The objective of this study was to prove the general applicability of an GC-TD-MS machine for analyzing different types of coffee beans like roasted coffee aroma considering the dependency of different roasting levels usually we analyzed the gas chromatograms obtained for the four different roast levels (from A to D) of coffee beans, Robusta coffee beans from Guatemala considering the raw coffee and yeast treated coffee and finally we concluded our study for coffee beans obtained from four different geographic origin coffee beans from Africa. This thesis proposes methods to analyze volatile organic compounds obtained from GC-TD-MS machine. First, a general data analysis methodology was proposed to analyze the data set obtained from the TD-GC-MS. The proposed methodology constitutes of five steps Data collection, Data cleaning, explanatory data analysis, Building supervised classification models and in the final phase we concluded the overall classification accuracy obtained. Raw Data obtained from TD-GC-MS, data cleaning is performed by using MS-access, MS-Excel and important compounds chosen for further analysis, in the explanatory model we used bar chart to plot mean values to measure the tendency of roasted coffee beans and PCA is used in explanatory phase to find pattern in discriminating roasted coffee, coffee stored under different temperature, finally used in discriminating different geographic coffee. In classification modeling phase supervised methods such as KNN and LDA are used to discriminate different coffee beans stored under room temperature and refrigerator temperature in the final phase we concluded i.e. specific process work of TD-GC-MS tool system for measuring gaseous compounds of different specimens. And it's practical and beneficial of the research for the coffee preparation.

References
[1]. Woolfenden, E., Sorbent-based sampling methods for volatile and semi-volatile organic compounds in air. Part 2. Sorbent selection and other aspects of optimizing air monitoring methods. Journal of Chromatography A, 2010. 1217(16): p. 2685-2694.
[2]. Wang, S.-C., Artificial Neural Network, in Interdisciplinary Computing in Java Programming. 2003, Springer US. p. 81-100.
[3]. Shimoda, M. and T. Shibamoto, Isolation and identification of headspace volatiles from brewed coffee with an on-column GC/MS method. Journal of Agricultural and Food Chemistry, 1990. 38(3): p. 802-804.
[4]. Pérez-Martínez, M., et al., Changes in volatile compounds and overall aroma profile during storage of coffee brews at 4 and 25 C. Journal of agricultural and food chemistry, 2008. 56(9): p. 3145-3154.
[5]. Gören*, A.C., et al., Analysis of essential oil of Satureja thymbra by hydrodistillation, thermal desorber, and headspace GC/MS techniques and its antimicrobial activity. Natural product research, 2004. 18(2): p. 189-195.
[6]. Helmig, D. and J.P. Greenberg, Automated in situ gas chromatographic-mass spectrometric analysis of ppt level volatile organic trace gases using multistage solid-adsorbent trapping. Journal of Chromatography A, 1994. 677(1): p. 123-132.
[7]. Li, C.-H., et al. Using TD-GC-MS to analyze coffee beans aromas of different roast levels. in Nano/Micro Engineered and Molecular Systems (NEMS), 2014 9th IEEE International Conference on. 2014. IEEE.
[8]. Fisk, I., et al., Discrimination of roast and ground coffee aroma. Flavour, 2012. 1(1): p. 14.
[9]. Witt, K., S. Reulecke, and A. Voss. Discrimination and characterization of breath from smokers and non-smokers via electronic nose and GC/MS analysis. in Engineering in Medicine and Biology Society,EMBC, 2011 Annual International Conference of the IEEE. 2011.
[10]. Schaller, E., J.O. Bosset, and F. Escher, ‘Electronic Noses’ and Their Application to Food. LWT - Food Science and Technology, 1998. 31(4): p. 305-316.
[11]. Jurs, P.C., G.A. Bakken, and H.E. McClelland, Computational Methods for the Analysis of Chemical Sensor Array Data from Volatile Analytes. Chemical Reviews, 2000. 100(7): p. 2649-2678.
[12]. Guo, D., D. Zhang, and L. Zhang, Sparse representation-based classification for breath sample identification. Sensors and Actuators B: Chemical, 2011. 158(1): p. 43-53.
[13]. Rui, X. and D. Wunsch, II, Survey of clustering algorithms. Neural Networks, IEEE Transactions on, 2005. 16(3): p. 645-678.
[14]. MacQueen, J. Some methods for classification and analysis of multivariate observations. in Proceedings of the fifth Berkeley symposium on mathematical statistics and probability. 1967. California, USA.
[15]. Hartigan, J.A. and M.A. Wong, Algorithm AS 136: A k-means clustering algorithm. Applied statistics, 1979: p. 100-108.
[16]. Holte, R.C., Very simple classification rules perform well on most commonly used datasets. Machine learning, 1993. 11(1): p. 63-90.
[17]. Pham, D.T. and M. Aksoy, An algorithm for automatic rule induction. Artificial Intelligence in Engineering, 1993. 8(4): p. 277-282.
[18]. Wu, X., Inductive learning: Algorithms and frontiers. Artificial Intelligence Review, 1993. 7(2): p. 93-108.
[19]. Bicego, M., et al., A comparative analysis of basic pattern recognition techniques for the development of small size electronic nose. Sensors and Actuators B: Chemical, 2002. 85(1): p. 137-144.
