近年來，氣體感測裝置被廣泛的使用在許多地方，包括環境監控、食物品質監測以及醫療上的診斷等。然而，氣體感測系統卻尚未被大力的推廣，主要受限於感測器常會受到像是溫度、濕度或是空氣汙染等環境因子的影響而會產生飄移現象，因此對於氣體感測系統來說，飄移校正的方法是有其必要性的。
本論文提出了一個簡單、低成本而且可以控制濕度、溫度的氣體感測系統，可以對可攜式電子鼻氣體感測系統做基本的環境控制，系統可控的環境相對濕度範圍為10%到80%；可控的溫度範圍為室溫到攝氏100度，我們可以將大部分的氣體感測裝置套用在此控制系統上，進行環境控制並且測試。
本文藉由觀察濕度對氣體感測器的影響，找出氣體感測器陣列資料中存在的濕度因子，並利用環境得到的參數以線性補償的方式，開發出基於主成分分析演算法下的飄移補償演算法來校正不同濕度情況下的甲醇以及乙醇氣體資料，校正演算法的結果在辨識正確率以及費式類別離散度上，相較於監督式學習的線性識別分析演算法上都有較好的表現，除此之外，相較於傳統的校正補償演算法，如：獨立成分分析法以及類神經網路演算法，本文提出的環境權重校正演算法可以在不增加過多計算步驟的同時，達到較好的分類分群結果。

Recently, gas sensing system has been widely used in many applications, including environmental monitoring, food quality management, and medical diagnosis. However, gas sensing systems are still not popular for these applications, restricted by sensor drift problem usually caused by environmental factor, such as humidity, temperature, air pollution, and so on. Therefore, it is necessary to develop a drift calibration method in gas sensing system.
In this thesis, we develop a simple and low-cost gas sensing system with humidity and temperature control. We can control the environmental condition by this system for most portable e-nose system. In this system, the range of relative humidity (RH) is controlled from 10% to 80%； the range of temperature is controlled from room temperature up to 100°C. With this environment controlled system, we can test the environment parameters for most gas sensing applications.
By observing the response of humidity and gas sensor, we find the humidity factor of gas sensor arrays. By using a linear calibration method, we developed a PCA-based drift calibration algorithm for the drift effect caused by humidity variation of the methanol and ethanol gas data collected under the different environment conditions. Our calibration result performs better than Linear Discriminant Analysis (LDA) algorithm in both classification accuracy and Fisher Class Separability. Besides, our algorithm also has a better grouping result than the traditional calibration algorithm such as Independent Component Analysis and Neural Network.

[1] Gardner, Julian W., and Philip N. Bartlett. "A brief history of electronic noses." Sensors and Actuators B: Chemical 18.1 (1994): 210-211.
[2] Buck, Linda, and Richard Axel. "A novel multigene family may encode odorant receptors: a molecular basis for odor recognition." Cell 65.1 (1991): 175-187.
[3] Chiu, Shih-Wen, and Kea-Tiong Tang. "Towards a chemiresistive sensor-integrated electronic nose: A review." Sensors 13.10 (2013): 14214-14247.
[4] Marco, Santiago, and Agustín Gutierrez-Galvez. "Signal and data processing for machine olfaction and chemical sensing: a review." IEEE Sensors Journal 12.11 (2012): 3189-3214.
[5] 林天送. "嗅覺與味蕾受體的新發現." (2010): 70-71.
[6] Tang, Kea-Tiong, Yi-Shan Lin, and Jyuo-Min Shyu. "A local weighted nearest neighbor algorithm and a weighted and constrained least-squared method for mixed odor analysis by electronic nose systems." Sensors 10.11 (2010): 10467-10483.
[7] Gualdrón, O., et al. "Variable selection for support vector machine based multisensor systems." Sensors and Actuators B: Chemical 122.1 (2007): 259-268.
[8] Korotcenkov, G., and B. K. Cho. "Engineering approaches to improvement of conductometric gas sensor parameters. Part 2: Decrease of dissipated (consumable) power and improvement stability and reliability." Sensors and Actuators B: Chemical 198 (2014): 316-341.
[9] Di Carlo, Stefano, and M. Falasconi. Drift correction methods for gas chemical sensors in artificial olfaction systems: techniques and challenges. InTech, 2012.
[10] Ziyatdinov, A., et al. "Drift compensation of gas sensor array data by common principal component analysis." Sensors and Actuators B: Chemical 146.2 (2010): 460-465.
[11] 殷勇, 吴文凯, and 于慧春. "独立分量分析融合小波能量阈值的电子鼻信号去漂移方法." 农业工程学报 30.24 (2014): 325-331.
[12] 田逢春, et al. "带参考向量的 ICA 电子鼻背景干扰消除算法." 计算机工程 38.21 (2012): 26-29.
[13] Omatu, Sigeru, and Mitsuaki Yano. "E-nose system by using neural networks." Neurocomputing 172 (2016): 394-398.
[14] Liu, Xiao, et al. "A survey on gas sensing technology." Sensors 12.7 (2012): 9635-9665.
[15] FIGARO USA., INC. http://www.figarosensor.com/
[16] The MatlabWorks, INC. http://www.mathworks.com/index.html?s_tid=gn_logo
[17] Distante, Cosimo, et al. "On the study of feature extraction methods for an electronic nose." Sensors and Actuators B: Chemical 87.2 (2002): 274-288.
[18] Cho, Jae-Hyun, et al. "Sensing behaviors of polypyrrole sensor under humidity condition." Sensors and Actuators B: Chemical 108.1 (2005): 389-392.
[19] Theodoridis, S., and K. Koutroumbas. "Pattern recognition. 2009."
[20] Wikipedia: 最近鄰居法https://zh.wikipedia.org/wiki/%E6%9C%80%E8%BF%91%E9%84%B0%E5%B1%85%E6%B3%95
[21] Berna, Amalia. "Metal oxide sensors for electronic noses and their application to food analysis." Sensors 10.4 (2010): 3882-3910.
[22] Gutierrez-Osuna, Ricardo. "Pattern analysis for machine olfaction: a review." IEEE Sensors journal 2.3 (2002): 189-202.
[23] Ccjou, "現代啟示錄. " Web. 17 March, 2014. https://ccjou.wordpress.com/2014/03/14/%E8%B2%BB%E9%9B%AA%E7%9A%84%E5%88%A4%E5%88%A5%E5%88%86%E6%9E%90%E8%88%87%E7%B7%9A%E6%80%A7%E5%88%A4%E5%88%A5%E5%88%86%E6%9E%90/
[24] Wang, Xudong, and Vassilis L. Syrmos. "Optimal cluster selection based on Fisher class separability measure." Proceedings of the 2005, American Control Conference, 2005.. IEEE, 2005.