You can view the full text of this article for free using the link below.

Title: Classification techniques of electronic nose: a review

Authors: Pengfei Jia; Xiaoyu Li; Min Xu; Lin Zhang

Addresses: School of Electrical Engineering, Guangxi University, Nanning, China ' School of Electrical Engineering, Guangxi University, Nanning, China; Guangxi Key Laboratory of Intelligent Control and Maintenance of Power Equipment, Guangxi University, Nanning, China ' College of Food Science and Bioengineering, Xihua University, Chengdu, China ' School of Mechanical and Electrical Engineering, Yangtze Normal University, Chongqing, China

Abstract: Electronic nose (e-nose) is composed of a set of gas sensors combined with a series of algorithmic models. The practical application of the electronic nose system can prove that the electronic nose is more widely used in the classification problems, and always has a good performance. Moreover, it can be inferred that classification methods significantly influence e-nose. So far, the classification models proposed in e-nose can generally be divided into two categories. One is the linear classifier, representing the model of the Bayesian classifier, principal component analysis (PCA), and K-nearest neighbour (KNN), etc. The other is the nonlinear classifier, including support vector machine (SVM), random forest (RF), and extreme learning machine (ELM), etc. This review aims to supply a summary of the various classification methods used in e-nose, and provides a reference for the choice of an appropriate classification model used in e-nose in the specific application.

Keywords: electronic nose; e-nose; classification techniques; artificial intelligence algorithm.

DOI: 10.1504/IJBIC.2024.136224

International Journal of Bio-Inspired Computation, 2024 Vol.23 No.1, pp.16 - 27

Received: 07 Jul 2022
Accepted: 11 May 2023

Published online: 22 Jan 2024 *

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