氣霧治療是藥物透過霧化器或吸入器產生藥物氣溶膠並運送至呼吸道作治療，需要藉由氣霧治療來恢復呼吸道功能的常見呼吸道疾病包含慢性肺阻塞、肺炎及哮喘。然而，霧化器或吸入器在目前臨床上有著較低的給藥效率、不穩定的接收劑量及護理人員接觸二手氣溶膠的問題。此外，患者在接受氣霧治療時，需要在醫院定期做肺活量測定，肺活量測定中的強制呼氣動作會危害原先患有心血管疾病的患者，且測量的儀器複雜、過程耗時，需要專業人員的協助操作。
於是在本篇研究中，我們開發了氣溶膠給藥系統和鼻氣音檢測系統。在氣溶膠給藥系統中，我們設計了校準演算法藉由聲音感測器來計算吸氣和吐氣時間，並設計了觸發演算法來控制霧化器在使用者吸氣時給藥。在氣溶膠給藥效率測量實驗中，in-vitro給藥效率為94.52%(SD=2.59)，ex-vivo給藥效率為88.75%(SD=2.95)，效率為傳統連續霧化藥物的2到4倍。根據in-vitro生物驗證，相較於連續霧化藥物，使用氣溶膠給藥系統遞送高劑量藥物能夠達到更好的抗菌效果，可應用於優化抗生素治療系統。在氣溶膠品質分析中，我們發現通過雙頻疊加作為網孔型霧化器的驅動頻率可以調整氣溶膠的粒徑大小，可應用於藥物氣溶膠更精準地沉降在欲治療的呼吸道位置。在鼻氣音檢測系統中，我們透過聲音感測器收集呼吸模擬器出口的風切聲作為呼吸氣音的特徵，比較兩種不同的資料前處理，包含梅爾倒頻譜係數轉換(MFCC)和短時距傅立葉轉換(STFT)，及三種分類模型，包含卷積神經網路(CNN)、卷積長短期記憶(ConvLSTM)及支持向量機(SVM)。對正常、輕度慢性肺阻塞、嚴重慢性肺阻塞、間質性肺病和哮喘五種肺部情形下的鼻氣音進行分類，根據分類的結果，ConvLSTM模型分類準確度達 0.96。實驗結果驗證了我們的鼻氣音檢測系統有著快速、準確、收錄過程簡單、使用者自然呼吸等好處，可應用於長期居家氣霧治療的呼吸監測。
綜合上述，我們設計了一套氣溶膠給藥系統，可提高霧化器的給藥效率和減少二手氣溶膠的暴露，並改變藥物氣溶膠的輸出粒徑大小，使藥物氣溶膠更精準地沉降在欲治療部位。另外，我們設計的鼻氣音檢測系統可用來檢測異常的呼吸情況，期望能夠透過時刻監測病人的呼吸道情況，作為醫務人員在評估病人呼吸道恢復狀態的時參考，以改善評估氣霧治療功效的過程。

Aerosol therapy is the inhalation treatment through a nebulizer or inhaler generating drug aerosols and delivering them to the respiratory tract for the treatment of respiratory diseases such as chronic obstructive pulmonary disease, pneumonia and asthma. However, the existing nebulizers or inhalers show disadvantages of low drug delivery efficiency, inconsistent drug dosage, and secondhand aerosol exposure to care helpers. In addition, patients using aerosol therapy need to use spirometry regularly to evaluate their pulmonary function. The forced exhalation action when using spirometry will threaten cardiovascular disease patients. The spirometer is a complex instrument requiring the assistance of professionals, and the entire process is time-consuming.
In this study, we developed an aerosol drug delivery system and nasal sound detection system. In the aerosol drug delivery system, we designed a calibration algorithm to calculate inspiratory and expiratory time through a sound sensor and a triggering algorithm to control the nebulizer action to release aerosols when the patient is inhaling. Drug delivery efficiency is 94.52%(SD=2.59) in vitro and 88.75%(SD=2.95) ex vivo. The efficiencies of triggered nebulization are two to four times more than the traditional continuous nebulization. According to in-vitro bio-validation, high drug dose delivery through this system achieves a better antibacterial effect, which can be utilized for optimization of the antibiotic treatment method. In aerosol quality analysis, we found that the particle size can be adjusted by using dual frequency superposition as the driving frequency of the mesh nebulizer, which can be applied for precision drug delivery to control the depth of aerosol deposition. In nasal sound detection system, we collected the flow sound of breathing simulator through a sound sensor as breathing pattern. We compare two data pre-processing techniques, including Mel-scale frequency cepstral coefficient (MFCC) and short-time Fourier transform (STFT), and three classification method, including convolutional neural network (CNN), convolutional long short-term memory (ConvLSTM) and support vector machine (SVM). The models are used to classify nasal sound into five lung conditions including Normal, COPD-mild, COPD-severe, ILD and Asthma. From our classification results, we achieved an accuracy of up to 0.96. The experimental results verify that our nasal sound detection system shows the advantages of fast, accurate, and simple recording process, of the user's general breathing. The system can be applied for respiratory monitoring of aerosol therapy at home.
