Abstract
In view of the time-consuming, labor-intensive, and costly problem of chemical detection methods in the national standard, the feasibility of near-infrared spectroscopy （NIRS） combined with chemometrics for rapid detection of rice protein was investigated. Based on strategies of variable selection, feature extraction and nonlinear modeling, BiPLS-PCA-SVM was constructed by combining reverse interval partial least squares （BiPLS） with principal component analysis （PCA） and support vector machine （SVM） to improve the performance of the protein regression model. In BiPLS-PCA-SVM, the optimal number of principal components （PCs） was selected by combining Monte Carlo cross validation with the predicted residual sum of squares, and the model parameters were optimized by genetic simulated annealing algorithm. To evaluate the performance of BiPLS-PCA-SVM, three different models, including Full-PLS, BiPLS and BiPLS-SVM, were established, and the prediction accuracy and model robustness of all models were systematically analyzed. The performance of BiPLS-PA-SVM model in predicting protein content was higher than that of other models, and the model established by using the optimal number of PCs and optimized SVM parameters had higher robustness and accuracy. For BiPLS-PCA-SVM, the determination coefficient, root-mean square error and residual predictive deviation of the validation set were 0.928 9, 0.196 7% and 4.024 6, respectively. The results showed that NIRS combined with BiPLS-PCA-SVM model could be used as a reliable alternative strategy to realize the rapid detection of protein content in rice.
Publication Date
5-28-2021
First Page
82
Last Page
88,175
DOI
10.13652/j.issn.1003-5788.2021.05.015
Recommended Citation
Kun, YIN; Jin-ming, LIU; Dong-jie, ZHANG; and Ai-wu, ZHANG
(2021)
"Rapid detection of protein contentin rice based on near infrared spectroscopy,"
Food and Machinery: Vol. 37:
Iss.
5, Article 15.
DOI: 10.13652/j.issn.1003-5788.2021.05.015
Available at:
https://www.ifoodmm.cn/journal/vol37/iss5/15
References
[1] 刘芳, 许宙, 陈茂龙, 等. 碱与热处理对大米蛋白质结构与功能性质的影响[J]. 食品与机械, 2018, 34（8）: 10-15.
[2] 刘文丽, 严虞虞, 吴东慧, 等. 近红外光谱技术无损检测大米中蛋白质[J]. 食品工业, 2019, 40（1）: 205-209.
[3] 吴长明, 孙传清, 陈亮, 等. 稻米营养品质性状的QTL及其与食味品质的关系研究[J]. 吉林农业科学, 2002, 27（4）: 3-7.
[4] 苗雪雪, 苗莹, 龚浩如, 等. 不同偏最小二乘法的近红外光谱技术测定大米中水分的研究[J]. 分析科学学报, 2019, 35（5）: 643-649.
[5] 俞法明, 陆艳婷, 严文潮, 等. 用近红外光谱技术快速测定籼稻品种的蛋白质含量[J]. 中国粮油学报, 2009, 24（5）: 134-138.
[6] YANG Mei-hua, XU Dong-yun, CHEN Song-chao, et al. Evaluation of machine learning approaches to predict soil organic matter and pH using vis-NIR spectra[J]. Sensors （Basel）, 2019, 19（2）: 263-277.
[7] 刘金明, 谢秋菊, 王雪, 等. 基于GSA-SVM的畜禽舍废气监测缺失数据恢复方法[J]. 东北农业大学学报, 2015, 46（5）: 95-101.
[8] 刘金明, 郭坤林, 甄峰, 等. 基于近红外光谱的沼液挥发性脂肪酸含量快速检测[J]. 农业工程学报, 2020, 36（18）: 188-196.
[9] 李子文, 李宗朋, 买书魁, 等. 最小二乘支持向量机的核桃露饮品中脂肪成分的定量分析[J]. 光谱学与光谱分析, 2019, 39（12）: 3 916-3 920.
[10] 孙丽萍, 张希萌, 何睿, 等. 基于SVM的近红外黑木耳多糖含量分类[J]. 电子科技, 2019, 32（8）: 16-21.
[11] 张晓冬, 陈龙, 黄必胜, 等. 基于NIRS和PCA-SVM算法快速鉴别4种含铁矿物药[J]. 中成药, 2018, 40（2）: 404-410.
[12] 魏从师, 雷福汉, 艾伟霞, 等. 基于NIRS技术和PCA-SVM算法6种树脂及其他类中药的快速鉴别[J]. 中国实验方剂学杂志, 2017, 23（9）: 17-23.
[13] 顾凯成. 改进网格搜索的支持向量机参数优化研究及应用[D]. 兰州: 兰州理工大学, 2016: 18-19.
[14] NORGAARD L, SAUDLAND A, WAGNER J, et al. Interval partial least-squares regression （iPLS）: A comparative chemometric study with an example from near-infrared spectroscopy[J]. Applied Spectroscopy, 2000, 54（3）: 413-419.
[15] LEARDI R, NRGAARD L. Sequential application of backward interval partial least squares and genetic algorithms for the selection of relevant spectral regions[J]. Journal of Chemometrics, 2010, 18（11）: 3 222-3 235.
[16] AMELIA P, WEIN A S, BANDEIRA A S, et al. Optimality and sub-optimality of PCA I: Spiked random matrix models[J]. Annals of Statistics, 2018, 46（5）: 2 416-2 451.
[17] YANG Yue, LIU Xue-song, LI Wei-li, et al. Rapid measurement of epimedin A, epimedin B, epimedin C, icariin, and moisture in Herba Epimedii using near infrared spectroscopy[J]. Spectrochimica Acta Part A Molecular & Biomolecular Spectroscopy, 2017, 171: 351-360.
[18] LIANG Long, WEI Lu-lu, FANG Gui-gan, et al. Prediction of holocellulose and lignin content of pulp wood feedstock using near infrared spectroscopy and variable selection[J]. Spectrochimica Acta Part A Molecular & Biomolecular Spectroscopy, 2019, 225: 117515.
[19] LIU Jin-ming, LI Nan, ZHEN Feng, et al. Rapid detection of carbon-nitrogen ratio for anaerobic fermentation feedstocks using near-infrared spectroscopy combined with BiPLS and GSA[J]. Applied Optics, 2019, 58（18）: 5 090.
[20] STONE R W K A. Computer aided design of experiments[J]. Technometrics, 1969, 11（1）: 137-148.
[21] LEARDI R, NRGAARD L. Sequential application of backward interval partial least squares and genetic algorithms for the selection of relevant spectral regions[J]. Journal of Chemometrics, 2004, 18（11）: 486-497.
[22] CHANG Chihh-chung, LIN Chih-jen. LIBSVM: A library for support vector machines[J]. ACM Transactions on Intelligent Systems and Technology, 2011, 2（3）: 1-27.
[23] CAO Jie, ZHU Shi-jie, LI Chao, et al. Integrating support vector regression with genetic algorithm for hydrate formation condition prediction[J]. Processes, 2020, 5（519）: 519.
[24] STOCKL A, LICHTI F. Near-infrared spectroscopy （NIRS） for a real time monitoring of the biogas process[J]. Bioresource Technology, 2018, 108（1）: 1 249-1 252.