目前在人工嗅覺領域中，利用電子鼻系統對混合氣體作有效的分析與識別仍是一大課題。當化學感測器陣列同時截取到多種目標氣體及當下環境的資訊時，如何採取適當的訊號處理使電子鼻系統能對抗不同的干擾，例如環境變量，背景氣體變化，感測器飄移等等，以獲取有意義的多變量響應作為特徵進行氣味識別(分類)和濃度估計(回歸)的任務，藉此增加整個系統的強健性，為本論文所關注的重點。首先，針對過去常採用電阻變化比例並取其穩態值作為特徵，本論文提出以電導變化差來進行比較，並且採用指數移動平均的概念在訊號未達穩態時擷取暫態響應，用以描述感測器對氣體的反應速率，使資料的分類鑑別度增加。接著在辨識混合氣味時，本論文採用基於構成成分作決策的多標籤辨識方法，有別於過去將單一組合皆視為一類進行分類，此方法分別對數種已知構成成分建立二元決策模型，最後將所有決策結果綜合，即為混合氣體辨識結果。與傳統方式相比，除了有效減低分類器負擔外，在低維度時也有更高的正確率。最後，為了進一步預估混合氣體各成分的濃度估計，除了使用多元線性回歸分析外，為避免資料產生共線性問題，本論文運用偏最小平方法(PLS)進行預估，此方法也可套用在分類問題上。結果顯示以電導作為特徵時，針對兩種氣體混合的情況，也能有效估計出其濃度。

In current research of artificial olfaction, effective analysis and recognition of mixed odors is still a challenging issue. Considering the specific case of a gas sensor array exposed to multiple target gases and various background gases simultaneously, and the sensor data are subject to interference from the environment such as temperature and humidity. In this research, we intend to find out some signal processing methods to get meaningful responses as multivariate features for odor identification (classification) and concentration estimation (regression). First, the thesis compares the performance with conductance difference changes and resistance fractional changes, the results show that using of conductance can achieve better accuracy rates. Secondly, we use transient features together with steady-state features. The underlying idea is that the transient phase may include additional information concerning to the constituting gases that the steady state does not provide. For the odor identification tasks, we perform multi-label classification using so-called the Individual Constituent Decision Method (ICDM) instead of conventional multi-class classification. The results show that multi-label classification reduces the computational complexity and improves the recognition accuracy. For the concentration estimation tasks, Multiple Linear Regression (MLR) is the common approach to estimate the concentration of individual constituents. In addition, in order to avoid the collinearity problem, this thesis uses the Partial Least Squares (PLS) method to estimate the concentration, and this method can also be applied to the classification problem. The results show that we can reasonably estimate the concentration of the individual constituent with conductance responses when two analyte gases existed simultaneously.

參考文獻
[1] J. W. Gardner, Handbook of Machine Olfaction. WILEY-VCH, 2003.
[2] K. Persaud and G. Dodd, “Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose,” Nature, vol. 299, pp. 352–355, 1982.
[3] H.V. Shurmer, “An electronic nose: a sensitive and discriminating substitute for a mammalian olfactory system,” IEE Proc. G Circuits, Devices Syst., vol. 137, pp. 197–204, 1990.
[4] J. W. Gardner and P. N. Bartlett, “A brief history of electronic noses,” Sensors Actuators B Chem., vol. 19, pp. 211–220, 1994.
[5] P. C. Jain and R. Kushwaha, “Wireless gas sensor network for detection and monitoring of harmful gases in utility areas and industries,” 2012 Sixth Int. Conf. Sens. Technol., pp. 642–646, 2012.
[6] 鄭桂忠, 施崇鴻, 王立群, 陳新, 劉奕汶, 徐爵民, 楊家銘, and 饒達仁, 「以電子鼻系統晶片早期預測及同步診斷使用人工呼吸器病患的肺炎菌種」, 國科會計畫 NSC 101-2220-E-007 -0062012.
[7] D. W. Ballantine, R. M. White, and S. J. Martin, Acoustic Wave Sensors, Theory Design and Physico-Chemical Applications. Academic Press, 1997.
[8] P. Hauptmann, Sensors-Principles and Applications. Carl Hanser Verlag & Prentice Hall, pp. 115–153, 1993.
[9] J. W. Gardner, Microsensors-Principles and Applications. John Wiley & Sons, pp. 224–246, 1994.
[10] J. W. Gardner and P. N. Bartlett, E-noses-Principles and Applications. Oxford, pp. 67–100, 1999.
[11] K. Toko, Biomimetic Sensor Technology. Cambridge University Press, pp. 92–111, 2000.
[12] W Göpel, H. J., and Z. J.N, Sensors: A Comprehensive Survey. VCH Verlagsgesellschaft GmbH, Weinheim, Germany, 1991.
[13] “Figaro Sensor.” [Online]. Available: http://www.figarosensor.com/.
[14] N. Barsan, D. Koziej, and U. Weimar, “Metal oxide-based gas sensor research: How to?,” Sensors Actuators B Chem., vol. 121, no. 1, pp. 18–35, Jan. 2007.