In conclusion, we provide an aerosol drug delivery system, which can improve the drug delivery efficiency of nebulizer, reduce second-hand aerosol exposure, and change the output aerosol size for precise drug deposition in the desired treatment location for therapy. In addition, we provide a nasal sound detection system which can detect abnormal respiratory conditions. It is expected that the process of evaluating the efficacy of aerosol therapy can be improved upon by providing the patient’s status to the healthcare professionals through constant monitoring of the patient’s respiratory conditions.

摘要 ii
Abstract iv
目錄 vii
圖目錄 ix
表目錄 xi
第一章 緒論 1
1.1 研究動機 1
1.2 呼吸治療 2
1.2.1 呼吸道相關疾病 2
1.2.2 氣霧治療 2
1.2.3 霧化器種類與運作原理 2
1.2.4 霧化器給藥效率不佳 4
1.2.5 二手氣溶膠藥害 5
1.2.6 氣溶膠沉積 5
1.3 呼吸診斷 6
1.3.1 慢性阻塞性肺病與測量困境 6
1.3.2 呼吸特徵 7
1.3.3 機器學習應用於呼吸疾病辨識 8
1.4 研究架構 9
第二章 實驗方法與材料 11
2.1 氣溶膠給藥系統 11
2.1.1 氣溶膠給藥系統硬體架構 11
2.1.2 氣溶膠給藥系統軟體架構 11
2.1.3 遞送效率之量測 14
2.1.4 In-vitro 生物驗證 18
2.1.5 In-vitro 生物驗證實驗之硬體架設 18
2.1.6 氣溶膠粒徑大小之量測 19
2.2 鼻氣音檢測系統 20
2.2.1 鼻氣音分類器資料處理流程 20
2.2.2 呼吸數據的收集 21
2.2.3 資料前處理 21
2.2.4 分類器: 卷積神經網路(Convolutional Neural Networks) 23
2.2.5 分類器: 長短期記憶(Long Short-Term Memory, LSTM) 26
2.2.6 分類器: 支持向量機(Support Vector Machine, SVM) 28
2.2.7 模型評估 29
2.3 資料擴增實驗 29
2.3.1 不平衡資料集(Unbalanced data) 30
2.3.2 生成對抗網絡(Generative Adversarial Networks) 30
2.3.3 DCGAN 30
2.3.4 DCGAN 資料處理流程 31
2.3.5 模型架構 32
2.4 實驗統計數據 34
2.5 實驗藥品與儀器 35
第三章 結果與討論 36
3.1 氣溶膠給藥系統 36
3.1.1 In-vitro給藥效率量測實驗 36
3.1.2 Ex-vivo給藥效率量測實驗 43
3.1.3 In-vitro 生物驗證 46
3.1.4 氣溶膠粒徑測量實驗 48
3.1.5 雙頻疊加的頻率調整影響氣溶膠粒徑 50
3.2 鼻氣音檢測系統 55
3.3 資料擴增實驗 60
3.3.1 MFCC-DCGAN 60
3.3.2 Image-DCGAN 62
第四章 結論 68
參考文獻 70
附錄 80

[1] " WHO Global Health Estimates," 2020.
[2] A. Ari, J. B. Fink, and S. P. Pilbeam, "Secondhand aerosol exposure during mechanical ventilation with and without expiratory filters: An in-vitro study," 2016.
[3] D. Price and G. Brusselle, "Challenges of COPD diagnosis," Expert Opinion on Medical Diagnostics, vol. 7, no. 6, pp. 543-556, 2013/11/01 2013.
[4] J. B. Scott and R. J. R. C. Kaur, "Monitoring breathing frequency, pattern, and effort," vol. 65, no. 6, pp. 793-806, 2020.
[5] Sheffield, "The Global Impact of Respiratory Disease – Second Edition.," European Respiratory Society2017.
[6] B. J. LIPWORTH, "Pharmacokinetics of inhaled drugs," vol. 42, no. 6, pp. 697-705, 1996.
[7] M. Lazaridis and I. Colbeck, "Introduction," in Aerosol Science, 2013, pp. 1-14.
[8] M. B. Dolovich and R. J. T. L. Dhand, "Aerosol drug delivery: developments in device design and clinical use," vol. 377, no. 9770, pp. 1032-1045, 2011.
