力學和沈積效率進行仿真所得的結果。三個主要參數影響哮喘患者肺部的氣溶膠沉積，流速，藥物劑量和顆粒粒徑。這三個參數的範圍如下，流速在30-60（L·min-1）之間，藥物劑量在200-400 (μg·puff-1)之間，粒徑在1-5 (μm)之間。在對田口方法的L9正交表進行組合分析後，在本研究中選擇了最佳的參數組合進行仿真，並且影響因子的重要性如下，粒徑大於藥物劑量大於流速。藉由使用響應平面方法的方差分析中可以發現，低流速，低藥物劑量和大粒徑具有更好的沉積效率。 Polyanalyst使用三種算法：多元自適應回歸樣條（MARS），神經網絡（NN）和卷積神經網絡（CNN）進行數據預測。發現多元自適應回歸樣條、神經網絡和卷積神經網絡的R2值分別高達0.999995, 0.999284和0.999998。因此發現田口法是找到最佳組合的分析方法。另一方面，響應平面方法可以找到最重要的關鍵因素。 Polyanalyst不僅可以找到最佳情況，還可以在最快的時間準確預測沉積效率。本研究也探討數據分析對於新冠狀病毒識別的重要性，已提早防止新冠狀病毒擴散。

Nowadays, respiratory diseases are of high concern especially the recent impact of the coronavirus on asthma disease. Asthma is a disease that needs to be controlled over a long period of time, and this study has been conducted in order to provide effective treatment. Data analysis is highly applied in recent years, including visualization, data mining, neural networks, etc., which can be used to find out the causes of asthma in different fields. In recent years, data analysis has been new in many fields, including visualization, data mining, and neural networks, etc. This study mainly discusses the deposition of asthma drug particles, and the content can be divided into two parts. The first part is the gas-solid two-phase motions and aerosol deposition during respiratory inhalation of patients with health and asthma; the second part is to study the prediction and application of drug particle deposition through data analysis methods.
In the first part, Inhalation of aerosols is an important and practical issue for human airways such as pharmaceutical or virus aerosol uptake. To figure out these aerosol physics, the deposition fractions (DFs) of aerosols with diameters of 1, 3, and 5 µm in generations 13-15 (G13-G15) of healthy and asthmatic human airways are predicted. The Navier-stokes equations governing the gaseous phase and the discrete phase model (DPM) for particles’ motion are solved using numerical methods. The main forces responsible for deposition are inertial impaction forces and complex secondary flow velocities. The curvatures and sinusoidal folds in the asthmatic geometry lead to the formation of complex secondary flows and hence higher DFs. The intensities of complex secondary flows are strongest at the generations affected by asthma. The DF in the healthy airways is 0%, and it ranges from 1.69% to 52.93% in the asthmatic ones. From this study, the effects of the pharmaceutical aerosol particle diameters in the treatment of asthma patients can be established, which is conducive to inhibiting the inflammation of asthma airways. Furthermore, with the recent development of COVID-19 which causes pneumonia, the predicted physics and effective simulation methods of bioaerosols delivery to asthma patients are vital to prevent the exacerbation of the chronic ailment and the epidemic.
The purpose of second part study focuses on analyzing data to find out the key factors in a study is important in the field of engineering. This study used three data analysis methods, Taguchi method, response surface method (RSM), and Polyanalyst statistical data analysis method. The data is based on the results from the simulation of airflow dynamics and deposition efficiencies of drug particles aerosols in the downstream airways of asthma patients using computational fluid dynamics (CFD) and discrete particle motion (DPM). Three main parameters affect aerosol deposition in the lungs of asthma patients, flow rate, drug dose, and particle size. The ranges for the three parameters are as follows, the flow rate is between 30-60 (L·min-1), the drug dose is between 200-400 (μg·puff-1), and the particle size is between 1-5 (μm). After the combination analysis of the L9 orthogonal table of the Taguchi method, the best combination of parameters is selected for simulation in this study, and the importance of the influencing factors rank as follows, particle size, drug dose, and flow rate. From the ANOVA using RSM, it can be found that small flow rates, drug doses, and the large particle sizes have a better deposition efficiency. Polyanalyst uses three algorithms: Multivariate Adaptive Regression Splines (MARS), Neural network (NN), and Convolutional neural network (CNN) for data prediction. It is found that the R2 values of MARS, NN, and CNN are as high as 0.999995, 0.999284, and 0.999998, respectively. Taguchi is discovered to be the best method of analysis in finding the best case. RSM, on the other hand, can find the most important factors. Polyanalyst can not only find the best case but also accurately predict the deposition efficiency at the fastest time. Furthermore, this study discusses the importance of data analysis for COVID-19 identification, which has prevented COVID-19 proliferation earlier.

