Prediction Of Raman Spectra and Adulteration Concentration of Wheat Flour Based on Neural Network Modelling

Zongze Li; Jingru Xiao

doi:10.54097/arzmtw42

Authors

Zongze Li
Jingru Xiao

DOI:

https://doi.org/10.54097/arzmtw42

Keywords:

Neural network; raman spectra; deep learning.

Abstract

In order to quickly detect the adulteration of flour containing wheat flour quality testing, the Raman spectrum of wheat flour as the object of study, based on a number of data-based neural network to identify and determine the concentration of wheat adulteration. Firstly, the neural network system in this study borrowed the Raman wave number and Raman intensity curve from "Non-contact Detection of Benzoyl Peroxide in Flour Based on Raman Spectroscopy" as the training and testing set. Next, we created the neural network, set the training parameters, trained the network and simulated the test. Finally, the supervised learning process resulted in error analysis and comparison of results, and the Raman spectra of wheat flour and adulteration concentration were plotted visually.

Downloads

Download data is not yet available.

References

Zhao Juan, & Peng Yankun. (2015). Non-contact detection of benzoyl peroxide in flour based on Raman spectroscopy. China Agricultural Science and Technology Herald, (5), 33-39.

Wee, & Zhang, Hua Yue. (2014). Analysis of gold price prediction based on BP neural network. Tianjin Science and Technology, 41(1), 68-73.

Xu Tianfeng, Peng Yankun, Li Yongyu, Zhai Chen, Zheng Xiaochun, & Qiao Lu. (2016). Raman point scanning method for rapid detection of spinach quality and safety parameters. Spectroscopy and Spectral Analysis, 36(6), 1765-1770.

Yanyan Huang, & Jian Yao. (2023). Prediction of rice moisture content based on PSO-GA-BP neural network. Grain and Feed Industry, (3), 56-60.

TONG Quan, SHI Zhixin, & MAO Zhiwei. (2023). Spatter analysis of rotating arc images based on multi-thresholding and neural network. Journal of Welding, 43(12), 41-46.

Peng, Yankun, Tian, Wenjian, Guo, Qinghui, Zhao, Xinlong, & Qiao, Xin. (2021). Non-destructive quantitative analysis of acetamiprid pesticide residues in apples based on enhanced Raman spectroscopy. Transactions of the Chinese Society of Agricultural Engineering, 37(14).

Yuan Feiniu, Zhang Lin, Shi Jinting, Xia Xue, & Li Gang. (2019). A review on the theory and application of self-coding neural networks. Journal of Computing, 42(1), 203-230.

Yang, S. E., & Wang, L. P.. (2007). Early warning of financial crisis of listed companies based on BP neural network and panel data (Doctoral dissertation).

Gan, Jingyi, Huang, Minghe, & Yuan, Jing. (2011). Analysis of China's financial risk early warning model based on BP artificial neural network. Business Times, (27), 65-66.

Yang, J., & Zeng, W.W.. (2022). A prediction model of surface settlement in mining area based on GA-BP neural network. Mining and Metallurgical Engineering, 42(2), 42-45.

Li, W.H., Wen, L., & Chen, Y.B.. (2017). Application of improved GA-BP neural network model in property crime prediction. Journal of Wuhan University (Information Science Edition), 42(8), 1110-1116.

Chen, Yuan-Ling, Wang, Xiao, Sun, Ying-Jie, & Zhang, Yang. (2022). Sugarcane harvest quality prediction based on GA-BP neural network. Agricultural Mechanization Research, 44(2), 187-191.