[15] G. Eranna, Metal Oxide Nanostructures as gas sensing devices. CRC Press, 2012.
[16] R. Gutierrez-Osuna, “Pattern analysis for machine olfaction: a review,” IEEE Sens. J., vol. 2, no. 3, pp. 189–202, Jun. 2002.
[17] S. Marco and A. Gutiérrez-gálvez, “Signal and Data Processing for Machine Olfaction and Chemical Sensing : A Review,” vol. 12, no. 11, pp. 3189–3214, 2012.
[18] 許柏安, 「快速混合氣體辨識方法之研究」, 國立清華大學資訊工程研究所, 碩士論文, 2012.
[19] 王家銘, 「利用樣式識別實現電子鼻肺炎偵測」, 國立清華大學電機工程研究所, 碩士論文, 2013.
[20] A. Fort, N. Machetti, S. Rocchi, M. B. Serrano Santos, L. Tondi, N. Ulivieri, V. Vignoli, and G. Sberveglieri, “Tin oxide gas sensing: Comparison among different measurement techniques for gas mixture classification,” IEEE Trans. Instrum. Meas., vol. 52, no. 3, pp. 921–926, Jun. 2003.
[21] F. J. Acevedo, S. Maldonado, E. Domínguez, a. Narváez, and F. López, “Probabilistic support vector machines for multi-class alcohol identification,” Sensors Actuators B Chem., vol. 122, no. 1, pp. 227–235, Mar. 2007.
[22] A. Vergara, E. Martinelli, E. Llobet, F. Giannini, A. D’Amico, and C. Di Natale, “An alternative global feature extraction of temperature modulated micro-hotplate gas sensors array using an energy vector approach,” Sensors Actuators B Chem., vol. 124, no. 2, pp. 352–359, Jun. 2007.
[23] M. Barker and W. Rayens, “Partial least squares for discrimination,” J. Chemom., vol. 17, no. 3, pp. 166–173, Mar. 2003.
[24] C. Distante, N. Ancona, and P. Siciliano, “Support vector machines for olfactory signals recognition,” Sensors Actuators B Chem., vol. 88, no. 1, pp. 30–39, Jan. 2003.
[25] M. Pardo and G. Sberveglieri, “Classification of electronic nose data with support vector machines,” Sensors Actuators B Chem., vol. 107, no. 2, pp. 730–737, Jun. 2005.
[26] M. K. Muezzinoglu, A. Vergara, R. Huerta, and M. I. Rabinovich, “A sensor conditioning principle for odor identification,” Sensors Actuators B Chem., vol. 146, no. 2, pp. 472–476, Apr. 2010.
[27] C. Chang and C. Lin, “LIBSVM : A Library for Support Vector Machines,” pp. 1–39, 2013.
[28] M. K. Muezzinoglu, A. Vergara, R. Huerta, N. Rulkov, M. I. Rabinovich, A. Selverston, and H. D. I. Abarbanel, “Acceleration of chemo-sensory information processing using transient features,” Sensors Actuators B Chem., vol. 137, no. 2, pp. 507–512, Apr. 2009.
[29] F. Tai and H. Lin, “Multilabel Classification with Principal Label Space,” vol. 2542, pp. 2508–2542, 2012.
[30] J. Read, B. Pfahringer, G. Holmes, and E. Frank, “Classifier chains for multi-label classification,” Mach. Learn., vol. 85, no. 3, pp. 333–359, Jun. 2011.
[31] E. Alpaydm, Introduction to Machine Learning, Second Edi. The MIT Press, 2010.
[32] S. Wold, K. Esbensen, and P. Geladi, “Principal component analysis,” Chemom. Intell. Lab. Syst., vol. 2, no. 1–3, pp. 37–52, Aug. 1987.
[33] J. Ye, “Least squares linear discriminant analysis,” Proc. 24th Int. Conf. Mach. Learn. - ICML ’07, pp. 1087–1093, 2007.
[34] J. C. Burges, “A Tutorial on Support Vector Machines for Pattern Recognition,” Data Min. Knowl. Discov., vol. 2, pp. 121–167, 1998.
[35] R. O. Duda, P. E. Hart, and D. G. Stork, Pattern classification. Wiley, 2001.
[36] P. Geladi and B. R. Kowalski, “Partial Least-Squares Regression: A Tutorial,” Anal. Chim. Acta, vol. 185, pp. 1–17, 1986.
[37] S. de Jong, “SIMPLS: An alternative approach to partial least squares regression,” Chemom. Intell. Lab. Syst., vol. 18, no. 3, pp. 251–263, Mar. 1993.
[38] D. M. Magerman, “Statistical Decision-Tree Models for Parsing,” Proc. 33rd Annu. Meet. Assoc. Comput. Linguist., pp. 276–283, 1995.
[39] G. H. Kim, Y. W. Kim, G. S. J. Lee, and G. J. Jeon, “Multi-Class System based on SVM for real-time Gas Mixture Classification,” SICE Annu. Conf., pp. 1764–1767, 2010.