[1] Guarnieri M, Balmes JR. Outdoor air pollution and asthma. The Lancet. 2014;383:1581-92.
[2] Kim K-H, Kabir E, Kabir S. A review on the human health impact of airborne particulate matter. Environment International. 2015;74:136-43.
[3] Lovinsky-Desir S, Acosta LM, Rundle AG, Miller RL, Goldstein IF, Jacobson JS, et al. Air pollution, urgent asthma medical visits and the modifying effect of neighborhood asthma prevalence. Pediatric Research. 2018.
[4] Kampa M, Castanas E. Human health effects of air pollution. Environmental Pollution. 2008;151:362-7.
[5] Pope IC, Burnett RT, Thun MJ, et al. Lung cancer, cardiopulmonary mortality, and long-term exposure to fine particulate air pollution. JAMA. 2002;287:1132-41.
[6] Piazzalunga-Expert A. Evaluation of the potential relationship between Particulate Matter (PM) pollution and COVID-19 infection spread in Italy. mimeo; 2020.
[7] Setti L, Passarini F, De Gennaro G, Barbieri P, Perrone MG, Piazzalunga A, et al. The Potential role of Particulate Matter in the Spreading of COVID-19 in Northern Italy: First Evidence-based Research Hypotheses. 2020.
[8] Decramer M, Janssens W. Chronic obstructive pulmonary disease and comorbidities. The Lancet Respiratory Medicine. 2013;1:73-83.
[9] Redelmeier DA, Bayoumi AM, Goldstein RS, Guyatt GH. Interpreting small differences in functional status: the Six Minute Walk test in chronic lung disease patients. American journal of respiratory and critical care medicine. 1997;155:1278-82.
[10] Covid C, COVID C, COVID C, Chow N, Fleming-Dutra K, Gierke R, et al. Preliminary estimates of the prevalence of selected underlying health conditions among patients with coronavirus disease 2019—United States, February 12–March 28, 2020. 2020;69:382.
[11] Akenroye AT, Wood R, Keet C. Asthma, biologics, corticosteroids, and coronavirus disease 2019. Annals of Allergy, Asthma & Immunology. 2020.
[12] Shaker MS, Oppenheimer J, Grayson M, Stukus D, Hartog N, Hsieh EWY, et al. COVID-19: Pandemic Contingency Planning for the Allergy and Immunology Clinic. The Journal of Allergy and Clinical Immunology: In Practice. 2020;8:1477-88.e5.
[13] Braman SS. The Global Burden of Asthma. Chest. 2006;130:4S-12S.
[14] Rahimi-Gorji M, Gorji TB, Gorji-Bandpy M. Details of regional particle deposition and airflow structures in a realistic model of human tracheobronchial airways: two-phase flow simulation. Computers in biology and medicine. 2016;74:1-17.
[15] Haughney J, Price D, Barnes NC, Virchow JC, Roche N, Chrystyn H. Choosing inhaler devices for people with asthma: Current knowledge and outstanding research needs. Respiratory Medicine CME. 2010;3:125-31.
[16] Pedersen SJRm. Inhalers and nebulizers: which to choose and why. 1996;90:69-77.
[17] Islam N, Cleary MJJMe, physics. Developing an efficient and reliable dry powder inhaler for pulmonary drug delivery–a review for multidisciplinary researchers. 2012;34:409-27.
[18] Friedman JHJCS, Statistics. Data Mining and Statistics: What's the connection? 1998;29:3-9.
[19] Kalogirou SA. Artificial intelligence for the modeling and control of combustion processes: a review. Progress in Energy and Combustion Science. 2003;29:515-66.
[20] Kumar K, Thakur GSMJIjoit, science c. Advanced applications of neural networks and artificial intelligence: A review. 2012;4:57.
[21] Rajasekaran S, Pai GV. Neural networks, fuzzy logic and genetic algorithm: synthesis and applications (with cd): PHI Learning Pvt. Ltd.; 2003.
[22] Pham D, Pham PJIJoMT, Manufacture. Artificial intelligence in engineering. 1999;39:937-49.
