Hyperspectral Imaging Combined with Back Propagation Neural Network Optimized by Sparrow Search Algorithm for Predicting Gelatinization Properties of Millet Flour

被引：1

作者：

Wang G. ^{[1
,2
]}

Wang W. ^{[1
]}

Cheng K. ^{[2
]}

Liu X. ^{[2
]}

Zhao J. ^{[1
]}

Li H. ^{[2
]}

Guo E. ^{[2
]}

Li Z. ^{[1
]}

机构：

[1] College of Agricultural Engineering, Shanxi Agricultural University, Taigu

[2] Millet Research Institute, Shanxi Agricultural University, Changzhi

来源：

Shipin Kexue/Food Science | 2022年 / 43卷 / 19期

关键词：

Data pre-processing; Gelatinization characteristics of millet flour; Hyperspectral imaging; Sparrow search algorithm;

D O I：

10.7506/spkx1002-6630-20210806-074

中图分类号：

学科分类号：

摘要：

For large-scale rapid detection of the gelatinization parameters of millet flour, a method to predict the gelatinization characteristics of millet flour was explored using hyperspectral imaging combined with deep learning. The average spectral data of millet flour were obtained through successive hyperspectral data feature extraction and preprocessing, and based on the data matrix obtained, a regression model to predict the gelatinization parameters of millet flour samples was developed using a back propagation (BP) neural network optimized by sparrow search algorithm (SSA). The results showed that the spectral data pre-processing program used in this study could standardize and simplify the process of spectral data extraction and pre-processing, and this program was generally applicable to spectral data extraction and preprocessing for powder and fine particle samples. BP algorithm and SSA-optimized BP algorithm were used to predict the gelatinization parameters of millet flour. The mean square error (MSE) between the prediction value and the tested value of each parameter decreased after optimization of BP algorithm, from 0.026 6 to 0.017 5 for peak viscosity. Therefore, the SSA optimized BP algorithm could predict the gelatinization properties of millet flour more accurately. This study can provide theoretical support for the application of hyperspectral imaging coupled with deep learning in the prediction of the gelatinization properties of millet flour. © 2022, China Food Publishing Company. All right reserved.

引用

页码：65 / 70

页数：5

共 13 条

[1] 31, (2010)
[2] ANOMA C, MARIAN N, FEREIDOON S, Et al., Effect of processing on the antioxidant activity of millet grains, Food Chemistry, 133, 1, pp. 1-9, (2012)
[3] pp. 260-262, (2011)
[4] ABBAS O, LECLER B, DARDENNE P, Et al., Detection of melamine and cyanuric acid in feed ingredients by near infrared spectroscopy and chemometrics, Journal of Near Infrared Spectroscopy, 21, 3, pp. 401-404, (2013)
[5] SHI Jiyong, HU Xuetao, ZHU Xiaobo, Et al., A rapid and nondestructive method to determine the distribution map of protein, carbohydrate and sialic acid on edible bird's nest by hyper-spectral imaging and chemometrics, Food Chemistry, 229, pp. 235-241, (2017)
[6] ANTONIOS M, XANTHOULA P, DIMOTRIOS M, Et al., Machine learning based prediction of soil total nitrogen, organic carbon and moisture content by using VIS-NIR spectroscopy, Biosystems Engineering, 152, 12, pp. 104-116, (2016)
[7] XUE Jiankai, SHEN Bo, A novel swarm intelligence optimization approach: sparrow search algorithm, Systems Science & Control Engineering, 8, 1, pp. 22-34, (2020)
[8] 28, 7, (2012)
[9] MAHARISHI T, RAKESH B, MANOJ K, Et al., Development of NIR spectroscopy based prediction models for nutritional profiling of pearl millet (Pennisetum glaucum (L.)) R.Br: a chemometrics approach, LWT-Food Science and Technology, 149, 5, pp. 1-11, (2021)
[10] CHEN Jing, REN Xin, ZHANG Qing, Et al., Determination of protein, total carbohydrates and crude fat contents of foxtail millet using effective wavelengths in NIR spectroscopy, Journal of Cereal Science, 58, 2, pp. 241-247, (2013)

← 1 2 →