[9] D. S. Gardenhire, D. Burnett, S. Strickland, and T. J. A. A. f. R. C. I. Myers, TX, USA, "Aerosol Delivery Devices for Respiratory Therapists," vol. 61, 2017.
[10] B. L. Laube et al., "What the pulmonary specialist should know about the new inhalation therapies," ed: Eur Respiratory Soc, 2011.
[11] L. Y. Yeo, J. R. Friend, M. P. McIntosh, E. N. Meeusen, and D. A. J. E. o. o. d. d. Morton, "Ultrasonic nebulization platforms for pulmonary drug delivery," vol. 7, no. 6, pp. 663-679, 2010.
[12] R. J. R. c. Dhand, "New frontiers in aerosol delivery during mechanical ventilation," vol. 49, no. 6, p. 667, 2004.
[13] R. J. R. c. Dhand, "Nebulizers that use a vibrating mesh or plate with multiple apertures to generate aerosol," vol. 47, no. 12, pp. 1406-16; discussion 1416, 2002.
[14] B. L. Laube et al., "What the pulmonary specialist should know about the new inhalation therapies," vol. 37, no. 6, pp. 1308-1417, 2011.
[15] R. L. Chatburn and M. J. R. c. McPeck, "A new system for understanding nebulizer performance," vol. 52, no. 8, pp. 1037-1050, 2007.
[16] C. Harvey, M. O'Doherty, C. Page, S. Thomas, T. Nunan, and D. J. E. R. J. Treacher, "Comparison of jet and ultrasonic nebulizer pulmonary aerosol deposition during mechanical ventilation," vol. 10, no. 4, pp. 905-909, 1997.
[17] W. Stahlhofen, J. Gebhart, and J. J. A. I. H. A. J. Heyder, "Experimental determination of the regional deposition of aerosol particles in the human respiratory tract," vol. 41, no. 6, pp. 385-398a, 1980.
[18] S. Erzinger, K. G. Schueepp, J. Brooks-Wildhaber, S. G. Devadason, and J. H. J. J. o. A. M. Wildhaber, "Facemasks and aerosol delivery in vivo," vol. 20, no. s1, pp. S78-S84, 2007.
[19] H.-L. Lin, R. D. Restrepo, D. S. Gardenhire, and J. L. Rau, "Effect of Face Mask Design on Inhaled Mass of Nebulized Albuterol, Using a Pediatric Breathing Model," vol. 52, no. 8, pp. 1021-1026, 2007.
[20] K. Nikander, E. Berg, and G. C. J. J. o. a. m. Smaldone, "Jet nebulizers versus pressurized metered dose inhalers with valved holding chambers: effects of the facemask on aerosol delivery," vol. 20, no. s1, pp. S46-S58, 2007.
[21] A.-M. Häkkinen, H. Uusi-Heikkilä, M. Järvinen, K. Saali, and L. J. C. p. Karhumäki, "The effect of breathing frequency on deposition of drug aerosol using an inhalation-synchronized dosimeter in healthy adults," vol. 19, no. 3, pp. 269-274, 1999.
[22] T. B. Martonen and I. M. J. P. r. Katz, "Deposition patterns of aerosolized drugs within human lungs: effects of ventilatory parameters," vol. 10, no. 6, pp. 871-878, 1993.
[23] S. P. Newman, G. Woodman, and S. W. Clarke, "Deposition of carbenicillin aerosols in cystic fibrosis: effects of nebuliser system and breathing pattern," vol. 43, no. 4, pp. 318-322, 1988.
[24] P. A. Valberg, J. D. Brain, S. L. Sneddon, and S. R. J. J. o. a. p. LeMott, "Breathing patterns influence aerosol deposition sites in excised dog lungs," vol. 53, no. 4, pp. 824-837, 1982.
[25] J. L. Rau, A. Ari, and R. D. J. R. C. Restrepo, "Performance comparison of nebulizer designs: constant-output, breath-enhanced, and dosimetric," vol. 49, no. 2, pp. 174-179, 2004.
[26] D. M. Newnham and B. J. Lipworth, "Nebuliser performance, pharmacokinetics, airways and systemic effects of salbutamol given via a novel nebuliser delivery system ("Ventstream")," (in eng), Thorax, vol. 49, no. 8, pp. 762-70, Aug 1994.
[27] M. J. O’Doherty, S. H. Thomas, C. J. Page, D. Treacher, and T. J. A. R. R. D. Nunan, "Delivery of a nebulized aerosol to a lung model during mechanical ventilation," vol. 146, no. 2, pp. 383-388, 1992.
[28] P. Barry and C. J. E. R. J. O'Callaghan, "An in vitro analysis of the output of salbutamol from different nebulizers," vol. 13, no. 5, pp. 1164-1169, 1999.