[23] Parry J, Bornoff RB, Stehouwer P, Driessen LT, Stinstra EJItoc, technologies p. Simulation-based design optimization methodologies applied to CFD. 2004;27:391-7.
[24] Ruan Q, Yang K, Wang W, Jiang L, Song J. Clinical predictors of mortality due to COVID-19 based on an analysis of data of 150 patients from Wuhan, China. Intensive Care Medicine. 2020;46:846-8.
[25] Remuzzi A, Remuzzi G. COVID-19 and Italy: what next? The Lancet. 2020;395:1225-8.
[26] L. Augusto GL, J. Goncalves. Pharmaceutical aerosols deposition during inhalation, breath holding and exhalation using CFD. Blucher Chemical Engineering Proceedings. 2015;1:5985-92.
[27] Tian G, Hindle M, Lee S, Longest PW. Validating CFD predictions of pharmaceutical aerosol deposition with in vivo data. Pharmaceutical research. 2015;32:3170-87.
[28] Longest PW, Tian G, Walenga RL, Hindle M. Comparing MDI and DPI aerosol deposition using in vitro experiments and a new stochastic individual path (SIP) model of the conducting airways. Pharmaceutical research. 2012;29:1670-88.
[29] Hofmann W. Modelling inhaled particle deposition in the human lung—A review. Journal of Aerosol Science. 2011;42:693-724.
[30] Deng Q, Ou C, Chen J, Xiang Y. Particle deposition in tracheobronchial airways of an infant, child and adult. Science of the Total Environment. 2018;612:339-46.
[31] Koullapis PG, Hofemeier P, Sznitman J, Kassinos SC. An efficient computational fluid-particle dynamics method to predict deposition in a simplified approximation of the deep lung. European Journal of Pharmaceutical Sciences. 2018;113:132-44.
[32] Chen X, Feng Y, Zhong W, Sun B, Tao F. Numerical investigation of particle deposition in a triple bifurcation airway due to gravitational sedimentation and inertial impaction. Powder Technology. 2018;323:284-93.
[33] Augusto L, Lopes G, Goncalves J. A CFD study of deposition of pharmaceutical aerosols under different respiratory conditions. Brazilian Journal of Chemical Engineering. 2016;33:549-58.
[34] Augusto L, Gonçalves J, Lopes G. CFD Evaluation of the Influence of Physical Mechanisms, Particle Size, and Breathing Condition on the Deposition of Particulates in a Triple Bifurcation Airway. Water, Air, & Soil Pollution. 2016;227:56.
[35] Shekunov BY, Chattopadhyay P, Tong HH, Chow AH. Particle size analysis in pharmaceutics: principles, methods and applications. Pharmaceutical research. 2007;24:203-27.
[36] Kleinstreuer C, Shi H, Zhang ZJJoam. Computational analyses of a pressurized metered dose inhaler and a new drug–aerosol targeting methodology. 2007;20:294-309.
[37] Zhang Z, Kleinstreuer C, Kim CS. Comparison of analytical and CFD models with regard to micron particle deposition in a human 16-generation tracheobronchial airway model. Journal of Aerosol Science. 2009;40:16-28.
[38] Kolanjiyil AV, Kleinstreuer C. Computational analysis of aerosol-dynamics in a human whole-lung airway model. Journal of Aerosol Science. 2017;114:301-16.
[39] Hou T-H, Su C-H, Liu W-LJPt. Parameters optimization of a nano-particle wet milling process using the Taguchi method, response surface method and genetic algorithm. 2007;173:153-62.
[40] Wang CJ, Ng CY, Brook RH. Response to COVID-19 in Taiwan: Big Data Analytics, New Technology, and Proactive Testing. JAMA. 2020;323:1341-2.
[41] Hetzel M, Clark T. Comparison of normal and asthmatic circadian rhythms in peak expiratory flow rate. Thorax. 1980;35:732-8.
[42] Quackenboss JJ, Lebowitz MD, Krzyzanowski M. The normal range of diurnal changes in peak expiratory flow rates. Am Rev Respir Dis. 1991;143:323-30.
[43] Mrindha MA-A, Amin MR, Kabir AL. Peak expiratory flow rate (PEFR)-A simple ventilatory lung function test. Journal of Shaheed Suhrawardy Medical College. 2011;3:44-7.
[44] Warke T, Fitch P, Brown V, Taylor R, Lyons J, Ennis M, et al. Exhaled nitric oxide correlates with airway eosinophils in childhood asthma. Thorax. 2002;57:383-7.
