飲食在人們的日常生活中有舉足輕重的影響，對食物品質的要求也不斷提升。在面對食品行業中不斷出現的食安問題，社會大眾希望利用更先進且準確的方法來保障消費者的權益。近年隨著科技的進步，越來越多的研究團隊開始探索利用低成本的感測器來檢測食品，取代傳統的人工檢測或昂貴的儀器分析。
本研究以咖啡和烈酒作為範例，藉由偵測咖啡與烈酒中的揮發性有機化合物(Volatile Organic Compounds, VOCs)，選取兩組各8種不同的感測器，透過自主研發的電子鼻系統來收集數種咖啡豆產區以及烈酒種類的氣味特性。並將收集到的氣味特徵輸入模型進行訓練，同時比較在不同機器學習模型的學習成效。本實驗模利用線性判別分析 (Linear Discriminant Analysis, LDA)與主成分分析 (Principal Component Analysis, PCA)做資料降維處理，並利用降維取得的特徵放入模型作訓練，並採用四種模型:極限梯度提升(eXtreme Gradient Boosting, XGBoos)、支持向量機 (Support Vector Machine, SVM)、卷積神經網路 (Convolutional Neural Network, CNN)與CNN-LSTM。本研究的主要目標是對食品中的氣味進行分析，以便在咖啡和烈酒的生產過程中檢測出任何可能的品質問題，進而防止不合格的產品流入市場，能讓消費者更加了解咖啡及烈酒的產地與種類。透過這項研究不僅可以提升消費者的滿意度，也可以對食品業中的不良經營者產生警示作用，並且有助於食品業者的創新和開發。

The diet has a significant impact on people's daily lives, and the requirements for food quality are also increasing.Faced with the rising food security issues in the food industry, the public wants to use more advanced and accurate methods to safeguard consumer rights.With technological advances in recent years, more and more research teams have begun to explore the use of low-cost sensors to detect foods, replacing traditional artificial detection or expensive instrument analysis.
Using coffee and spirits as examples, the study selected two sets of eight different sensors by detecting volatile organic compounds (VOCs) in coffee and Spirits, and collected the odor properties of several coffee bean grown areas as well as spirits through an independently developed electronic nose system.And the accumulated odor characteristics input models will be trained while comparing learning outcomes across different machine learning models.This experimental module uses linear discriminant analysis (LDA) and primary component analysis (PCA) for data degradation processing, and uses the characteristics obtained from the degeneration to be put into the model for training, and adopts four models: eXtreme Gradient Boosting (XGBoos), Support Vector Machine (SVM), Convolutional Neural Network (CNN) and CNN-LSTM.The main objective of this study is to analyze the odors in foods in order to detect any possible quality problems in the production process of coffee and spirits, thereby preventing the flow of unqualified products into the market, and to give consumers a better understanding of the origin and type of coffee or spirits.This study not only boosts consumer satisfaction, but also warns of bad operators in the food industry, and contributes to innovation and development in food industry.

目 錄
摘 要 i
ABSTRACT ii
誌 謝 iii
目 錄 iv
表目錄 vi
圖 目 錄 vii
第一章 緒論 1
1.1 前言 1
1.2 研究背景 2
1.3 研究動機與目的 4
1.4 研究步驟 4
1.5 論文組織架構 5
第二章 文獻與相關技術之探討 6
2.1 食品詐欺的介紹 6
2.2 食品詐欺的檢測方式 7
2.2.1 傳統檢測方式 7
2.2.2 現代科技檢測方式 8
2.3 食品科技檢測的方法 8
2.3.1 視覺檢測 9
2.3.2 嗅覺檢測 10
2.3.3 味覺檢測 10
2.3.4 觸覺檢測 11
2.4 感測器應用於食品詐欺 11
2.4.1 光譜成像 12
2.4.2 電子鼻 12
2.5 電子鼻技術結合食品檢測 13
第三章 研究方法 15
3.1 電子鼻相關介紹 16
3.1.1 感測器介紹 16
3.1.2 選擇感測器 17
3.1.3 電子鼻架構 19

3.2 資料處理 21
3.2.1 正規化 21
3.2.2 線性判別分析 22
3.2.3 主成分分析 22
3.3 深度學習相關技術 23
3.3.1 激勵函數(Activation Function) 26
3.3.2 損失函數(Loss Funciton) 26
3.3.3 優化器(Optimizer) 27
3.3.4 XGBoost 27
3.3.5 支持向量機 28
3.3.6 卷積神經網路模型 28
3.3.7 CNN-LSTM 29
第四章 實驗架構與流程設計 31
4.1 實驗架構 31
4.2 收集數據 32
4.2.1 咖啡數據 32
4.2.2 烈酒數據 33
4.3 資料前處理 35
4.4 模型建置與參數設定 37
4.5 實驗結果與評估 40
4.5.1 咖啡氣味分類實驗用於PCA之實驗結果與表現 40
4.5.2 咖啡氣味分類實驗用於LDA之實驗結果與表現 45
4.5.3 烈酒氣味用於PCA之實驗結果與表現 50
4.5.4 烈酒氣味用於LDA之實驗結果與表現 54
第五章 實驗結果討論 60
第六章 未來工作 61
參考文獻 62
附錄 67

參考文獻
[1]Goyal, K., Kumar, P., & Verma, K. (2022). Food adulteration detection using artificial intelligence: A systematic review. Archives of Computational Methods in Engineering, 29(1), 397-426.
