Title

Fuzzy logic and artificial neural network approaches in odor detection

RIS ID

41312

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.

Please refer to publisher version or contact your library.

Share

COinS
 

Link to publisher version (DOI)

http://dx.doi.org/10.1109/ICINFA.2006.374158