Implementation of Electronic Nose Using Neural Network.

Khairallah, B. S.; Hegazy, T. A.

doi:10.21608/bfemu.2020.123640

Implementation of Electronic Nose Using Neural Network.

Document Type : Research Studies

Authors

B. S. Khairallah ¹
T. A. Hegazy ²

¹ Electrical Power Engineering Department., Faculty of Engineering., El-Mansoura University., Egypt.

² Computer Engineering and Systems Department., Faculty of Engineering., El-Mansoura University., Mansoura., Egypt

10.21608/bfemu.2020.123640

Abstract

Electronic Noses were engineered to mimic the mammalian olfactory system within an instrument designed to obtain repeatable measurements, allowing identifications and classifications while eliminating operator fatigue. They are used in several real-life applications such as food industry, environment protection, and gas identification. In this paper, an odor identification problem is addressed, where it is required to identify certain products according to their odors. An electronic nose is constructed using a number of sensors and a neural network to perform the identification. Experimental results showed that the proposed multilayer perceptron structure can identify new products with more than 90% accuracy.

Keywords

Main Subjects