[2]Winickoff, D. E., & Bushey, D. M. (2010). Science and power in global food regulation: The rise of the codex alimentarius. Science, Technology, & Human Values, 35(3), 356-381.
[3]Trienekens, J., & Zuurbier, P. (2008). Quality and safety standards in the food industry, developments and challenges. International journal of production economics, 113(1), 107-122.
[4]Savov, A. V., & Kouzmanov, G. B. (2009). Food quality and safety standards at a glance. Biotechnology & Biotechnological Equipment, 23(4), 1462-1468.
[5]Peng, G. J., Chang, M. H., Fang, M., Liao, C. D., Tsai, C. F., Tseng, S. H., ... & Cheng, H. F. (2017). Incidents of major food adulteration in Taiwan between 2011 and 2015. Food Control, 72, 145-152.
[6]Tian, F. (2017, June). A supply chain traceability system for food safety based on HACCP, blockchain & Internet of things. In 2017 International conference on service systems and service management (pp. 1-6). IEEE.
[7]Bansal, S., Singh, A., Mangal, M., Mangal, A. K., & Kumar, S. (2017). Food adulteration: Sources, health risks, and detection methods. Critical reviews in food science and nutrition, 57(6), 1174-1189.
[8]Cheng, J. H., Sun, D. W., Han, Z., & Zeng, X. A. (2014). Texture and structure measurements and analyses for evaluation of fish and fillet freshness quality: a review. Comprehensive Reviews in Food Science and Food Safety, 13(1), 52-61.
[9]He, H. J., & Sun, D. W. (2015). Microbial evaluation of raw and processed food products by Visible/Infrared, Raman and Fluorescence spectroscopy. Trends in food science & technology, 46(2), 199-210.
[10]Hassoun, A., Sahar, A., Lakhal, L., & Aït-Kaddour, A. (2019). Fluorescence spectroscopy as a rapid and non-destructive method for monitoring quality and authenticity of fish and meat products: Impact of different preservation conditions. Lwt, 103, 279-292.
[11]Li, T. T., Jalbani, Y. M., Zhang, G. L., Zhao, Z. Y., Wang, Z. Y., Zhao, X. Y., & Chen, A. L. (2019). Detection of goat meat adulteration by real-time PCR based on a reference primer. Food Chemistry, 277, 554-557.
[12]Griesche, C., & Baeumner, A. J. (2020). Biosensors to support sustainable agriculture and food safety. TrAC Trends in Analytical Chemistry, 128, 115906.
[13]Orrillo, I., Cruz-Tirado, J. P., Cardenas, A., Oruna, M., Carnero, A., Barbin, D. F., & Siche, R. (2019). Hyperspectral imaging as a powerful tool for identification of papaya seeds in black pepper. Food Control, 101, 45-52.
[14]Jahanbakhshi, A., Abbaspour-Gilandeh, Y., Heidarbeigi, K., & Momeny, M. (2021). Detection of fraud in ginger powder using an automatic sorting system based on image processing technique and deep learning. Computers in biology and medicine, 136, 104764.
[15]Chakravartula, S. S. N., Moscetti, R., Bedini, G., Nardella, M., & Massantini, R. (2022). Use of convolutional neural network (CNN) combined with FT-NIR spectroscopy to predict food adulteration: A case study on coffee. Food Control, 135, 108816.
[16]Pu, M., Li, X., Ma, X., Wang, Y., Zhao, Z., Wang, C., ... & Luo, X. (2015). Catenary optics for achromatic generation of perfect optical angular momentum. Science Advances, 1(9), e1500396.