[45] Berry M, Shaw D, Green R, Brightling C, Wardlaw A, Pavord I. The use of exhaled nitric oxide concentration to identify eosinophilic airway inflammation: an observational study in adults with asthma. Clinical & experimental allergy. 2005;35:1175-9.
[46] Kim K-H, Jahan SA, Kabir E. A review on human health perspective of air pollution with respect to allergies and asthma. Environment International. 2013;59:41-52.
[47] Dixon WE, Brodie TGJTJop. Contributions to the physiology of the lungs: Part I. The bronchial muscles, their innervation, and the action of drugs upon them. 1903;29:97-173.
[48] Keatings VM, Jatakanon A, Worsdell YM, Barnes PJJAjor, medicine cc. Effects of inhaled and oral glucocorticoids on inflammatory indices in asthma and COPD. 1997;155:542-8.
[49] Bell T, Bigley JJP. Sustained-release theophylline therapy for chronic childhood asthma. 1978;62:352-8.
[50] Shah LS, Wilson AJ, Gibson PG, Coughlan JJJCDosr. Long‐acting beta2‐agonists versus theophylline for maintenance treatment of asthma. 2003.
[51] Watts K, Chavasse RJJCDoSR. Leukotriene receptor antagonists in addition to usual care for acute asthma in adults and children. 2012.
[52] Mash BR, Bheekie A, Jones PJCDoSR. Inhaled versus oral steroids for adults with chronic asthma. 2001.
[53] Nelson HSJNEJoM. β-Adrenergic bronchodilators. 1995;333:499-507.
[54] Barnes PJ. New drugs for asthma. Nature reviews Drug discovery. 2004;3:831.
[55] Telko MJ, Hickey AJJRc. Dry powder inhaler formulation. 2005;50:1209-27.
[56] Hillman T, Mortimer F, Hopkinson NS. Inhaled drugs and global warming: time to shift to dry powder inhalers. British Medical Journal Publishing Group; 2013.
[57] Rodrigo GJ, Rodrigo C, Hall JB. Acute Asthma in Adults: A Review. Chest. 2004;125:1081-102.
[58] Longest PW, Vinchurkar SJJob. Validating CFD predictions of respiratory aerosol deposition: effects of upstream transition and turbulence. 2007;40:305-16.
[59] Holbrook LT, Longest PWJJoas. Validating CFD predictions of highly localized aerosol deposition in airway models: In vitro data and effects of surface properties. 2013;59:6-21.
[60] Longest PW, Bass K, Dutta R, Rani V, Thomas ML, El-Achwah A, et al. Use of computational fluid dynamics deposition modeling in respiratory drug delivery. 2019;16:7-26.
[61] Zhang Z, Kleinstreuer C, Kim C. Gas–solid two-phase flow in a triple bifurcation lung airway model. International Journal of Multiphase Flow. 2002;28:1021-46.
[62] Chen W-H, Lee K-H, Mutuku JK, Hwang C-J. Flow dynamics and PM2. 5 deposition in healthy and asthmatic airways at different inhalation statuses. Aerosol and Air Quality Research. 2018;18:866-83.
[63] Farkhadnia F, Gorji TB, Gorji-Bandpy M. Airflow, transport and regional deposition of aerosol particles during chronic bronchitis of human central airways. Australasian physical & engineering sciences in medicine. 2016;39:43-58.
[64] Kim YH, Tong ZB, Chan HK, Yang RY. CFD modelling of air and particle flows in different airway models. Journal of Aerosol Science. 2019;134:14-28.
[65] Deng Q, Ou C, Shen Y-M, Xiang Y, Miao Y, Li Y. Health effects of physical activity as predicted by particle deposition in the human respiratory tract. Science of The Total Environment. 2019;657:819-26.
[66] Gharibshahi R, Jafari A, Ahmadi H. CFD investigation of enhanced extra-heavy oil recovery using metallic nanoparticles/steam injection in a micromodel with random pore distribution. Journal of Petroleum Science and Engineering. 2019;174:374-83.
[67] Khaw JFC, Lim BS, Lim LEN. Optimal design of neural networks using the Taguchi method. Neurocomputing. 1995;7:225-45.
[68] Sholahudin S, Han H. Simplified dynamic neural network model to predict heating load of a building using Taguchi method. Energy. 2016;115:1672-8.
