進階搜尋


   電子論文尚未授權公開,紙本請查館藏目錄
(※如查詢不到或館藏狀況顯示「閉架不公開」,表示該本論文不在書庫,無法取用。)
系統識別號 U0026-1508201915023900
論文名稱(中文) 應用電子鼻及機器學習演算法於細菌及傷口期程之自動辨識
論文名稱(英文) Bacteria and Wound Stage Classification based on Machine Learning and E-nose
校院名稱 成功大學
系所名稱(中) 生物醫學工程學系
系所名稱(英) Department of BioMedical Engineering
學年度 107
學期 2
出版年 108
研究生(中文) 吳宜臻
研究生(英文) Yi-Jhen Wu
學號 P86061118
學位類別 碩士
語文別 英文
論文頁數 69頁
口試委員 指導教授-林哲偉
共同指導教授-吳炳慶
口試委員-蔡宗霖
口試委員-林育昇
中文關鍵字 揮發性有機物質  電子鼻感測器  細菌  傷口  特徵擷取 
英文關鍵字 Volatile organic compounds (VOCs)  Electronic Nose (E-nose)  Wound  Feature Extraction 
學科別分類
中文摘要 電子鼻的發展結合了「對揮發性有機物之感測器陣列」和「多種氣體辨識之演算法」的軟硬體開發,已逐漸協助產業技術分析,在食品安全、公共衛生、空氣汙染等應用都有更好的趨勢。而為了應用於居家照護,期望用戶可透過簡易的方式得以立即因應各種不同類型的傷口,給予適當的治療或預防惡化的護理措施。本研究特別為檢測傷口之氣味,而設計了能隨隔絕外部變因的軟質罩子,並連結管路進而使電子鼻收集所需的特定揮發性有機物質。在演算法的開發上,我們比較了六通道之原始訊號及取得每秒間的特徵擷取訊號(包含平均值、標準差、變異數、四分位距、香農熵(Shannon entropy)和對數能量熵(Log-energy entropy)),也加入增加完特徵後進行如NCA或PCA的特徵選擇並以k折交叉驗證(k-fold cross validation)與留一驗證法(Leave-one-out cross validation)驗證在決策樹(Decision tree)、線性判別分析(Linear discriminant analysis)、二次判別分析(Quadratic discriminant analysis)、k-近鄰演算法(k-nearest neighbor)四種辨識器上的表現結果。在樣本的採集方面有兩項,分別為細菌與傷口氣味之辨識:在細菌方面,我們針對兩種一級菌,枯草桿菌(Bacillus subtilis)、大腸桿菌(Escherichia coli)與兩種二級菌,金黃色葡萄球菌(Staphylococcus aureus)、白色念珠菌(Candida albicans),亦加入其一的培養基(LB),辨識五類之結果,其總資料數為4500筆;而在傷口的分類上,我們針對一般綜合型傷口測量完整的癒合過程學習,從健康為受傷的皮膚到產生傷口後,經過凝血、發炎、增生、修復期,及最後完全癒合可以有效辨識多個類別的期程,其總資料數為105,000筆。本論文中也特別比較四種分類器結合特徵擷取與選擇的辨識結果,欲提高預測的靈敏度與特異度,從整體採用10-fold驗證後的最佳結果可看到,在細菌的表現上,可達到99.29%的準確率、99.29%的靈敏度、99.82%的特異度;而傷口的表現,則可達到99.79%的準確率、99.79%的靈敏度、99.97%的特異度。
英文摘要 The development of electronic nose combining the technology of software and hardware on “Volatile organic compounds sensor array” and “Multiple gas classification algorithms in machine learning” has gradually supported industrial technology analysis in food safety, public health, air pollution, and other applications and let our life getting a better trend. To the application of home care, it is expected that the user can immediately receive the evaluation results from various types of wounds by a simple method, and also that provides an appropriate treatment or prevent deterioration measures. For the experiment of detecting wound odor, we specially designed a soft cover with a tube to isolate the external ambient and to collect the specific volatile organic compounds by E-nose. In the development of the algorithm, we compared the raw signals with six channels and obtained the feature extraction from raw signals per second (including mean, standard deviation, variance, quartile deviation, Shannon entropy, and logical energy entropy) and also adding the feature selections method, like NCA or PCA for dimensionality reduction. Then validating the results of performance with four classifiers (decision tree, linear discriminant analysis, quadratic discriminant analysis, and k-nearest neighbor) by k-fold and leave-one-out cross validation.
