Development of an Electronic Nose for Olfactory System Modelling using Artificial Neural Network
Electronic nose (e-nose) devices have received considerable attention in the field of sensor technology because of their many potential uses such as in identification of toxic wastes, monitoring air quality, examining odors in infected wounds and in inspection of food. Notwithstanding the vast amount of literature on the usage of e-noses for specific purposes, the technology originally and ultimately aims to mimic the capability of mammals to discriminate odors from all sorts of objects. This study demonstrates the theoretical and practical feasibility of designing an e-nose towards general odor classification. A multi-sensor array hardware unit was carefully constructed for data collection and odor detection. Important hardware design considerations such as sensor calibration, aeration, circuit protection, and voltage/current requirements were satisfied. A highly fine-tuned artificial neural network (ANN) was integrated to the hardware to interpret and relate the data to a target odor class from a set of 10 primary odors identified in a previous study. Various network architecture considerations, such as neuron count, number of layers and activation function, as well as various data treatment methods, such as normalization, and data partitioning, were investigated. The results showed that careful hardware integration with an ANN having sufficiently deep internal structure can yield accurate classification to at least half of the ten primary odor classes, namely fragrant (96%), fruity (98%), chemical (99%), peppermint (98%), and popcorn (90%). The results demonstrate the feasibility of making e-noses for general odor classification, which could lead to further broadening of e-nose applications.
(1) Barwich, “A sense so rare: measuring olfactory experiences and making a case for a process perspective on sensory perception.” Biol Theory 9:258–268, 2014.
(2) L. Harman, “Human relationship with fragrance,” In: The chemistry of fragrances: from perfumer to consumer. Royal Society of Chemistry, Cambridge, 2006, pp 1–2.
(3) D. Schild and J.W. Gardner, “Detection and coding of chemical signals: a omparison between artificial and biological systems,” University of Warwick, 1991.
(4) N. Barsan, and U. Weimar, “Electronic nose: current status and future trends,” Institute of Physical and Theoretical Chemistry, University of Tubingen, Germany, 2008.
(5) K. Persaud, and G. Dodd, “Analysis of discrimination mechanisms in the mammalian olfactory system using a model nose,” Nature. 299:352–355, 1982.
(6) P.E. Keller, R.T. Kouzes, and L.J. Kangas, “Three neural network based sensor systems for environmental monitoring,” IEEE Electro 94 Conference Proceedings, Boston, MA, 1994, pp.377-382.
(7) R.J. Lauf and B.S. Hoffheins, “Analysis of liquid fuels using a gas sensor array,” Fuel , vol. 70, 1991, pp. 935-940.
(8) H.V. Shurmur, “The fifth sense: on the scent of the electronic nose,” IEEE Review, March 1990, pp. 95-58.
(9) Amico, A. Natale, C. Paolesse, and R. Macagnano, “Olfactory systems for medical applications” Sens. Actuators B Chem., 1, 2008, 458–465.
(10) I.A.Casalinuovo, D. di Pierro, M. Coletta, P. di Francesco, “Application electronic noses for disease diagnosis and food spoilage detection,” Sensors, 6, 2008, 1428–1439.
(11) H. Sun, F. Tian and Z. Liang, “Sensor array optimization of electronic nose for detection of bacteria in wound infection,” IEEE Transactions on Industrial Electronics, Volume 64, Issue 9, 2017.
(12) Norah Trent, “ Global Electronic Nose Industry 2016 Market Research Report,“ 2016.
(13) J. Castro, A. Ramanathan, and C. Chennubhotla, “Categorical
dimensions of human odor descriptor space revealed by non-negative matrix factorization,” 2013.
(14) M. Roa and P. Fernandez, “A study of the effect of network architecture in artificial neural network performance applied to electronic olfactory device, National Graduate Student Leadership and Research
Conference, Laguna, Philippines, 18-19 August 2016.
(15) M. Roa and P. Fernandez, “Study on optimization of artificial neural network generalization power based on architecture,” Proceedings of 90th The IIER International Conference, Dubai, UAE, 1st-2nd January 2017, ISBN: 978-93-86291-78-3.
(16) M. Roa and P. Fernandez, “An empirical study of different artificial neural network activation functions applied to five classification problems,” submitted, 2017.
(17) M. Roa and P. Fernandez, “Development of an Electronic Nose for Olfactory System Modelling using Artificial Neural Network,“ 2018. [Online]. Available: https://www.researchgate.net/project/Development-of-an-Electronic-Nose-for-Olfactory-System-Modelling-using-Artificial-Neural-Network
(18) S. Glen, “Alpha Level (Significance Level): What is it? Retrieved,” 2012. from: http://www.statisticshowto.com/what-is-an-alpha-level/