[17]Haff, R. P., & Toyofuku, N. (2008). X-ray detection of defects and contaminants in the food industry. Sensing and Instrumentation for Food Quality and Safety, 2, 262-273.
[18]Saxe, J., & Berlin, K. (2017). eXpose: A character-level convolutional neural network with embeddings for detecting malicious URLs, file paths and registry keys. arXiv preprint arXiv:1702.08568.
[19]Woertz, K., Tissen, C., Kleinebudde, P., & Breitkreutz, J. (2011). Taste sensing systems (electronic tongues) for pharmaceutical applications. International journal of pharmaceutics, 417(1-2), 256-271.
[20]Baldwin, E. A., Bai, J., Plotto, A., & Dea, S. (2011). Electronic noses and tongues: Applications for the food and pharmaceutical industries. Sensors, 11, 4744-4766.
[21]Dargahi, J., & Najarian, S. (2005). Advances in tactile sensors design/manufacturing and its impact on robotics applications–a review. Industrial Robot: An International Journal, 32(3), 268-281.
[22]Ribeiro, P., Cardoso, S., Bernardino, A., & Jamone, L. (2020, October). Fruit quality control by surface analysis using a bio-inspired soft tactile sensor. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 8875-8881). IEEE.
[23]Ali, M. M., Hashim, N., Abd Aziz, S., & Lasekan, O. (2020). Emerging non-destructive thermal imaging technique coupled with chemometrics on quality and safety inspection in food and agriculture. Trends in Food Science & Technology, 105, 176-185.
[24]Wang, J., Li, D., Ye, Y., Qiu, Y., Liu, J., Huang, L., ... & Chen, B. (2021). A fluorescent metal–organic framework for food real‐time visual monitoring. Advanced Materials, 33(15), 2008020.
[25]Vasquez, J. A. T., Scapaticci, R., Turvani, G., Ricci, M., Farina, L., Litman, A., ... & Vipiana, F. (2020). Noninvasive inline food inspection via microwave imaging technology: An application example in the food industry. IEEE Antennas and Propagation Magazine, 62(5), 18-32.
[26]Kim, C., Lee, K. K., Kang, M. S., Shin, D. M., Oh, J. W., Lee, C. S., & Han, D. W. (2022). Artificial olfactory sensor technology that mimics the olfactory mechanism: A comprehensive review. Biomaterials Research, 26(1), 1-13.
[27]Ali, M. M., Hashim, N., Abd Aziz, S., & Lasekan, O. (2020). Principles and recent advances in electronic nose for quality inspection of agricultural and food products. Trends in Food Science & Technology, 99, 1-10.
[28]Wu, X., & Toko, K. (2022). Taste sensor with multiarray lipid/polymer membranes. TrAC Trends in Analytical Chemistry, 116874.
[29]Fujimoto, H., Narita, Y., Iwai, K., Hanzawa, T., Kobayashi, T., Kakiuchi, M., ... & Toko, K. (2021). Bitterness compounds in coffee brew measured by analytical instruments and taste sensing system. Food Chemistry, 342, 128228.
[30]Christopher, C. T., Fath Elbab, A. M., Osueke, C. O., Ikua, B. W., Sila, D. N., & Fouly, A. (2022). A piezoresistive dual-tip stiffness tactile sensor for mango ripeness assessment. Cogent Engineering, 9(1), 2030098.
[31]Ribeiro, P., Cardoso, S., Bernardino, A., & Jamone, L. (2020, October). Fruit quality control by surface analysis using a bio-inspired soft tactile sensor. In 2020 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) (pp. 8875-8881). IEEE.
[32]Li, S., Simonian, A., & Chin, B. A. (2010). Sensors for agriculture and the food industry. The Electrochemical Society Interface, 19(4), 41.
[33]Ma, J., Sun, D. W., Pu, H., Cheng, J. H., & Wei, Q. (2019). Advanced techniques for hyperspectral imaging in the food industry: Principles and recent applications. Annual review of food science and technology, 10, 197-220.
[34]Saha, D., & Manickavasagan, A. (2021). Machine learning techniques for analysis of hyperspectral images to determine quality of food products: A review. Current Research in Food Science, 4, 28-44.
[35]Roy, M., & Yadav, B. K. (2021). Electronic nose for detection of food adulteration: A review. Journal of Food Science and Technology, 1-13.
[36]Gliszczyńska-Świgło, A., & Chmielewski, J. (2017). Electronic nose as a tool for monitoring the authenticity of food. A review. Food Analytical Methods, 10, 1800-1816.