There were two items in the collection of samples, one was classification of bacteria and another one was classification of wound. In the case of bacteria, we targeted two kinds of bacteria with bio-safety level 1 (BSL-1), including Bacillus subtilis and Escherichia coli; two with bio-safety level 1 (BSL-1), including Staphylococcus aureus and Candida albicans; also adding one of growth media-LB. To discriminate the results of classification in five classes, and the total sample datapoints were 4500. And in the case of healing wounds, we measured the complete comprehensive healing phase of wounds, the classes from healthy skin to injured fresh skin, and through coagulation, inflammation, proliferation, remodeling, and finally healed wound completely. Multiple categories of phase could be effectively predicted and the total sample datapoints were 105,000. In this research, we also compare the classification results between for classifier with feature extraction and selection to improve the sensitivity and specificity of the prediction. As the results, we obtained that the best results in 10-fold validation were in the performance of bacteria could reach 99.29% accuracy, 99.29% sensitivity and 99.82% specificity; the performance of wound could reach 99.79% accuracy, 99.79% sensitivity and 99.97% specificity.
論文目次 摘 要 i
Abstract iii
誌謝 v
Table of Contents vi
List of Tables viii
List of Figures ix
List of Abbreviations xi
Chapter 1 Introduction 1
1.1 Introduction 1
1.2 Biological Olfactory System 2
1.3 Electronic Nose System 4
1.4 Literature Survey 6
1.5 Motivation and Limitations 7
Chapter 2 Methodology 9
2.1 Taiyo Smell Sensor (E-nose) odor data collection 9
2.2 Principle of Detection 9
2.3 Sample Gathering 12
2.4 Streptozotocin-Induced Type 1 Diabetes Mellitus in Rats 16
2.5 Wound Odor Detection 19
Chapter 3 Odor Recognition Algorithm 21
3.1 Data Preprocessing 22
3.2 Feature Extraction 24
3.3 Feature Selection 27
3.4 Algorithm Models 30
3.5 Classifier Validation 33
3.6 Performance Measures 36
Chapter 4 Experimental Results and Discussions 38
4.1 Information on Sample 38
4.2 Experimental results 40
4.3 Discussion 53
4.4 Conclusions and future works 54
References 55
Appendix A – Confusion Matrix on Bacteria 62
Appendix B – Confusion Matrix on Wound 66
參考文獻 [1] S. Kort, M. Brusse-Keizer, J. W. Gerritsen, and J. van der Palen, “Data analysis of electronic nose technology in lung cancer: generating prediction models by means of Aethena,” Journal of Breath Research, vol. 11, no. 2, p. 026006, 2017.
[2] Zhenzhen Xie, “Electronic nose of analysis of volatile organic compounds in air and exhaled breath,” Ph.D. dissertation, Chemical Engineering Dept., Louisville Univ., Kentucky, 2017.
[3] N. Yusuf, A. A. Abdullah, Y. Htut, and A. Zakaria, “Comparison of various pattern recognition techniques based on e-nose for identifying bacterial species in diabetic wound infections,” WIT Trans Inf Commun Technol, vol. 53, pp. 43-59, 2014.
[4] H. G. Byun, K. C. Persaud, A. M. Pisanelli, “Wound-state monitoring for burn patients using e-nose/SPME System,” ETRI Journal, vol. 32, no. 3, pp. 440-446, 2010.
[5] H. T. Nagle, R. Gutierrez-Osuna, and S. S. Schiffman, “The how and why of electronic noses,” IEEE spectrum, vol. 35, no. 9, pp. 22-34, 1998.
[6] A. D. Wilson, “Review of electronic-nose technologies and algorithms to detect hazardous chemicals in the environment,” Procedia Technology, vol. 1, pp. 453-463, 2012.
[7] A. D. Wilson and M. Baietto, “Applications and advances in electronic-nose technologies,” Sensors, vol. 9, no. 7, pp. 5099-5148, 2009.
[8] J. W. Gardner, H. W. Shin, and E. L. Hines, “An electronic nose system to diagnose illness,” Sensors and Actuators B: Chemical, vol. 70, no. 1-3, pp. 19-24, 2000.
[9] R. Edwards and K. G. Harding, “Bacteria and wound healing,” Current opinion in infectious diseases, vol. 17, no. 2, pp. 91-96, 2004.
[10] R. Dutta, E. L. Hines, J. W. Gardner, and P. Boilot, “Bacteria classification using Cyranose 320 electronic nose,” Biomedical engineering online, vol. 1, no. 1, pp. 4-10, 2002.
[11] N. Yusuf, A. Zakaria, M. I. Omar, A. Y. Md Shakaff, M. J. Masnan, L. M. Kamarudin, N. A. Rahim, N. Z. Isqi Zakaria, A. A. Abdullah, A. Othman and M. S. Yasin, “In-vitro diagnosis of single and poly microbial species targeted for diabetic foot infection using e-nose technology,” BMC Bioinformatics, vol. 16, no. 1, p. 1-12, 2015.
