Main content

Neural Network Compound Predictor For Spirits in an Electronic Nose

Show simple item record

dc.contributor.advisor Muresan, Radu Littel, Robert 2014-02-13T20:11:16Z 2014-02-13T20:11:16Z 2014-02 2014-02-07 2014-02-13
dc.description This work is an attempt to create an electronic nose prototype to investigate the analysis of high concentration spirits from chemical sensors. A 12 MOS sensor custom fabricated electronic nose was developed to attempt to classify the off compounds associated with Whisky and other popular alcoholic beverages. This classification will be accomplished through signal response feature extraction and a back propagating neural network. Mixed concentrations of Ethanol, Ethyl Acetate, and Isopropyl Alcohol will be analyzed for classification. en_US
dc.description.abstract An electronic nose was designed to investigate the digital response from MOS sensors for high concentration Ethanol spirits. Hardware was custom designed, and fabricated to classify spirits with 12 sensors for further analysis with a neural network. Electronic noses have been used for quality control with various foods and beverages in the past. Methods for classification and post processing techniques have varied from numerous publications. The popular methods used in the industry have been presented and their corresponding effectiveness has been analyzed. A systematic procedure has been created which can be used to recreate results for future sample collections. Seven different sensors were used to record time dependant chemical responses in a controlled environment. The sample responses were further used to acquire 7 unique features defining each sensor’s response. These 49 features were used as the inputs into a 45 hidden node, 3 node output, back propagating neural network. This network was able to classify 5µL samples of mixed concentrations of Ethanol, Ethyl Acetate and Isopropyl Alcohol to within 12.5% accuracy. en_US
dc.description.sponsorship Pernod-Ricard (Project No. TP-SW-11168-11) and Ontario Centres of Excellence (OCE) en_US
dc.language.iso en en_US
dc.rights Attribution 2.5 Canada *
dc.rights.uri *
dc.subject Electronic Nose en_US
dc.subject Ethanol en_US
dc.subject Neural Network en_US
dc.subject Classifier en_US
dc.subject Whisky en_US
dc.subject Whiskey en_US
dc.subject Sensor Array en_US
dc.subject Air Filtration en_US
dc.title Neural Network Compound Predictor For Spirits in an Electronic Nose en_US
dc.type Thesis en_US Engineering en_US Master of Science en_US School of Engineering en_US
dc.rights.license All items in the Atrium are protected by copyright with all rights reserved unless otherwise indicated.

Files in this item

Files Size Format View
Littel_Robert_201402_MASc.pdf 3.174Mb PDF View/Open

This item appears in the following Collection(s)

Show simple item record

Attribution 2.5 Canada Except where otherwise noted, this item's license is described as Attribution 2.5 Canada