[29] D. Hess, D. Fisher, P. Williams, S. Pooler, and R. M. Kacmarek, "Medication Nebulizer Performance: Effects Of Diluent Volume, Nebulizer Flow, and Nebulizer Brand," Chest, vol. 110, no. 2, pp. 498-505, 1996/08/01/ 1996.
[30] W. Finlay, K. Stapleton, and P. J. J. o. a. m. Zuberbuhler, "Variations in predicted regional lung deposition of salbutamol sulphate between 19 nebulizer types," vol. 11, no. 2, pp. 65-80, 1998.
[31] H. Fuller, M. Dolovich, G. Posmituck, W. Wong Pack, and M. J. A. R. R. D. Newhouse, "Pressurized aerosol versus jet aerosol delivery to mechanically ventilated patients," vol. 141, no. 2, pp. 440-444, 1990.
[32] C. Harvey, M. O'Doherty, C. Page, S. Thomas, T. Nunan, and D. J. T. Treacher, "Effect of a spacer on pulmonary aerosol deposition from a jet nebuliser during mechanical ventilation," vol. 50, no. 1, pp. 50-53, 1995.
[33] N. R. MacIntyre, R. M. Silver, C. W. Miller, F. Schuler, and R. E. J. C. c. m. Coleman, "Aerosol delivery in intubated, mechanically ventilated patients," vol. 13, no. 2, pp. 81-84, 1985.
[34] M. O'Doherty and S. J. T. Thomas, "Nebuliser therapy in the intensive care unit," vol. 52, no. Suppl 2, p. S56, 1997.
[35] V. Ravichandiran, K. Masilamani, S. Satheshkumar, and D. J. I. J. P. S. R. R. Joseprakash, "Drug delivery to the lungs," vol. 10, pp. 85-89, 2011.
[36] H. J. R. m. Chrystyn, "Is inhalation rate important for a dry powder inhaler? Using the In-Check Dial to identify these rates," vol. 97, no. 2, pp. 181-187, 2003.
[37] R. Melchor, M. F. Biddiscombe, V. H. Mak, M. D. Short, and S. G. Spiro, "Lung deposition patterns of directly labelled salbutamol in normal subjects and in patients with reversible airflow obstruction," vol. 48, no. 5, pp. 506-511, 1993.
[38] "In Vitro Comparison of Five Nebulizers During Noninvasive Ventilation: Analysis of Inhaled and Lost Doses," vol. 27, no. 6, pp. 430-440, 2014.
[39] G. L. Delclos et al., "Occupational risk factors and asthma among health care professionals," (in eng), Am J Respir Crit Care Med, vol. 175, no. 7, pp. 667-75, Apr 1 2007.
[40] C. E. Mapp, P. Boschetto, P. Maestrelli, L. M. J. A. j. o. r. Fabbri, and c. c. medicine, "Occupational asthma," vol. 172, no. 3, pp. 280-305, 2005.
[41] H. Dimich-Ward, M. L. Wymer, and M. J. C. Chan-Yeung, "Respiratory health survey of respiratory therapists," vol. 126, no. 4, pp. 1048-1053, 2004.
[42] D. G. Kern and H. J. A. o. I. M. Frumkin, "Asthma in respiratory therapists," vol. 110, no. 10, pp. 767-773, 1989.
[43] B. Carnathan, B. Martin, and G. J. R. C. Colice, "Second hand (S)-albuterol: RT exposure risk following racemic albuterol," vol. 46, no. 10, p. 1084, 2001.
[44] A. Ari, J. Fink, and S. Pilbeam, "Secondhand aerosol exposure during mechanical ventilation with and without expiratory filters: An in-vitro study," Indian Journal of Respiratory Care, vol. 5, pp. 677-683, 01/01 2016.
[45] A. Fernández Tena and P. Casan Clarà, "Deposition of Inhaled Particles in the Lungs," Archivos de Bronconeumología (English Edition), vol. 48, no. 7, pp. 240-246, 2012/07/01/ 2012.
[46] M. B. Dolovich and R. Dhand, "Aerosol drug delivery: developments in device design and clinical use," (in eng), Lancet, vol. 377, no. 9770, pp. 1032-45, Mar 19 2011.
[47] R. V. Lourenço and E. J. A. o. i. m. Cotromanes, "Clinical aerosols: I. Characterization of aerosols and their diagnostic uses," vol. 142, no. 12, pp. 2163-2172, 1982.
[48] "Pocket guide to COPD diagnosis, management, and prevention," 2020.
[49] D. Singh et al., "Global strategy for the diagnosis, management, and prevention of chronic obstructive lung disease: the GOLD science committee report 2019," European Respiratory Journal, vol. 53, no. 5, 2019.
