Title: Applications of electronic nose in gas detection: a review

Authors: Guosheng Mao; Yiyi Zhang; Pengfei Jia

Addresses: School of Electrical Engineering, Guangxi University, Nanning, Guangxi, China ' School of Electrical Engineering, Guangxi University, Nanning, Guangxi, China ' School of Electrical Engineering, Guangxi University, Nanning, Guangxi, China

Abstract: Electronic nose (E-nose) employs the sensor array and pattern recognition algorithm to simulate the mammalian olfaction. Widely used in gas detection, E-nose has outperformed the traditional gas detection methods in many aspects. E-nose is usually used in qualitative classification and quantitative regression analysis in the field of gas detection, that is, to perform the identification on the mixed gases. Currently, the most commonly used sensors for E-nose can be divided into conductivity sensor, piezoelectrical sensor, MOSFET sensor and optical sensor, and the most widely used pattern recognition algorithms are classical machine learning, deep learning and hybrid models. This article aims to summarise the sensors and pattern recognition algorithms widely used in E-nose, and provides reference for the prospective specific application of E-nose.

Keywords: E-nose; gas detection; sensor; machine learning; classification.

DOI: 10.1504/IJWMC.2025.147626

International Journal of Wireless and Mobile Computing, 2025 Vol.29 No.1, pp.31 - 41

Received: 27 Mar 2023
Accepted: 26 Oct 2023
Published online: 24 Jul 2025 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article