Multiple Kinds of Pesticides Detection Based on Back-Propagation Neural Network Analysis of Fluorescence Spectra

• Published in: IEEE photonics journal Vol. 12; no. 2; pp. 1 - 9
• Main Authors: Bian, Haiyi, Yao, Hua, Lin, Guohua, Yu, Yinshan, Chen, Ruiqiang, Wang, Xiaoyan, Ji, Rendong, Yang, Xiao, Zhu, Tiezhu, Ju, Yongfeng
• Format: Journal Article
• Language: English
• Published: Piscataway IEEE 01.04.2020; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Algorithms; Back propagation; Bouguer law; BP neural network algorithm; Fluorescence; fluorescence spectroscopy; Mathematical model; Network analysis; Neural networks; Pesticide residue; Pesticides; Predictive models; Raman scattering; Spectroscopy; Spectrum analysis; Training
• ISSN: 1943-0655; 1943-0655; 1943-0647
• DOI: 10.1109/JPHOT.2020.2973653

Fluorescence spectroscopy attracted more and more attention in pesticide residue detection field because of its advantages of non-destructive, non-contact, high speed and no requirement of complex pre-process procedure. However, given that the concentration of the pesticide detected via fluorescence spectroscopy is calculated in accordance with the Beer-Lambert law, this method can only be used to detect samples containing a single kind of pesticide or several kinds of pesticides with completely different fluorescence which is not in accordance with practical cases. In this article, to overcome this disadvantage, back-propagation (BP) neural network algorithm was introduced to detect multiple kinds of pesticides via fluorescence spectroscopy. The results from four kinds of pesticides which are usually used for fruits and vegetables indicated the effectiveness of BP neural network algorithm.