[12] S. F. Lo and W. Y. Hu, “The principle of chronic wound assessment and measurement,” Hu li za zhi The journal of nursing, vol. 54, no. 2, pp. 62-67, 2007.
[13] J. Yan, S. Duan, T. Huang, and L. Wang, “Hybrid feature matrix construction and feature selection optimization-based multi-objective QPSO for electronic nose in wound infection detection,” Sensor Review, vol. 36, no. 1, pp.23-33, 2016.
[14] H. Sun, F. Tian, Z. Liang, T. Sun, B. Yu, S. X. Yang, Q. He, L. L. Zhang and X. M. Liu, “Sensor array optimization of electronic nose for detection of bacteria in wound infection,” IEEE Transactions on Industrial Electronics, vol. 64, no. 9, pp. 7350-7358, 2017.
[15] Initium INC., “Technology of QCM based Molecular Interation Analyzer,” Available: http://www.initium2000.com/en/technology.html. [Accessed: July 25, 2019].
[16] Stephanie Pappas, “Why do our feet smell worse in the winter?,” livescience.com, Dec. 5, 2016. [Online], Available: https://www.livescience.com/57089-foot-odor-worse-in-winter.html. [Accessed: July 14, 2019].
[17] Microbiology Learning: the "WHY"OLOGY of Microbial Testing, “Common bacteria “SCENTS” in culture,” Available: https://microbiologylearning.weebly.com. [Accessed: July 13, 2019].
[18] S. Lazarus, D. M. Cooper, D. R. Knighton, D. J. Margolis, R. E. Percoraro, G. Rodeheaver, and M. C. Robson, “Definitions and guidelines for assessment of wounds and evaluation of healing,” Wound Repair and Regeneration, vol. 2, no. 3, pp. 165-170, 1994.
[19] S. Barber, “A Clinically Relevant Wound Assessment Method to Monitor Healing Progression,” OstomyWound Management, vol. 54, no.3, pp.42-49, 2008.
[20] B. L. Furman, “Streptozotocin‐induced diabetic models in mice and rats,” Current protocols in pharmacology, vol. 70, no. 1, pp. 5-47, 2015.
[21] A. Estabrooks, T. Jo, and N. Japkowicz, “A multiple resampling method for learning from imbalanced data sets,” Computational intelligence, vol. 20, no. 1, pp.18-36, 2004.
[22] A. Estabrooks, T. Jo, and N. Japkowicz, “A multiple resampling method for learning from imbalanced data sets,” Computational intelligence, vol. 20, no. 1, pp.18-36, 2004.
[23] M. L. TIKU, “Estimating the mean and standard deviation from a censored normal sample,” Biometrika, vol. 54, no. 1-2, pp. 155-165, 1967.
[24] M. Rostaghi and H. Azami, “Dispersion entropy: a measure for time-series analysis,” IEEE Signal Processing Letters, vol. 23, no. 5, pp. 610-614, 2016.
[25] J. Urban, “Information entropy,” in Applications from Engineering with MATLAB Concepts, Rijeka, Croatia: InTech, 2016, ch. 2, pp. 43-71.
[26] S. Aydın, H. M. Saraoğlu, and S. Kara, “Log energy entropy-based EEG classification with multilayer neural networks in seizure,” Annals of biomedical engineering, vol. 37, no. 12, pp. 2626-2630, 2009.
[27] W. Yang, K. Wang, and W. Zuo, “Neighborhood component feature selection for high-dimensional data,” Journal of Computers, vol. 7, no. 1, pp. 161-168, 2012.
[28] J. R. Quinlan, “Induction of decision trees,” Machine learning, vol. 1, no. 1, pp.81-106, 1986.
[29] A. Tharwat, “Linear vs. quadratic discriminant analysis classifier: a tutorial,” International Journal of Applied Pattern Recognition, vol. 3, no. 2, pp. 145-180, 2016.
[30] Q. Li and J. Shao, “Sparse quadratic discriminant analysis for high dimensional data,” Statistica Sinica, vol. 25, no. 2, pp. 457-473, 2015.
[31] T. Hastie, R. Tibshirani, and J. Friedman, “Linear Methods for Classification,” in The Elements of Statistical Learning, Hoboken, NJ: John Wiley and Sons, 1999.
[32] E. I. Mohamed, R. Linder, G. Perriello, N. Di Daniele, S. J. Pöppl and A. De Lorenzo, “Predicting type 2 diabetes using an electronic nose-based artificial neural network analysis,” Diabetes, nutrition & metabolism, vol. 15, no. 4, pp. 215-221, 2002.
[33] R. Trevethan, “Sensitivity, specificity, and predictive values: foundations, pliabilities, and pitfalls in research and practice,” Frontiers in public health, vol. 5, p. 307-313, 2017.