[50] M. R. Miller et al., "General considerations for lung function testing," (in English), European Respiratory Journal, vol. 26, no. 1, pp. 153-161, Jul 2005.
[51] M. A. Cretikos, R. Bellomo, K. Hillman, J. Chen, S. Finfer, and A. J. M. J. o. A. Flabouris, "Respiratory rate: the neglected vital sign," vol. 188, no. 11, pp. 657-659, 2008.
[52] G. Yuan, N. A. Drost, and R. A. J. M. U. M. J. McIvor, "Respiratory rate and breathing pattern," vol. 10, no. 1, pp. 23-25, 2013.
[53] E. Bijaoui, S. A. Tuck, J. E. Remmers, and J. H. J. J. o. A. P. Bates, "Estimating respiratory mechanics in the presence of flow limitation," vol. 86, no. 1, pp. 418-426, 1999.
[54] D. Papandrinopoulou, V. Tzouda, and G. J. P. m. Tsoukalas, "Lung compliance and chronic obstructive pulmonary disease," vol. 2012, 2012.
[55] F. Demir, A. Sengur, V. J. H. i. s. Bajaj, and systems, "Convolutional neural networks based efficient approach for classification of lung diseases," vol. 8, no. 1, pp. 1-8, 2020.
[56] P. Bright, M. R. Miller, J. A. Franklyn, M. C. J. A. j. o. r. Sheppard, and c. c. medicine, "The use of a neural network to detect upper airway obstruction caused by goiter," vol. 157, no. 6, pp. 1885-1891, 1998.
[57] J. Räsänen, M. A. J. J. o. C. M. León, and Computing, "Detection of lung injury with conventional and neural network-based analysis of continuous data," vol. 14, no. 6, pp. 433-440, 1998.
[58] D. Perna, "Convolutional Neural Networks Learning from Respiratory data," in 2018 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2018, pp. 2109-2113.
[59] L. Liu, W. Li, and C. Jiang, "Breath Sounds Recognition and Classification for Respiration System Diseases," in ICC 2019 - 2019 IEEE International Conference on Communications (ICC), 2019, pp. 1-6.
[60] J. Acharya and A. Basu, "Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning," (in eng), IEEE Trans Biomed Circuits Syst, vol. 14, no. 3, pp. 535-544, Jun 2020.
[61] G. Chambres, P. Hanna, and M. Desainte-Catherine, "Automatic Detection of Patient with Respiratory Diseases Using Lung Sound Analysis," in 2018 International Conference on Content-Based Multimedia Indexing (CBMI), 2018, pp. 1-6.
[62] D. Chamberlain, R. Kodgule, D. Ganelin, V. Miglani, and R. R. Fletcher, "Application of semi-supervised deep learning to lung sound analysis," in 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2016, pp. 804-807.
[63] M. A. Islam, I. Bandyopadhyaya, P. Bhattacharyya, G. J. C. m. Saha, and p. i. biomedicine, "Multichannel lung sound analysis for asthma detection," vol. 159, pp. 111-123, 2018.
[64] G. Serbes, S. Ulukaya, and Y. P. Kahya, "An automated lung sound preprocessing and classification system based onspectral analysis methods," in International Conference on Biomedical and Health Informatics, 2017, pp. 45-49: Springer.
[65] E. Messner et al., "Multi-channel lung sound classification with convolutional recurrent neural networks," vol. 122, p. 103831, 2020.
[66] E. Seren, "Frequency Spectra of Normal Expiratory Nasal Sound," vol. 19, no. 3, pp. 257-261, 2005.
[67] C.-E. Luyt et al., "Pharmacokinetics and lung delivery of PDDS-aerosolized amikacin (NKTR-061) in intubated and mechanically ventilated patients with nosocomial pneumonia," Critical Care, vol. 13, no. 6, p. R200, 2009/12/10 2009.
[68] S.-H. Moon, K. H. Chang, H. M. Park, B. J. Park, S. K. Yoo, and K. C. Nam, "Effects of Driving Frequency and Voltage on the Performances of Vibrating Mesh Nebulizers," vol. 11, no. 3, p. 1296, 2021.
[69] S. Böck, F. Krebs, and M. Schedl, "Evaluating the Online Capabilities of Onset Detection Methods," in ISMIR, 2012, pp. 49-54: Citeseer.
[70] B. McFee et al., "librosa: Audio and music signal analysis in python," in Proceedings of the 14th python in science conference, 2015, vol. 8, pp. 18-25: Citeseer.
[71] A. R. Martin, I. M. Katz, K. Jenöfi, G. Caillibotte, L. Brochard, and J. Texereau, "Bench experiments comparing simulated inspiratory effort when breathing helium-oxygen mixtures to that during positive pressure support with air," (in eng), BMC pulmonary medicine, vol. 12, pp. 62-62, 2012.