[69] Karimifard S, Alavi Moghaddam MR. Application of response surface methodology in physicochemical removal of dyes from wastewater: A critical review. Science of The Total Environment. 2018;640-641:772-97.
[70] Mai CK, Krishna IVM, Reddy AV. Polyanalyst application for forest data mining. Proceedings 2005 IEEE International Geoscience and Remote Sensing Symposium, 2005 IGARSS'05: IEEE; 2005. p. 4 pp.
[71] Gürbüz F, Eski İ, Denizhan B, Dağlı CJJoIM. Prediction of damage parameters of a 3PL company via data mining and neural networks. 2019;30:1437-49.
[72] Gürbüz F, Özbakir L, Yapici H. Data mining and preprocessing application on component reports of an airline company in Turkey. Expert Systems with Applications. 2011;38:6618-26.
[73] Demir B, Gürbüz F, Eski I, Kus ZJAUJotAF. Data mining approach for prediction of fruit color properties. 2018;49:37-43.
[74] Asfaram A, Ghaedi M, Azqhandi MA, Goudarzi A, Dastkhoon MJRa. Statistical experimental design, least squares-support vector machine (LS-SVM) and artificial neural network (ANN) methods for modeling the facilitated adsorption of methylene blue dye. 2016;6:40502-16.
[75] Yang M, Yu D, Liu M, Zheng L, Zheng X, Wei Y, et al. Optimization of MBR hydrodynamics for cake layer fouling control through CFD simulation and RSM design. 2017;227:102-11.
[76] Chen M, Rosendahl LA, Condra T. A three-dimensional numerical model of thermoelectric generators in fluid power systems. International Journal of Heat and Mass Transfer. 2011;54:345-55.
[77] Gürbüz F, Demi̇r B, İkbal E, KUŞ ZA, YILMAZ KU, İLİKÇİOĞLU E, et al. Estimation of the weights of almond nuts based on physical properties through data mining. 2018;46:579-84.
[78] Muñoz J, Felicísimo ÁM. Comparison of statistical methods commonly used in predictive modelling. Journal of Vegetation Science. 2004;15:285-92.
[79] Chakraborty S, Jain S, Nandy A, Venture G. Pathological Gait Detection Based on Multiple Regression Models Using Unobtrusive Sensing Technology. Journal of Signal Processing Systems. 2020.
[80] Deconinck E, Xu QS, Put R, Coomans D, Massart DL, Vander Heyden Y. Prediction of gastro-intestinal absorption using multivariate adaptive regression splines. Journal of Pharmaceutical and Biomedical Analysis. 2005;39:1021-30.
[81] Badnjević A, Gurbeta L, Cifrek M, Marjanovic D. Classification of asthma using artificial neural network. 2016 39th International Convention on Information and Communication Technology, Electronics and Microelectronics (MIPRO)2016. p. 387-90.
[82] Nazir J, Barlow DJ, Lawrence MJ, Richardson CJ, Shrubb I. Artificial Neural Network Prediction of Aerosol Deposition in Human Lungs. Pharmaceutical Research. 2002;19:1130-6.
[83] Richardson CJ, Barlow DJ. Neural Network Computer Simulation of Medical Aerosols. Journal of Pharmacy and Pharmacology. 1996;48:581-91.
[84] de Matas M, Shao Q, Richardson CH, Chrystyn H. Evaluation of in vitro in vivo correlations for dry powder inhaler delivery using artificial neural networks. European Journal of Pharmaceutical Sciences. 2008;33:80-90.
[85] Abiyev RH, Ma’aitah MKSJJohe. Deep convolutional neural networks for chest diseases detection. 2018;2018.
[86] Weibel ER, Cournand AF, Richards DW. Morphometry of the human lung: Springer; 1963.
[87] Horsfield K, Dart G, Olson DE, Filley GF, Cumming G. Models of the human bronchial tree. Journal of applied physiology. 1971;31:207-17.
[88] Braun L. Race, ethnicity and lung function: A brief history. Can J Respir Ther. 2015;51:99-101.
[89] Moulton DE, Goriely A. Possible role of differential growth in airway wall remodeling in asthma. Journal of applied physiology. 2011;110:1003-12.
[90] Lambert R, Codd S, Alley M, Pack RJJoAP. Physical determinants of bronchial mucosal folding. 1994;77:1206-16.
