Identification of heavy metal pollutants in wheat by THz spectroscopy and deep support vector machine

Hongyi Ge; Xiaodi Ji; Xuejing Lu; Ming Lv; Yuying Jiang; Zhiyuan Jia; Yuan Zhang

doi:10.1016/j.saa.2023.123206

Identification of heavy metal pollutants in wheat by THz spectroscopy and deep support vector machine

Spectrochim Acta A Mol Biomol Spectrosc. 2023 Dec 15:303:123206. doi: 10.1016/j.saa.2023.123206. Epub 2023 Jul 25.

Authors

Hongyi Ge¹, Xiaodi Ji¹, Xuejing Lu², Ming Lv¹, Yuying Jiang³, Zhiyuan Jia¹, Yuan Zhang¹

Affiliations

¹ Key Laboratory of Grain Information Processing and Control, Ministry of Education, Henan University of Technology, Zhengzhou 450001, Henan, China; Henan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou 450001, Henan, China; College of Information Science and Engineering, Henan University of Technology, Zhengzhou 450001, Henan, China.
² PLA Strategic Support Force Information Engineering University, Zhengzhou 450001, Henan, China.
³ Key Laboratory of Grain Information Processing and Control, Ministry of Education, Henan University of Technology, Zhengzhou 450001, Henan, China; Henan Provincial Key Laboratory of Grain Photoelectric Detection and Control, Zhengzhou 450001, Henan, China; School of Artificial Intelligence and Big Data, Henan University of Technology, Zhengzhou 450001, Henan, China. Electronic address: yyjiang@haut.edu.cn.

PMID: 37542868
DOI: 10.1016/j.saa.2023.123206

Abstract

This paper proposes to detect heavy metal pollutants in wheat using terahertz spectroscopy and deep support vector machine (DSVM). Five heavy metal pollutants, arsenic, lead, mercury, chromium, and cadmium, were considered for detection in wheat samples. THz spectral data were pre-processed by wavelet denoising. DSVM was introduced to further enhance the accuracy of the SVM classification model. According to the relationship between the accuracy and the training time with the number of hidden layers ranging from 1 to 4, the model performs the best when the hidden layer network has three layers. Besides, using the back-propagation algorithm to optimize the entire DSVM network. Compared with Deep neural network (DNN) and SVM models, the comprehensive evaluation index of the proposed model optimized by DSVM has the highest accuracy of 91.3 %. It realized the exploration enhanced the classification accuracy of the heavy metal pollutants in wheat.

Keywords: Deep support vector machine; Heavy metal pollutants in wheat; Terahertz (THz) spectrum.