[72] J.-M. Arnal et al., "Feasibility study on full closed-loop control ventilation (IntelliVent-ASV™) in ICU patients with acute respiratory failure: a prospective observational comparative study," Critical Care, vol. 17, no. 5, p. R196, 2013/09/11 2013.
[73] A. J. Woolcock and J. Read, "The static elastic properties of the lungs in asthma," (in eng), Am Rev Respir Dis, vol. 98, no. 5, pp. 788-94, Nov 1968.
[74] D. E. O'Donnell, R. Sanii, N. R. Anthonisen, and M. Younes, "Expiratory resistive loading in patients with severe chronic air-flow limitation. An evaluation of ventilatory mechanics and compensatory responses," (in eng), Am Rev Respir Dis, vol. 136, no. 1, pp. 102-7, Jul 1987.
[75] A. Ari, O. T. Atalay, R. Harwood, M. M. Sheard, E. A. Aljamhan, and J. B. Fink, "Influence of Nebulizer Type, Position, and Bias Flow on Aerosol Drug Delivery in Simulated Pediatric and Adult Lung Models During Mechanical Ventilation," Respiratory Care, vol. 55, no. 7, p. 845, 2010.
[76] X. Song, J. Hu, S. Zhan, R. Zhang, and W. J. A. P. Tan, "Effects of temperature and humidity on laser diffraction measurements to jet nebulizer and comparison with NGI," vol. 17, no. 2, pp. 380-388, 2016.
[77] J. J. A. n. c. i. i. t. B. M. Pritchard, "Particle growth in the airways and the influence of airflow," pp. 3-24, 1987.
[78] B. Logan, "Mel frequency cepstral coefficients for music modeling," in In International Symposium on Music Information Retrieval, 2000: Citeseer.
[79] E. Sejdić, I. Djurović, and J. J. D. s. p. Jiang, "Time–frequency feature representation using energy concentration: An overview of recent advances," vol. 19, no. 1, pp. 153-183, 2009.
[80] "Librosa. 2020. Feature extraction—Librosa 0.8.0 documentation. Available at https://librosa.org/doc/latest/feature.html," (accessed 21 May 2020).
[81] Z. Tariq, S. K. Shah, and Y. Lee, "Lung Disease Classification using Deep Convolutional Neural Network," in 2019 IEEE International Conference on Bioinformatics and Biomedicine (BIBM), 2019, pp. 732-735.
[82] "Delivery Efficacy of a Vibrating Mesh Nebulizer and a Jet Nebulizer under Different Configurations," vol. 23, no. 6, pp. 389-396, 2010.
[83] K. Nikander, I. Prince, S. Coughlin, S. Warren, and G. Taylor, "Mode of breathing-tidal or slow and deep-through the I-neb Adaptive Aerosol Delivery (AAD) system affects lung deposition of (99m)Tc-DTPA," (in eng), J Aerosol Med Pulm Drug Deliv, vol. 23 Suppl 1, no. Suppl 1, pp. S37-43, Apr 2010.
[84] Á. Farkas, F. Lizal, J. Jedelsky, J. Elcner, A. Horváth, and M. J. P. Jicha, "Simulation of airway deposition of an aerosol drug in COPD patients," vol. 11, no. 4, p. 153, 2019.
[85] W. A. Briscoe and A. B. J. T. J. o. c. i. Dubois, "The relationship between airway resistance, airway conductance and lung volume in subjects of different age and body size," vol. 37, no. 9, pp. 1279-1285, 1958.
[86] R. N. Jones, "Microbial etiologies of hospital-acquired bacterial pneumonia and ventilator-associated bacterial pneumonia," (in eng), Clin Infect Dis, vol. 51 Suppl 1, pp. S81-7, Aug 1 2010.
[87] S. C. Brewer, R. G. Wunderink, C. B. Jones, and K. V. J. C. Leeper Jr, "Ventilator-associated pneumonia due to Pseudomonas aeruginosa," vol. 109, no. 4, pp. 1019-1029, 1996.
[88] N. Mesaros et al., "Pseudomonas aeruginosa: resistance and therapeutic options at the turn of the new millennium," vol. 13, no. 6, pp. 560-578, 2007.
[89] J. Rello et al., "Recurrent Pseudomonas aeruginosa pneumonia in ventilated patients: relapse or reinfection?," vol. 157, no. 3, pp. 912-916, 1998.
[90] Q. Lu et al., "Nebulized Ceftazidime and Amikacin in Ventilator-associated Pneumonia Caused by Pseudomonas aeruginosa," vol. 184, no. 1, pp. 106-115, 2011.
