Five Typical Stenches Detection Using an Electronic Nose

Sensors

Wei Jiang¹  Daqi Gao¹ 

[1] School of Information Science and Engineering, East China University of Science and Technology, Shanghai 200030, China;

关键词: stenches detection;    odor concentration;    electronic nose;    machine learning algorithm;   

DOI  :  10.3390/s20092514

来源: DOAJ

【 摘 要 】

This paper deals with the classification of stenches, which can stimulate olfactory organs to discomfort people and pollute the environment. In China, the triangle odor bag method, which only depends on the state of the panelist, is widely used in determining odor concentration. In this paper, we propose a stenches detection system composed of an electronic nose and machine learning algorithms to discriminate five typical stenches. These five chemicals producing stenches are 2-phenylethyl alcohol, isovaleric acid, methylcyclopentanone, γ-undecalactone, and 2-methylindole. We will use random forest, support vector machines, backpropagation neural network, principal components analysis (PCA), and linear discriminant analysis (LDA) in this paper. The result shows that LDA (support vector machine (SVM)) has better performance in detecting the stenches considered in this paper.

【 授权许可】

Unknown