[91] Wiggs BR, Hrousis CA, Drazen JM, Kamm RD. On the mechanism of mucosal folding in normal and asthmatic airways. Journal of Applied Physiology. 1997;83:1814-21.
[92] Donovan GM, Tawhai MH. A simplified model of airway narrowing due to bronchial mucosal folding. Respiratory physiology & neurobiology. 2010;171:144-50.
[93] Hofmann W, Balásházy I, Koblinger L. The effect of gravity on particle deposition patterns in bronchial airway bifurcations. Journal of Aerosol Science. 1995;26:1161-8.
[94] Johnson PC, Jackson R. Frictional–collisional constitutive relations for granular materials, with application to plane shearing. Journal of fluid Mechanics. 1987;176:67-93.
[95] Miao Z, Kuang S, Zughbi H, Yu A. CFD simulation of dilute-phase pneumatic conveying of powders. Powder Technology. 2019;349:70-83.
[96] Morsi S, Alexander A. An investigation of particle trajectories in two-phase flow systems. Journal of Fluid Mechanics. 1972;55:193-208.
[97] Fenn W, Rahn H. HANDBOOK PHYSIOLOGY SECTION 3-RESPIRATION. AMER COLL PHYSICIANS INDEPENDENCE MALL WEST 6TH AND RACE ST, PHILADELPHIA …; 1965.
[98] Tena A, Francos J, Álvarez E, Casan P. A three dimensional in SILICO model for the simulation of inspiratory and expiratory airflow in humans. Engineering Applications of Computational Fluid Mechanics. 2015;9:187-98.
[99] Zhang Z, Kleinstreuer C, Kim CS. Gas–solid two-phase flow in a triple bifurcation lung airway model. International Journal of Multiphase Flow. 2002;28:1021-46.
[100] Zanen P, Go LT, Lammers JW. Optimal particle size for beta 2 agonist and anticholinergic aerosols in patients with severe airflow obstruction. Thorax. 1996;51:977.
[101] Pilcer G, Amighi K. Formulation strategy and use of excipients in pulmonary drug delivery. International Journal of Pharmaceutics. 2010;392:1-19.
[102] DeCarlo PF, Slowik JG, Worsnop DR, Davidovits P, Jimenez JL. Particle morphology and density characterization by combined mobility and aerodynamic diameter measurements. Part 1: Theory. Aerosol Science and Technology. 2004;38:1185-205.
[103] Zhang Z, Kleinstreuer C. Effect of Particle Inlet Distributions on Deposition in a Triple Bifurcation Lung Airway Model. Journal of Aerosol Medicine. 2001;14:13-29.
[104] Van Ertbruggen C, Hirsch C, Paiva M. Anatomically based three-dimensional model of airways to simulate flow and particle transport using computational fluid dynamics. Journal of applied physiology. 2005;98:970-80.
[105] Kleinstreuer C, Zhang Z. An adjustable triple-bifurcation unit model for air-particle flow simulations in human tracheobronchial airways. Journal of biomechanical engineering. 2009;131.
[106] Comer J, Kleinstreuer C, Kim CJJoFM. Flow structures and particle deposition patterns in double-bifurcation airway models. Part 2. Aerosol transport and deposition. 2001;435:55.
[107] Rahimi-Gorji M, Pourmehran O, Gorji-Bandpy M, Gorji TB. CFD simulation of airflow behavior and particle transport and deposition in different breathing conditions through the realistic model of human airways. Journal of Molecular Liquids. 2015;209:121-33.
[108] Zhang Z, Kleinstreuer C, Kim CJJFE. Flow structure and particle transport in a triple bifurcation airway model. 2001;123:320-30.
[109] Taguchi G. Introduction to quality engineering: designing quality into products and processes. 1986.
[110] Chen W-H, Chen C-J, Hung C-I. Taguchi approach for co-gasification optimization of torrefied biomass and coal. Bioresource Technology. 2013;144:615-22.
[111] Chen W-H, Huang S-R, Lin Y-LJAE. Performance analysis and optimum operation of a thermoelectric generator by Taguchi method. 2015;158:44-54.
[112] Hill WJ, Hunter WGJT. A review of response surface methodology: a literature survey. 1966;8:571-90.
[113] Box GE, Behnken DWJT. Some new three level designs for the study of quantitative variables. 1960;2:455-75.
[114] Emami J, Hamishehkar H, Najafabadi AR, Gilani K, Minaiyan M, Mahdavi H, et al. Particle size design of PLGA microspheres for potential pulmonary drug delivery using response surface methodology. 2009;26:1-8.
