Skip to main content
Presentation
Fuzzy logic and artificial neural network approaches in odor detection
Faculty of Engineering and Information Sciences - Papers
  • Lasantha Meegahapola, University of Moratuwa
  • J P Karunadasa, University of Moratuwa
  • Kasun Sandasiri, University of Moratuwa
  • Damith Tharanga, University of Moratuwa
  • Dammika Jayasekara, University of Moratuwa
RIS ID
41312
Publication Date
1-1-2006
Publication Details

L. Meegahapola, J. P. Karunadasa, K. Sandasiri, D. Tharanga & D. Jayasekara, "Fuzzy logic and artificial neural network approaches in odor detection," in 2nd International Conference on Information and Automation, ICIA 2006, 2006, pp. 92-97.

Abstract

This paper presents the research segment of development of methodology for determining odor level of various applications using two different concepts; Fuzzy logic based algorithm and Artificial Neural Network (ANN) based algorithm. Three different gas sensors are used which respond to ammonia (NH3), hydrogen sulfide (H2S) and methane (CH4). Sensory fusion is achieved through processing the analog to digital converted values of sensor outputs using the algorithm to determine the odor level of various types of predetermined odors. Olfactometry was used to determine the desired outputs (odor levels) of the algorithms. Fuzzy logic algorithm uses Zadeh-Mamdani type Fuzzy inference system and the neural network approach uses feedforward backpropogation algorithm. Further this paper presents some results based on gathered data from various odor-emitting sources.

Citation Information
Lasantha Meegahapola, J P Karunadasa, Kasun Sandasiri, Damith Tharanga, et al.. "Fuzzy logic and artificial neural network approaches in odor detection" (2006)
Available at: http://works.bepress.com/lasantha_meegahapola/5/