本研究首先會利用熱脫附儀氣相層析質譜儀(TD-GC-MS)聯用系統，針對不同成熟階段的水果進行氣味分析，證明透過TD-GC-MS系統可以分析不同階段間的氣體種類差異。在獲得目標氣體後，我們利用金屬氧化物半導體氣體感測器陣列開發出一種高靈敏度的電子鼻系統(E-nose)，用於識別水果果實的成熟度。
在本論文中，我們開發出一套電子鼻系統，該系統具有作為非破壞性系統的潛力，用於監測在成熟過程中由水果產生的揮發性有機化合物的變化。除了此電子鼻系統，我們還額外提出了一個相機系統來監控水果的果皮顏色，作為識別的另一個特徵。 透過將電子鼻和相機系統結合在一起，我們提出了一種用於水果成熟度監測的非破壞性解決方案。雙電子鼻/相機系統提供了最佳的可分性測量，並顯示了水果四個成熟階段的完美分類：未成熟、半成熟、完全成熟和過熟。
為了降低演算法運算複雜度，我們使用主要成分分析和線性判別方法來降低數據資料的維度，也利於後續觀察資料的分佈情況，而辨識方法則使用了最近Ｋ個鄰居法和支持向量機進行分類器準確率的評估。最初單一電子鼻系統辨識結果約達到平均80多％左右，隨後加入了外表顏色變化的特徵後，會達到更佳的分群效果，最終辨識準確率可以達到100%。

In this research, thermal desorption tendon with gas chromatography-mass spectrum (GC-MS) system has been used to find the target of volatile organic compounds (VOCs) in fruit with different maturity. After getting the target gas, we utilize Metal Oxide Semiconductor (MOS) gas sensor arrays to develop a highly sensitive electronic nose system (E-nose) for identifying maturity of fruit .
In this thesis, we propose an E-nose system that has potential as a non-destructive system for monitoring variation in the volatile organic compounds produced by fruit during the maturing process. In addition to the E-nose system, we also propose a camera system to monitor the peel color of fruit as another feature for identification. By incorporating E-nose and camera systems together, we propose a non-destructive solution for fruit maturity monitoring. The dual E-nose/camera system presents the best class separability measure and shows a perfect classification of the four maturity stages of banana: Unripe, half-ripe, fully ripe, and overripe.
This study proposes a dual E-nose/camera system that utilizes both smell and vision information for improving fruit ripeness classification. This non-destructive system aims to monitor fruit maturity and provide better accuracy in identifying fruit ripeness stages. In order to reduce the complexity of algorithm operations, the principal component analysis (PCA) and linear discriminant (LDA) methods were used to reduce the dimension of data and visualize the distribution of the data. We used the nearest K-neighbor method (KNN) and support vector machine (SVM) classification with leave-one-out cross validation. The initial accuracy was about 80%. After adding the color feature, the result showed that this method yielded better classification and the accuracy achieve up to 100% in classifying fruit maturity.

[1] Rahman, M.M.; Charoenlarpnopparut, C.; Suksompong, P.; Toochinda, P.; Taparugssanagorn, A. A False Alarm Reduction Method for a Gas Sensor Based Electronic Nose. Sensors 2017, 17, 2089.
[2] Gardner, J.W.; Bartlet, P.N. A brief history of electronic noses. Sens. Actuators B 1994, 18, 210-211.
[3] Baietto, M.; Wilson, A.D. Electronic-Nose Applications for Fruit Identification, Ripeness and Quality Grading. Sensors 2015, 15, 899-931.
[4] Cui, S.; Ling, P.; Zhu, H.; Keener, H.M. Plant Pest Detection Using an Artificial Nose System: A Review. Sensors 2018, 18, 378.
[5] Wojnowski, W.; Majchrzak, T.; Dymerski, T.; Gębicki, J.; Namieśnik, J. Portable Electronic Nose Based on Electrochemical Sensors for Food Quality Assessment. Sensors 2017, 17, 2715.
[6] Phaisangittisagul, E.; Nagle, H.T.; Areekul, V. Intelligent method for sensor subset selection for machine olfaction. Sens. Actuator B Chem. 2010, 145, 507-515.
[7] Sneddon, J.; Masuram, S.; Richert, J. Gas chromatography-mass spectrometry, basic principles, instrumentation and selected applications for the detection of organic compounds. Anal. Lett. 2007, 40, 1003-1012.
[8] Filipiak, W.; Sponring, A.; Filipiak, A.; Ager, C.; Schubert, J.; Miekisch, W.; Amann, A.; Troppmair, J. TD-GC-MS analysis of volatile metabolites of human lung cancer and normal cells in vitro. Cancer Epidemiol. Prev. Biomark. 2010, 19, 182-195.
[9] Le, M.; Slaughter, D.C.; Thompson, J.E. Optical chlorophyll sensing system for banana ripening. Postharvest Biol. Technol. 1997, 12, 273-83.
[10] Abdullah, H.; Zaipun, M. Z.; Rohaya, M. A. Maturity indices of banana (Musa sapientum CV. Berangan). MARDI Res. Bull. 1986, 14, 237-242.
[11] Ammawath, W.; Che Man, Y.B.; Yusof, S.; Rahman, R.A. Effects of variety and stage of fruit ripeness on the physicochemical and sensory characteristics of deep‐fat‐fried banana chips. J. Sci. Food Agric. 2001, 81, 1166-1171.
[12] Baietto, M.; Wilson, A.D. Electronic-Nose Applications for Fruit Identification, Ripeness and Quality Grading. Sensors 2015, 15, 899-931.
