Abstract

Electronic nose is a device that attempts to mimic the living being smell system for detection of particular gases or volatile compounds. This paper reports the development of an optical electronic nose using Fe (III) based metalloporphyrins Langmuir-Blodgett thin films as sensing elements for discriminating four volatiles, 2-propanol, acetone, cyclohexane and ethanol. A multilayer feed forward neural network was developed to classify the input vectors from these two sensors. After the network being trained 100 times and introduced to blind samples, it was found that there are three fault decision for propanol, two for acetone, five for cyclohexane and one four ethanol, during 50 times being recognized to the samples.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call