Application of colorimetric sensor array coupled with machine-learning approaches for the discrimination of grains based on freshness.
colorimetric sensor array
freshness degree
grain
image processing
visible-near-infrared spectroscopy
Journal
Journal of the science of food and agriculture
ISSN: 1097-0010
Titre abrégé: J Sci Food Agric
Pays: England
ID NLM: 0376334
Informations de publication
Date de publication:
Nov 2023
Nov 2023
Historique:
revised:
28
05
2023
received:
05
08
2022
accepted:
13
06
2023
medline:
23
10
2023
pubmed:
13
6
2023
entrez:
12
6
2023
Statut:
ppublish
Résumé
Volatile organic compounds (VOCs) in grain fluctuate depending on the degree of grain freshness. A new colorimetric sensor array (CSA) was developed as capture probes for the quantification of VOCs in grains in this work, and it was designed to monitor the variation of grain VOCs. CSA spectral data acquisition using visible-near-infrared spectroscopy and image processing of CSA's image imformation by computer were used comparatively. Then, machine-learning-based models - for example, synergistic interval partial least squares, genetic algorithm, competitive adaptive reweighted sampling (CARS) algorithm, and ant colony optimization (ACO) algorithm - were introduced to optimize variables. Moreover, principal component analysis, and linear discriminant analysis (LDA), and K-nearest neighbors (KNN) were used for the classification. Ultimately, quantitative models for detecting grain freshness are developed using various variable selection strategies. Compared with the pattern recognition results of image processing, visible-near-infrared spectroscopy could better separate the grains with different freshness from principal component analysis, and the prediction set of LDA models could correctly identify 100% of rice, 96.88% of paddy, and 97.9% of soybeans. In addition, compared with CARS and ACO, the LDA model and KNN model based on genetic algorithms show the best prediction performance. The prediction set could correctly identify 100% of rice and paddy samples and 95.83% of soybean samples. The method developed could be used for non-destructive detection of grain freshness. © 2023 Society of Chemical Industry.
Sections du résumé
BACKGROUND
BACKGROUND
Volatile organic compounds (VOCs) in grain fluctuate depending on the degree of grain freshness. A new colorimetric sensor array (CSA) was developed as capture probes for the quantification of VOCs in grains in this work, and it was designed to monitor the variation of grain VOCs. CSA spectral data acquisition using visible-near-infrared spectroscopy and image processing of CSA's image imformation by computer were used comparatively. Then, machine-learning-based models - for example, synergistic interval partial least squares, genetic algorithm, competitive adaptive reweighted sampling (CARS) algorithm, and ant colony optimization (ACO) algorithm - were introduced to optimize variables. Moreover, principal component analysis, and linear discriminant analysis (LDA), and K-nearest neighbors (KNN) were used for the classification. Ultimately, quantitative models for detecting grain freshness are developed using various variable selection strategies.
RESULTS
RESULTS
Compared with the pattern recognition results of image processing, visible-near-infrared spectroscopy could better separate the grains with different freshness from principal component analysis, and the prediction set of LDA models could correctly identify 100% of rice, 96.88% of paddy, and 97.9% of soybeans. In addition, compared with CARS and ACO, the LDA model and KNN model based on genetic algorithms show the best prediction performance. The prediction set could correctly identify 100% of rice and paddy samples and 95.83% of soybean samples.
CONCLUSION
CONCLUSIONS
The method developed could be used for non-destructive detection of grain freshness. © 2023 Society of Chemical Industry.
Substances chimiques
Volatile Organic Compounds
0
Types de publication
Journal Article
Langues
eng
Sous-ensembles de citation
IM
Pagination
6790-6799Subventions
Organisme : Jiangsu Agricultural independent innovation fund
ID : SCX 203321
Organisme : Key R&D program of Jiangsu Province
ID : BE2021343
Organisme : National Natural Science Foundation of China
ID : 51975259
Informations de copyright
© 2023 Society of Chemical Industry.
Références
Wang XD and Wang ZH, Effects of storage methods on storage quality of soybean in Northeast China. Cereals & Oils 34:60-64 (2021).
Zhang YJ and Wang H, Application technology of soybean safe storage. Cereal and Food Industry 17:48-50 (2010) (in Chinese with English abstract).
Wu Q, Li Y and Zhang LL, Discussion on storage of soybean(II). Grain Processing 46:70-75 (2021) (in Chinese with English abstract).
Thanathornvarakul N, Anuntagool J and Tananuwong K, Aging of low and high amylose rice at elevated temperature: mechanism and predictive modeling. J Cereal Sci 70:155-163 (2016). https://doi.org/10.1016/j.jcs.2016.06.004.
Liu C, Quality changes of soybean during storage. China Oils Fats 34:65-67 (2009).
Ezhilan M, Nesakumar N, Babu KJ, Srinandan CS and Rayappan JBB, Freshness assessment of broccoli using electronic nose. Measurement 145:735-743 (2019).
Zhang C and Suslick KS, A colorimetric sensor array for organics in water. J Am Chem Soc 127:11548-11549 (2005).
Lin H, Duan Y, Yan S, Wang Z and Zareef M, Quantitative analysis of volatile organic compound using novel chemoselective response dye based on Vis-NIRS coupled Si-PLS. Microchem J 145:1119-1128 (2019).
Huo D, Wu Y, Yang M, Fa H, Luo X and Hou C, Discrimination of Chinese green tea according to varieties and grade levels using artificial nose and tongue based on colorimetric sensor arrays. Food Chem 145:639-645 (2014). https://doi.org/10.1016/j.foodchem.2013.07.142.