[37]Yuan, H., Chen, X., Shao, Y., Cheng, Y., Yang, Y., Zhang, M., ... & Wu, Z. (2019). Quality evaluation of green and dark tea grade using electronic nose and multivariate statistical analysis. Journal of food science, 84(12), 3411-3417.
[38]Wilson, A. D., & Baietto, M. (2009). Applications and advances in electronic-nose technologies. sensors, 9(7), 5099-5148.
[39]Mahmoudi, E. (2009). Electronic nose technology and its applications. Sensors & Transducers, 107(8), 17.
[40]Ghasemi-Varnamkhasti, M., Mohtasebi, S. S., Siadat, M., & Balasubramanian, S. (2009). Meat quality assessment by electronic nose (machine olfaction technology). Sensors, 9(8), 6058-6083.
[41]O’Connell, M., Valdora, G., Peltzer, G., & Negri, R. M. (2001). A practical approach for fish freshness determinations using a portable electronic nose. Sensors and Actuators B: chemical, 80(2), 149-154.
[42]Pardo, M., & Sberveglieri, G. (2002). Coffee analysis with an electronic nose. IEEE Transactions on Instrumentation and Measurement, 51(6), 1334-1339.
[43]Dutta, R., Kashwan, K. R., Bhuyan, M., Hines, E. L., & Gardner, J. W. (2003). Electronic nose based tea quality standardization. Neural Networks, 16(5-6), 847-853.
[44]Martı́, M. P., Busto, O., Guasch, J., & Boqué, R. (2005). Electronic noses in the quality control of alcoholic beverages. TrAC Trends in Analytical Chemistry, 24(1), 57-66.
[45]Hong, X., Wang, J., & Hai, Z. (2012). Discrimination and prediction of multiple beef freshness indexes based on electronic nose. Sensors and Actuators B: Chemical, 161(1), 381-389.
[46]GholamHosseini, H., Luo, D., Liu, H., & Xu, G. (2007, December). Intelligent processing of E-nose information for fish freshness assessment. In 2007 3rd International Conference on Intelligent Sensors, Sensor Networks and Information (pp. 173-177). IEEE.
[47]Barea-Ramos, J. D., Cascos, G., Mesías, M., Lozano, J., & Martín-Vertedor, D. (2022). Evaluation of the Olfactory Quality of Roasted Coffee Beans Using a Digital Nose. Sensors, 22(22), 8654.
[48]Lu, X., Wang, J., Lu, G., Lin, B., Chang, M., & He, W. (2019). Quality level identification of West Lake Longjing green tea using electronic nose. Sensors and Actuators B: Chemical, 301, 127056.
[49]Viejo, C. G., Fuentes, S., Godbole, A., Widdicombe, B., & Unnithan, R. R. (2020). Development of a low-cost e-nose to assess aroma profiles: An artificial intelligence application to assess beer quality. Sensors and Actuators B: Chemical, 308, 127688.
[50]Falasconi, M., Concina, I., Gobbi, E., Sberveglieri, V., Pulvirenti, A., & Sberveglieri, G. (2012). Electronic nose for microbiological quality control of food products. International Journal of Electrochemistry, 2012.
[51]Röck, F., Barsan, N., & Weimar, U. (2008). Electronic nose: current status and future trends. Chemical reviews, 108(2), 705-725.
[52]Mombaerts, P. (1999). Odorant receptor genes in humans. Current opinion in genetics & development, 9(3), 315-320.
[53]Illy, A., & Viani, R. (Eds.). (2005). Espresso coffee: the science of quality. Academic Press.
[54]Lee, C. H., Chen, I. T., Yang, H. C., & Chen, Y. J. (2022). An AI-powered Electronic Nose System with Fingerprint Extraction for Aroma Recognition of Coffee Beans. Micromachines, 13(8), 1313.
[55]Rehm, J., Kanteres, F., & Lachenmeier, D. W. (2010). Unrecorded consumption, quality of alcohol and health consequences. Drug and alcohol review, 29(4), 426-436.
[56]Budner, D., Bell, L., & Thompson-Witrick, K. (2023). The BooZi device’s effect on aroma compounds in distilled spirits. Journal of the South Carolina Academy of Science, 21(1), 5.
[57]Jung, A., Jung, H., Auwärter, V., Pollak, S., Farr, A. M., Hecser, L., & Schiopu, A. (2010). Volatile congeners in alcoholic beverages: analysis and forensic significance. Rom. J. Leg. Med, 18(4), 265-270.