[91] I. Goldstein, F. Wallet, A. Nicolas-Robin, F. Ferrari, C.-H. Marquette, and J.-J. Rouby, "Lung Deposition and Efficiency of Nebulized Amikacin during Escherichia coli Pneumonia in Ventilated Piglets," American Journal of Respiratory and Critical Care Medicine, vol. 166, no. 10, pp. 1375-1381, 2002/11/15 2002.
[92] K. J. J. o. A. C. Drlica, "The mutant selection window and antimicrobial resistance," vol. 52, no. 1, pp. 11-17, 2003.
[93] G. Sindelar et al., "Mutant prevention concentration as a measure of fluoroquinolone potency against mycobacteria," vol. 44, no. 12, pp. 3337-3343, 2000.
[94] D. Traini and P. M. Young, "Delivery of antibiotics to the respiratory tract: an update," Expert Opinion on Drug Delivery, vol. 6, no. 9, pp. 897-905, 2009/09/01 2009.
[95] R. Dhand and H. Sohal, "Pulmonary Drug Delivery System for inhalation therapy in mechanically ventilated patients," Expert Review of Medical Devices, vol. 5, no. 1, pp. 9-18, 2008/01/01 2008.
[96] D. P. I. D. J. C. f. D. E. Drug and Research, "Guidance for industry," vol. 1000, 1998.
[97] P. Sharma, M. Quazi, I. R. Vazquez, and N. Jackson, "Investigation of droplet size distribution for vibrating mesh atomizers," Journal of Aerosol Science, vol. 166, p. 106072, 2022/11/01/ 2022.
[98] S.-C. J. M. E. Shen, "A new cymbal-shaped high power microactuator for nebulizer application," vol. 87, no. 2, pp. 89-97, 2010.
[99] Y.-M. Kuo, W.-H. Chan, C.-W. Lin, S.-H. Huang, C.-C. J. A. Chen, and A. Q. Research, "Characterization of vibrating mesh aerosol generators," vol. 19, no. 8, pp. 1678-1687, 2019.
[100] T. Lin, Y. Shen, and M. Wang, "Effects of membrane vibration on performance of nebulization," in 13th International Conference on Liquid Atomization and Spray Systems, ICLASS 2015, 2015.
[101] Q. Yan, C. Wu, and J. Zhang, "Effect of the Dynamic Cone Angle on the Atomization Performance of a Piezoceramic Vibrating Mesh Atomizer," vol. 9, no. 9, p. 1836, 2019.
[102] N. Rao, N. Kadrichu, B. J. J. o. a. m. Ament, and p. d. delivery, "Application of a droplet evaporation model to aerodynamic size measurement of drug aerosols generated by a vibrating mesh nebulizer," vol. 23, no. 5, pp. 295-302, 2010.
[103] K.-H. Choi, S.-H. Moon, S.-K. Park, G. Cho, K. C. Nam, and B. J. Park, "Fabrication and Characterization of Medical Mesh-Nebulizer for Aerosol Drug Delivery," vol. 8, no. 4, p. 604, 2018.
[104] O. Z. Olszewski, R. MacLoughlin, A. Blake, M. O’Neill, A. Mathewson, and N. Jackson, "A Silicon-based MEMS Vibrating Mesh Nebulizer for Inhaled Drug Delivery," Procedia Engineering, vol. 168, pp. 1521-1524, 2016/01/01/ 2016.
[105] E. Guerra-Bravo, H.-J. Lee, A. Baltazar, and K. J. J. A. S. Loh, "Vibration analysis of a piezoelectric ultrasonic atomizer to control atomization rate," vol. 11, no. 18, p. 8350, 2021.
[106] Y. Cai, J. Zhang, C. Zhu, J. Huang, and F. J. C. J. o. M. E. Jiang, "Theoretical calculations and experimental verification for the pumping effect caused by the dynamic micro-tapered angle," vol. 29, no. 3, pp. 615-623, 2016.
[107] Q. Yan, J. Zhang, J. Huang, and Y. Wang, "The Effect of Vibration Characteristics on the Atomization Rate in a Micro-Tapered Aperture Atomizer," vol. 18, no. 4, p. 934, 2018.
[108] Q. Yan, W. Sun, and J. Zhang, "Study on the Influencing Factors of the Atomization Rate in a Piezoceramic Vibrating Mesh Atomizer," vol. 10, no. 7, p. 2422, 2020.
[109] "The Influence of Lung Deposition on Clinical Response," vol. 14, no. supplement 1, pp. 19-26, 2001.
[110] N. R. Labiris and M. B. J. B. j. o. c. p. Dolovich, "Pulmonary drug delivery. Part I: physiological factors affecting therapeutic effectiveness of aerosolized medications," vol. 56, no. 6, pp. 588-599, 2003.
[111] M. Biddiscombe, S. Meah, P. Barnes, and O. Usmani, "Drug particle size and lung deposition in COPD," ed: Eur Respiratory Soc, 2016.