Salinas Y, Ros-Lis JV, Vivancos JL, Martínez-Máñez R, Marcos MD, Aucejo S et al., A novel colorimetric sensor array for monitoring fresh pork sausages spoilage. Food Control 35:166-176 (2014). https://doi.org/10.1016/j.foodcont.2013.06.043.
Guan B, Zhao J, Jin H and Lin H, Determination of rice storage time with colorimetric sensor array. Food Anal Methods 10:1054-1062 (2016). https://doi.org/10.1007/s12161-016-0664-6.
Guan B, Xue Z, Chen Q, Lin H and Zhao J, Preparation of zinc porphyrin nanoparticles and application in monitoring the ethanol content during the solid-state fermentation of Zhenjiang aromatic vinegar. Microchem J 153:104353 (2020). https://doi.org/10.1016/j.microc.2019.104353.
Han F, Zhang D, Aheto JH, Feng F and Duan T, Integration of a low-cost electronic nose and a voltammetric electronic tongue for red wines identification. Food Sci Nutr 8:4330-4339 (2020). https://doi.org/10.1002/fsn3.1730.
Magnaghi LR, Capone F, Zanoni C, Alberti G, Quadrelli P and Biesuz R, Colorimetric sensor array for monitoring, modelling and comparing spoilage processes of different meat and fish foods. Foods 9:684 (2020). https://doi.org/10.3390/foods9050684.
Kutsanedzie FYH, Hao L, Yan S, Ouyang Q and Chen Q, Near infrared chemo-responsive dye intermediaries spectra-based in-situ quantification of volatile organic compounds. Sens Actuators B 254:597-602 (2018). https://doi.org/10.1016/j.snb.2017.07.134.
Lin H, Man ZX, Kang WC, Guan BB, Chen QS and Xue ZL, A novel colorimetric sensor array based on boron-dipyrromethene dyes for monitoring the storage time of rice. Food Chem 268:300-306 (2018). https://doi.org/10.1016/j.foodchem.2018.06.097.
Zhang J, Li M, Pan T, Yao L and Chen J, Purity analysis of multi-grain rice seeds with non-destructive visible and near-infrared spectroscopy. Comput Electron Agric 164:104882 (2019). https://doi.org/10.1016/j.compag.2019.104882.
Barbin DF, Badaró AT, Honorato DCB, Ida EY and Shimokomaki M, Identification of turkey meat and processed products using near infrared spectroscopy. Food Control 107:106816 (2020). https://doi.org/10.1016/j.foodcont.2019.106816.
Leardi R and Nørgaard L, Sequential application of backward interval partial least squares and genetic algorithms for the selection of relevant spectral regions. J Chemom 18:486-497 (2004). https://doi.org/10.1002/cem.893.
Shetty N and Gislum R, Quantification of fructan concentration in grasses using NIR spectroscopy and PLSR. Field Crop Res 120:31-37 (2011). https://doi.org/10.1016/j.fcr.2010.08.008.
Ma HL, Wang JW, Chen YJ, Cheng JL and Lai ZT, Rapid authentication of starch adulterations in ultrafine granular powder of shanyao by near-infrared spectroscopy coupled with chemometric methods. Food Chem 215:108-115 (2017). https://doi.org/10.1016/j.foodchem.2016.07.156.
Sampaio PS, Soares A, Castanho A, Almeida AS, Oliveira J and Brites C, Optimization of rice amylose determination by NIR-spectroscopy using PLS chemometrics algorithms. Food Chem 242:196-204 (2018). https://doi.org/10.1016/j.foodchem.2017.09.058.
Lee K, Park H, Baek S, Han S, Kim D, Chung S et al., Colorimetric array freshness indicator and digital color processing for monitoring the freshness of packaged chicken breast. Food Packag Shelf Life 22:100408 (2019). https://doi.org/10.1016/j.fpsl.2019.100408.
Hu L, Yin C, Ma S and Liu Z, Rapid detection of three quality parameters and classification of wine based on Vis-NIR spectroscopy with wavelength selection by ACO and CARS algorithms. Spectrochim Acta Part A 205:574-581 (2018). https://doi.org/10.1016/j.saa.2018.07.054.
Su WH and Sun DW, Multispectral imaging for plant food quality analysis and visualization. Compr Rev Food Sci Food Saf 17:220-239 (2018). https://doi.org/10.1111/1541-4337.12317.
Agyekum AA, Kutsanedzie FYH, Annavaram V, Mintah BK, Asare EK and Wang B, FT-NIR coupled chemometric methods rapid prediction of K-value in fish. Vib Spectrosc 108:103044 (2020). https://doi.org/10.1016/j.vibspec.2020.103044.
Agyekum AA, Kutsanedzie FYH, Mintah BK, Annavaram V, Zareef M, Hassan MM et al., Rapid and nondestructive quantification of trimethylamine by FT-NIR coupled with chemometric techniques. Food Anal Methods 12:2035-2044 (2019). https://doi.org/10.1007/s12161-019-01537-0.
Li M, Wijewardane NK, Ge Y, Xu Z and Wilkins MR, Visible/near infrared spectroscopy and machine learning for predicting polyhydroxybutyrate production cultured on alkaline pretreated liquor from corn stover. Bioresour Technol Rep 9:100386 (2020). https://doi.org/10.1016/j.biteb.2020.100386.
Lin H, Jiang H, Lin J, Chen Q, Ali S, Teng SW et al., Rice freshness identification based on visible near-infrared spectroscopy and colorimetric sensor array. Food Anal Methods 14:1305-1314 (2021). https://doi.org/10.1007/s12161-021-01963-z.
Li HH, Geng W, Hassan MM, Zuo M, Wei W, Wu X et al., Rapid detection of chloramphenicol in food using SERS flexible sensor coupled artificial intelligent tools. Food Control 128:108186 (2021). https://doi.org/10.1016/j.foodcont.2021.108186.