Abstract—Electronic Nose employs an array of gas sensors and has been widely used in many specific applications for the analysis of gas composition. In this study, electronic nose, integrating ten MQ gas sensors, is intended to model olfactory system which generally classifies smells based on ten basic categories namely: fragrant, sweet, woody/resinous, pungent, peppermint, decaying, chemical, citrus, fruity, and popcorn using artificial neural network as its pattern recognition algorithm. Initial results suggest that four (Pungent, Chemical, Peppermint, and Decaying) among the ten classifications are detectable by the sensors commercially available today while technology for classifying the remaining six is still under development. Meanwhile, results provided by this study affirm that electronic nose indeed displays a potential of modelling olfactory system.
 

Index Terms—electronic nose, MQ gas sensors, artificial neural network, pattern recognition

Cite: Dailyne Macasaet, Argel Bandala, Ana Antoniette Illahi, Elmer Dadios, Sandy Lauguico, and Jonnel Alejandrino, "Development of an Electronic Nose for Smell Categorization Using Artificial Neural Network," Journal of Advances in Information Technology, Vol. 12, No. 1, pp. 36-44, February 2021. doi: 10.12720/jait.12.1.36-44

Copyright © 2021 by the authors. This is an open access article distributed under the Creative Commons Attribution License (CC BY-NC-ND 4.0), which permits use, distribution and reproduction in any medium, provided that the article is properly cited, the use is non-commercial and no modifications or adaptations are made.