[112] N. S. Haider, B. K. Singh, R. Periyasamy, and A. K. Behera, "Respiratory Sound Based Classification of Chronic Obstructive Pulmonary Disease: a Risk Stratification Approach in Machine Learning Paradigm," Journal of Medical Systems, vol. 43, no. 8, p. 255, 2019/06/28 2019.
[113] K. Mridha, S. Sarkar, and D. Kumar, "Respiratory Disease Classification by CNN using MFCC," in 2021 IEEE 6th International Conference on Computing, Communication and Automation (ICCCA), 2021, pp. 517-523.
[114] D. Perna and A. Tagarelli, "Deep auscultation: Predicting respiratory anomalies and diseases via recurrent neural networks," in 2019 IEEE 32nd International Symposium on Computer-Based Medical Systems (CBMS), 2019, pp. 50-55: IEEE.
[115] M. Aykanat, Ö. Kılıç, B. Kurt, S. J. E. J. o. I. Saryal, and V. Processing, "Classification of lung sounds using convolutional neural networks," vol. 2017, no. 1, pp. 1-9, 2017.
[116] I. Sen, M. Saraclar, and Y. P. Kahya, "A Comparison of SVM and GMM-Based Classifier Configurations for Diagnostic Classification of Pulmonary Sounds," IEEE Transactions on Biomedical Engineering, vol. 62, no. 7, pp. 1768-1776, 2015.
[117] S. Charleston-Villalobos et al., "Assessment of multichannel lung sounds parameterization for two-class classification in interstitial lung disease patients," vol. 41, no. 7, pp. 473-482, 2011.
[118] B. Rocha et al., "Α respiratory sound database for the development of automated classification," in International Conference on Biomedical and Health Informatics, 2017, pp. 33-37: Springer.
[119] M. Grønnesby, J. C. A. Solis, E. Holsbø, H. Melbye, and L. A. J. a. p. a. Bongo, "Feature extraction for machine learning based crackle detection in lung sounds from a health survey," 2017.
[120] N. Alcaraz Meseguer, "Speech analysis for automatic speech recognition," Institutt for elektronikk og telekommunikasjon, 2009.
[121] A. Gouda, S. El Shehaby, N. Diaa, and M. Abougabal, "Classification techniques for diagnosing respiratory sounds in infants and children," in 2019 IEEE 9th Annual Computing and Communication Workshop and Conference (CCWC), 2019, pp. 0354-0360: IEEE.
[122] K. Larsson et al., "Impact of COPD diagnosis timing on clinical and economic outcomes: the ARCTIC observational cohort study," vol. 14, p. 995, 2019.
[123] K. C. Chang, J. W. Huang, and Y. F. Wu, "Design of e-Health System for Heart Rate and Lung Sound Monitoring with AI-based Analysis," in 2021 IEEE International Conference on Consumer Electronics-Taiwan (ICCE-TW), 2021, pp. 1-2.
[124] A. Antoniou, A. Storkey, and H. J. a. p. a. Edwards, "Data augmentation generative adversarial networks," 2017.
[125] G. Petmezas et al., "Automated Lung Sound Classification Using a Hybrid CNN-LSTM Network and Focal Loss Function," vol. 22, no. 3, p. 1232, 2022.
[126] J. Acharya and A. Basu, "Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning," IEEE Transactions on Biomedical Circuits and Systems, vol. 14, no. 3, pp. 535-544, 2020.
[127] E. Dong, G. Liu, Y. Zhou, and Y. Cai, "Voice activity detection based on short-time energy and noise spectrum adaptation," in 6th International Conference on Signal Processing, 2002., 2002, vol. 1, pp. 464-467 vol.1.
[128] K. J. Piczak, "Environmental sound classification with convolutional neural networks," in 2015 IEEE 25th International Workshop on Machine Learning for Signal Processing (MLSP), 2015, pp. 1-6.
[129] J. Salamon and J. P. Bello, "Deep Convolutional Neural Networks and Data Augmentation for Environmental Sound Classification," IEEE Signal Processing Letters, vol. 24, no. 3, pp. 279-283, 2017.
[130] Y. Kim, J. Sa, Y. Chung, D. Park, and S. J. S. Lee, "Resource-efficient pet dog sound events classification using LSTM-FCN based on time-series data," vol. 18, no. 11, p. 4019, 2018.
[131] "The Effect of Breathing Pattern on Nebulizer Drug Delivery," vol. 16, no. 3, pp. 325-339, 2003.
[132] G. Benchetrit, "Breathing pattern in humans: diversity and individuality," Respiration Physiology, vol. 122, no. 2, pp. 123-129, 2000/09/01/ 2000.