[115] Gunaraj V, Murugan N. Application of response surface methodology for predicting weld bead quality in submerged arc welding of pipes. Journal of Materials Processing Technology. 1999;88:266-75.
[116] Aslan N, Cebeci Y. Application of Box–Behnken design and response surface methodology for modeling of some Turkish coals. Fuel. 2007;86:90-7.
[117] Kiselev MV. PolyAnalyst-A Machine Discovery System Inferring Functional Programs. KDD Workshop1994. p. 237-50.
[118] Kiselev MV, Ananyan SM, Arseniev SB. PolyAnalyst data analysis technique. Proceedings of Conference on Principles of Data Mining and Knowledge Discovery Lecture Notes in Computer Science1998.
[119] Friedman JHJTaos. Multivariate adaptive regression splines. 1991:1-67.
[120] McCulloch WS, Pitts WJTbomb. A logical calculus of the ideas immanent in nervous activity. 1943;5:115-33.
[121] Rumelhart DE, Hinton GE, Williams RJJn. Learning representations by back-propagating errors. 1986;323:533-6.
[122] Fahlman SE. An empirical study of learning speed in back-propagation networks: Carnegie Mellon University, Computer Science Department; 1988.
[123] Riedmiller M, Braun H. Rprop: A fast adaptive learning algorithm.
[124] Igel C, Hüsken M. Improving the Rprop learning algorithm. Proceedings of the second international ICSC symposium on neural computation (NC 2000): Citeseer; 2000. p. 115-21.
[125] Riedmiller M, Braun H. A direct adaptive method for faster backpropagation learning: The RPROP algorithm. IEEE international conference on neural networks: IEEE; 1993. p. 586-91.
[126] Han J, Moraga C. The influence of the sigmoid function parameters on the speed of backpropagation learning. International Workshop on Artificial Neural Networks: Springer; 1995. p. 195-201.
[127] Rawat W, Wang ZJNc. Deep convolutional neural networks for image classification: A comprehensive review. 2017;29:2352-449.
[128] LeCun Y, Bengio Y, Hinton GJn. Deep learning. 2015;521:436-44.
[129] Piglione MC, Fontana D, Vanni M. Simulation of particle deposition in human central airways. European Journal of Mechanics - B/Fluids. 2012;31:91-101.
[130] Li Z, Kleinstreuer C, Zhang Z. Simulation of airflow fields and microparticle deposition in realistic human lung airway models. Part I: Airflow patterns. European Journal of Mechanics - B/Fluids. 2007;26:632-49.
[131] Isabey D, Chang H. A model study of flow dynamics in human central airways. Part II: Secondary flow velocities. Respiration physiology. 1982;49:97-113.
[132] Inthavong K, Tu J, Ye Y, Ding S, Subic A, Thien F. Effects of airway obstruction induced by asthma attack on particle deposition. Journal of Aerosol Science. 2010;41:587-601.
[133] Cheng YS. Mechanisms of pharmaceutical aerosol deposition in the respiratory tract. AAPS PharmSciTech. 2014;15:630-40.
[134] Kim Y, Tong Z, Chan H, Yang R. CFD modelling of air and particle flows in different airway models. Journal of Aerosol Science. 2019;134:14-28.
[135] Xu P, Sasmito AP, Li C, Qiu S. Global and local transport properties of steady and unsteady flow in a symmetrical bronchial tree. International Journal of Heat and Mass Transfer. 2016;97:696-704.
[136] Farkas Á, Balásházy I. Simulation of the effect of local obstructions and blockage on airflow and aerosol deposition in central human airways. Journal of Aerosol Science. 2007;38:865-84.
[137] Yu IT, Li Y, Wong TW, Tam W, Chan AT, Lee JH, et al. Evidence of airborne transmission of the severe acute respiratory syndrome virus. New England Journal of Medicine. 2004;350:1731-9.
[138] Adhikari U, Chabrelie A, Weir M, Boehnke K, McKenzie E, Ikner L, et al. A Case Study Evaluating the Risk of Infection from Middle Eastern Respiratory Syndrome Coronavirus (MERS‐CoV) in a Hospital Setting Through Bioaerosols. Risk Analysis. 2019;39:2608-24.
[139] Zhang H, Li X, Ma R, Li X, Zhou Y, Dong H, et al. Airborne spread and infection of a novel swine-origin influenza A (H1N1) virus. Virology journal. 2013;10:204.