[34] Ada Wai-Chee Fu, E. Keogh, Leo Yung Hang Lau, C. A. Ratanamahatana, and Raymond Chi-Wing Wong, “Scaling and time warping in time series querying,” The VLDB Journal, vol. 17, no. 4, pp. 899-921, 2008.
[35] J. Zhao, and L. Itti, “ShapeDTW: shape dynamic time warping,” Pattern Recognition, vol. 74, pp. 171-184, 2018.
[36] E. Parzen, “Quantile probability and statistical data modeling,” Statistical Science, vol. 19, no. 4, pp.652-662, 2004.
[37] H. Akaike, “Prediction and entropy,” Selected Papers of Hirotugu Akaike, pp. 387-410, 1985.
[38] Z. Jaadi, “A step by step explanation of principal component analysis,” Feb. 2019. [Online]. Available: http://towardsdatascience.com. [Accessed: July 13, 2019].
[39] J. W. Gardner, H. W. Shin, and E. L. Hines, “An electronic nose system to diagnose illness,” Sensors and Actuators B: Chemical, vol. 70, no. 1-3, pp. 19-24, 2000.
[40] T. Frisk, L. Eng, S. Guo, W. van der Wijngaart, and G. Stemme, “A miniaturised integrated QCM-based electronic nose microsystem,” 2007 IEEE 20th International Conference on Micro Electro Mechanical Systems (MEMS), Hyogo, 2007, pp. 417-420.
[41] R. Nijland and J. G. Burgess, “Bacterial olfaction,” Biotechnology Journal, vol.5, no. 9, pp. 974-977, 2010.
[42] S. P. Bernier, S. Létoffé, M. Delepierre, and J. M. Ghigo, “Biogenic ammonia modifies antibiotic resistance at a distance in physically separated bacteria,” Molecular Microbiology, vol. 81, no. 3, pp. 705-716, 2011.
[43] L. Pan, W. Zhang, Na Zhu, S. Mao, and K. Tu, “Early detection and classification of pathogenic fungal disease in post-harvest strawberry fruit by electronic nose and gas chromatography–mass spectrometry,” Food Research International, vol. 62, pp. 162-168, 2014.
[44] J. E. Haugen, “The use of chemical sensor array technology, the electronic nose, for detection of boar taint,” Acta Veterinaria Scandinavica, vol. 48, no. 1, pp. 15-17, 2006.
[45] J. Yan, X. Guo, S. Duan, P. Jia, L. Wang, C. Peng, and S. Zhang, “Electronic nose feature extraction methods: a review,” Sensors, vol. 15, no. 11, pp. 27804-27831, 2015.
[46] A. N. Thomas, S. Riazanskaia, W. Cheung, Y. Xu, R. Goodacre, C. L. Thomas, M. S. Baguneid, and A. Bayat, “Novel noninvasive identification of biomarkers by analytical profiling of chronic wounds using volatile organic compounds,” Wound Repair and Regeneration, vol. 18, no. 4, pp. 391-400, 2010.
[47] Q. He, J. Yan, Y. Shen, Y. Bi, G. Ye, F. Tian, and Z. Wang, “Classification of Electronic Nose Data in Wound Infection Detection Based on PSO-SVM Combined with Wavelet Transform,” Intelligent Automation & Soft Computing, vol. 18, no. 7, pp. 967-979, 2012.
[48] R. A. Fisher, “The statistical utilization of multiple measurements,” Annals of Eugenics banner, vol. 8, no. 4, pp. 376-386, 1938.
[49] R. A. Fisher, “The statistical utilization of multiple measurements,” Annals of Eugenics banner, vol. 8, no. 4, pp. 376-386, 1938.
[50] S. Mikat, G. Rätsch, J. Weston, B. Schölkopf, and K. R. Mullert, “Fisher discriminant analysis with kernels,” Neural Networks for Signal Processing IX: Proceedings of the 1999 IEEE Signal Processing Society Workshop, pp. 41-48.
[51] R. Setiawan, “Quadratic classifier from discriminant analysis for classification of multiple attributes data: (Case study: Fertility data set),” 2017 ICIMTech, pp. 112-115.
[52] J. H. Friedman, “Regularized Discriminant Analysis,” Journal of the American Statistical Association, vol. 84, no. 405, pp. 165-175, 1989.
論文全文使用權限
  • 同意授權校內瀏覽/列印電子全文服務,於2024-08-01起公開。
  • 同意授權校外瀏覽/列印電子全文服務,於2024-08-01起公開。


  • 如您有疑問,請聯絡圖書館
    聯絡電話:(06)2757575#65773
    聯絡E-mail:etds@email.ncku.edu.tw