[13] Rudnitskaya, A.; Legin, A. Sensor systems, electronic tongues and electronic noses, for the monitoring of biotechnological processes. J. Ind. Microbiol. Biotechnol. 2008, 35, 443-451.
[14] Che Harun, F.K.; Taylor, J.E.; Covington, J.A.; Gardner, J.W. An electronic nose employing dual-channel odour separation columns with large chemosensor array for advanced odour discrimination. Sens. Actuators B 2009, 141, 134-140.
[15] Llobet, E.; Hines, E.L.; Gardner, J.W.; Franco, S. Non-destructive banana ripeness determination using a neural network-based electronic nose. Meas. Sci. Technol. 1999, 10, 538-548.
[16] Konduru, T.; Rains, G.C.; Li, C. A customized metal oxide semiconductor-based gas sensor array for onion quality evaluation: System development and characterization. Sensors 2015, 15, 1252-1273.
[17] Brezmes, J.; Fructuoso, L.; Llobet, E.; Vilanova, X.; Recasens, I.; Orts, J.; Saiz, G.; Correig, X. Evaluation of an electronic nose to assess fruit ripeness. IEEE Sens. J. 2005, 5, 97-108.
[18] Mendoza, F.; Aguilera, J.M. Application of Image Analysis for Classification of Ripening Bananas. J. Food Sci. 2004, 69, 415-423.
[19] Gokul, P.; Raj, S.; Suriyamoorthi, P. Estimation of Volume and Maturity of Sweet Lime Fruit using Image Processing Algorithm. In Proceedings of the 2015 International Conference on Communications and Signal Processing, IEEE ICCSP 2015, 1227-1229.
[20] Asnor, J.I.; Rosnah, S.; Wan, Z.W.H.; Badrul, H.A.B. Pineapple maturity recognition using RGB extraction. World Acad. Sci. Eng. Technol. 2013, 78, 147-150.
[21] Di Rosa, A.R.; Leone, F.; Cheli, F.; Chiofalo, V. Fusion of electronic nose, electronic tongue and computer vision for animal source food authentication and quality assessment-A review. J. Food Eng. 2017, 210, 62-75.
[22] Rodríguez-Navas, C.; R.Forteza, C.; Cerdà, V. Use of thermal desorption-gas chromatography-mass spectrometry (TD-GC-MS) on identification of odorant emission focus by volatile organic compounds characterization. Chemosphere 2012, 89, 1426-143.
[23] Franc, C.; David, F.;de Revel, G. Multi-residue off-flavour profiling in wine using stir bar sorptive extraction-thermal desorption-gas chromatography-mass spectrometry. Journal of Chromatography A. 2009, 1216, 3318-3327.
[24] Distantea, C.; Leo, M.; Sicilianoa, P.; Persaud, K. On the study of feature extraction methods for an electronic nose. Sens. Actuators B Chem. 2002, 87, 274-288.
[25] Sanaeifar, A.; Mohtasebi, S.S.; Varnamkhasti, M.G.; Ahmadi, H.; Lozano, J. Development and application of a new low cost electronic nose for the ripeness monitoring of banana using computational techniques (PCA, LDA, SIMCA, and SVM). Czech J. Food Sci. 2014, 32, 538-548.
[26] Bedoui, S.; Faleh, R.; Samet, H.; Kachouri, A. Electronic nose system and principal component analysis technique for gases identification. Proc. IEEE 10th Int. Multi-Conf. Syst. Signals Devices (SSD) 2013, 1-6.
[27] Arnold, C.; Haeringer, D.; Kiselev, I.; Goschnick, J. Sub-surface probe module equipped with the Karlsruhe Micronose KAMINA using a hierarchical LDA for the recognition of volatile soil pollutants. Sens. Actuators B 2006, 116, 90-94.
[28] Qiu, S.; Wang, J.; Gao, L. Discrimination and characterization of strawberry juice based on electronic nose and tongue: Comparison of different juice processing approaches by LDA, PLSR, RF, and SVM. J. Agric. Food Chem. 2014, 62, 6426-6434.
[29] Tang, K.T.; Chiu, S.W.; Pan, C.H.; Hsieh, H.Y.; Liang, Y.S.; Liu, S.C. Development of a portable electronic nose system for the detection and classification of fruity odors. Sensors 2010, 10, 9179-9193.
[30] Shao, X.; Li, H.; Wang, N.; Zhang, Q. Comparison of different classification methods for analyzing electronic nose data to characterize sesame oils and blends. Sensors 2015, 15, 26726-22674.
[31] Brudzewski, K.; Osowski, S.; Markiewicz, T.; Ulaczyk, J. Classification of gasoline with supplement of bio-products by means of an electronic nose and SVM neural network. Sensors Actuat. B Chem. 2006, 113, 135-141.
[32] Arlot, S.; Celisse, A. A survey of cross-validation procedures for model selection. Statist. Surv. 2010, 4, 40-79.
[33] Dadzie, B.K.; Orchard, J.E. Routine Post-Harvest Screening of Banana/Plantain Hybrids: Criteria and Methods. INIBAP Technical Guidelines 2; International Plant Genetic Resources Institute 1997, 5-30.
[34] Le, M.; Slaughter, D.C.; Thompson, J.E. Optical chlorophyll sensing system for banana ripening. Postharvest Biol. Technol. 1997, 12, 273-83.
[35] Wang, X.; Syrmos, V.L. Optimal Cluster Selection Based on Fisher Class Separability Measure. In Proceedings of the American Control Conference, 2005, 3, 1929-1934.