[20]. Gómez, A.H., et al., Evaluation of tomato maturity by electronic nose. Computers and electronics in agriculture, 2006. 54(1): p. 44-52.
[21]. Yu, H., et al., Identification of green tea grade using different feature of response signal from E-nose sensors. Sensors and Actuators B: Chemical, 2008. 128(2): p. 455-461.
[22]. Shi, Z.-b., et al., Comparison of algorithms for an electronic nose in identifying liquors. Journal of Bionic Engineering, 2008. 5(3): p. 253-257.
[23]. GholamHosseini, H., et al. Intelligent processing of E-nose information for fish freshness assessment. in Intelligent Sensors, Sensor Networks and Information, 2007. ISSNIP 2007. 3rd International Conference on. 2007. IEEE.
[24]. Martinez, A.M. and A.C. Kak, PCA versus LDA. Pattern Analysis and Machine Intelligence, IEEE Transactions on, 2001. 23(2): p. 228-233.
[25]. Fisk, I.D. and A.T. Massey, Composition for Preparing a Beverage or Food Product Comprising a Plurality Insoluble Material Bodies. 2011, Google Patents.
[26]. Semmelroch, P. and W. Grosch, Studies on character impact odorants of coffee brews. Journal of Agricultural and Food Chemistry, 1996. 44(2): p. 537-543.
[27]. Mancha Agresti, P.D., et al., Discrimination between defective and non-defective Brazilian coffee beans by their volatile profile. Food chemistry, 2008. 106(2): p. 787-796.
[28]. Silva, E.A.d., et al., The influence of water management and environmental conditions on the chemical composition and beverage quality of coffee beans. Brazilian Journal of Plant Physiology, 2005. 17(2): p. 229-238.
[29]. Risticevic, S., E. Carasek, and J. Pawliszyn, Headspace solid-phase microextraction–gas chromatographic–time-of-flight mass spectrometric methodology for geographical origin verification of coffee. Analytica chimica acta, 2008. 617(1): p. 72-84.
[30]. Franca, A.S., et al., A preliminary evaluation of the effect of processing temperature on coffee roasting degree assessment. Journal of food engineering, 2009. 92(3): p. 345-352.
[31]. Bhumiratana, N., K. Adhikari, and E. Chambers IV, Evolution of sensory aroma attributes from coffee beans to brewed coffee. LWT-Food Science and Technology, 2011. 44(10): p. 2185-2192.
[32]. Gonzalez-Rios, O., et al., Impact of “ecological” post-harvest processing on coffee aroma: II. Roasted coffee. Journal of food composition and analysis, 2007. 20(3): p. 297-307.
[33]. Bröhan, M., et al., Influence of storage conditions on aroma compounds in coffee pads using static headspace GC–MS. Food chemistry, 2009. 116(2): p. 480-483.
[34]. Fisk, I.D., et al., Gamma-irradiation as a method of microbiological control, and its impact on the oxidative labile lipid component of Cannabis sativa and Helianthus annus. European Food Research and Technology, 2009. 228(4): p. 613-621.
[35]. BudryN, G., et al., HS-SPME/GC/MS profiles of convectively and microwave roasted Ivory Coast Robusta coffee brews. Czech J Food Sci, 2011. 29: p. 151-160.
[36]. Cantergiani, E., et al., Characterisation of the aroma of green Mexican coffee and identification of mouldy/earthy defect. European Food Research and Technology, 2001. 212(6): p. 648-657.
[37]. Holscher, W. and H. Steinhart, Aroma compounds in green coffee. Developments in Food Science, 1995. 37: p. 785-803.
[38]. Wu, S., A review on coarse warranty data and analysis. Reliability Engineering & System Safety, 2013. 114(0): p. 1-11.
[39]. Dettmer, K. and W. Engewald, Ambient air analysis of volatile organic compounds using adsorptive enrichment. Chromatographia, 2003. 57(1): p. S339-S347.
[40]. Holscher, W. and H. Steinhart, Investigation of roasted coffee freshness with an improved headspace technique. Zeitschrift für Lebensmittel-Untersuchung und Forschung, 1992. 195(1): p. 33-38.
[41]. Hofmann, T., et al., Model studies on the influence of coffee melanoidins on flavor volatiles of coffee beverages. Journal of agricultural and food chemistry, 2001. 49(5): p. 2382-2386.
[42]. Müller, C. and T. Hofmann, Quantitative studies on the formation of phenol/2-furfurylthiol conjugates in coffee beverages toward the understanding of the molecular mechanisms of coffee aroma staling. Journal of agricultural and food chemistry, 2007. 55(10): p. 4095-4102.
[43]. Jolliffe, I., Principal component analysis. 2005: Wiley Online Library.
[44]. Guo, G., et al., KNN model-based approach in classification, in On The Move to Meaningful Internet Systems 2003: CoopIS, DOA, and ODBASE. 2003, Springer. p. 986-996.
[45]. Sarrazin, C., et al., Representativeness of coffee aroma extracts: a comparison of different extraction methods. Food Chemistry, 2000. 70(1): p. 99-106.
[46]. Hao, H., et al., Development of a portable electronic nose based on chemical surface acoustic wave array with multiplexed oscillator and readout electronics. Sensors and Actuators B: Chemical, 2010. 146(2): p. 545-553.