[140] Kulkarni H, Smith CM, Lee DDH, Hirst RA, Easton AJ, O’Callaghan C. Evidence of respiratory syncytial virus spread by aerosol. Time to revisit infection control strategies? American journal of respiratory and critical care medicine. 2016;194:308-16.
[141] Wang J, Du G. COVID-19 may transmit through aerosol. Irish Journal of Medical Science (1971 -). 2020.
[142] Shereen MA, Khan S, Kazmi A, Bashir N, Siddique R. COVID-19 infection: Origin, transmission, and characteristics of human coronaviruses. Journal of Advanced Research. 2020;24:91-8.
[143] Velavan TP, Meyer CG. The COVID-19 epidemic. Trop Med Int Health. 2020;25:278-80.
[144] Howarth PJJoAM. Why particle size should affect clinical response to inhaled therapy. 2001;14:27-34.
[145] Carvalho TC, Peters JI, Williams III ROJIjop. Influence of particle size on regional lung deposition–what evidence is there? 2011;406:1-10.
[146] Dolovich MAJRc. Influence of inspiratory flow rate, particle size, and airway caliber on aerosolized drug delivery to the lung. 2000;45:597-608.
[147] Li Z, Kleinstreuer C, Zhang Z. Particle deposition in the human tracheobronchial airways due to transient inspiratory flow patterns. Journal of Aerosol Science. 2007;38:625-44.
[148] Muddle J, Kirton SB, Parisini I, Muddle A, Murnane D, Ali J, et al. Predicting the Fine Particle Fraction of Dry Powder Inhalers Using Artificial Neural Networks. Journal of Pharmaceutical Sciences. 2017;106:313-21.
[149] Eppinger T, Wehinger G, Kraume MJCER, Design. Parameter optimization for the oxidative coupling of methane in a fixed bed reactor by combination of response surface methodology and computational fluid dynamics. 2014;92:1693-703.
[150] Crino S, Brown DE. Global Optimization With Multivariate Adaptive Regression Splines. IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics). 2007;37:333-40.
[151] Brasier AR, Ju H. Analysis and Predictive Modeling of Asthma Phenotypes. In: Brasier AR, editor. Heterogeneity in Asthma. Boston, MA: Springer US; 2014. p. 273-88.
[152] Chou S-M, Lee T-S, Shao YE, Chen IF. Mining the breast cancer pattern using artificial neural networks and multivariate adaptive regression splines. Expert Systems with Applications. 2004;27:133-42.
[153] Nazir J, Barlow DJ, Jayne Lawrence M, Shrubb I. Artificial Neural Network Prediction of the Patterns of Deposition of Polydisperse Aerosols Within Human Lungs. Journal of Pharmaceutical Sciences. 2005;94:1986-97.
[154] Sun W, Tseng T-L, Zhang J, Qian W. Enhancing deep convolutional neural network scheme for breast cancer diagnosis with unlabeled data. Computerized Medical Imaging and Graphics. 2017;57:4-9.
[155] Kikidis D, Votis K, Tzovaras D. Utilizing convolution neural networks for the acoustic detection of inhaler actuations. 2015 E-Health and Bioengineering Conference (EHB)2015. p. 1-4.
[156] Usmani OS, Biddiscombe MF, Nightingale JA, Underwood SR, Barnes PJJJoAP. Effects of bronchodilator particle size in asthmatic patients using monodisperse aerosols. 2003;95:2106-12.
[157] Takayama K, Fujikawa M, Nagai T. Artificial Neural Network as a Novel Method to Optimize Pharmaceutical Formulations. Pharmaceutical Research. 1999;16:1-6.
[158] Apostolopoulos ID, Mpesiana TAJP, Medicine ESi. Covid-19: automatic detection from x-ray images utilizing transfer learning with convolutional neural networks. 2020:1.
[159] Li L, Qin L, Xu Z, Yin Y, Wang X, Kong B, et al. Artificial Intelligence Distinguishes COVID-19 from Community Acquired Pneumonia on Chest CT. Radiology.0:200905.
[160] Shi F, Wang J, Shi J, Wu Z, Wang Q, Tang Z, et al. Review of Artificial Intelligence Techniques in Imaging Data Acquisition, Segmentation and Diagnosis for COVID-19. IEEE Reviews in Biomedical Engineering. 2020:1-.