{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T11:57:03Z","timestamp":1784203023226,"version":"3.55.0"},"reference-count":38,"publisher":"MDPI AG","issue":"13","license":[{"start":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T00:00:00Z","timestamp":1624320000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Natural Science Foundation of\u00a0China; Major Special Science and Technology Project of Anhui Province","award":["31901402, 31801262 and 61672032; 202003A06020016"],"award-info":[{"award-number":["31901402, 31801262 and 61672032; 202003A06020016"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>A rapid and nondestructive method is greatly important for the classification of aflatoxin B1 (AFB1) concentration of single maize kernel to satisfy the ever-growing needs of consumers for food safety. A novel method for classification of AFB1 concentration of single maize kernel was developed on the basis of the near-infrared (NIR) hyperspectral imaging (1100\u20132000 nm). Four groups of AFB1 samples with different concentrations (10, 20, 50, and 100 ppb) and one group of control samples were prepared, which were preprocessed with Savitzky\u2013Golay (SG) smoothing and first derivative (FD) algorithms for their raw NIR spectra. A key wavelength selection method, combining the variance and order of average spectral intensity, was proposed on the basis of pretreated spectra. Moreover, principal component analysis (PCA) was conducted to reduce the dimensionality of hyperspectral data. Finally, a classification model for AFB1 concentrations was developed through linear discriminant analysis (LDA), combined with five key wavelengths and the first three PCs. The results show that the proposed method achieved an ideal performance for classifying AFB1 concentrations in a single maize kernel with overall accuracy, with an F1-score and Kappa values of 95.56%, 0.9554, and 0.9444, respectively, as well as the test accuracy yield of 88.67% for independent validation samples. The combinations of variance and order of average spectral intensity can be used for key wavelength selection which, combined with PCA, can achieve an ideal dimensionality reduction effect for model development. The findings of this study have positive significance for the classification of AFB1 concentration of maize kernels.<\/jats:p>","DOI":"10.3390\/s21134257","type":"journal-article","created":{"date-parts":[[2021,6,22]],"date-time":"2021-06-22T22:10:59Z","timestamp":1624399859000},"page":"4257","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":27,"title":["Classification of Aflatoxin B1 Concentration of Single Maize Kernel Based on Near-Infrared Hyperspectral Imaging and Feature Selection"],"prefix":"10.3390","volume":"21","author":[{"given":"Quan","family":"Zhou","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei 230601, China"},{"name":"Beijing Research Center of Intelligent Equipment for Agriculture, Beijing 100097, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenqian","family":"Huang","sequence":"additional","affiliation":[{"name":"Beijing Research Center of Intelligent Equipment for Agriculture, Beijing 100097, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dong","family":"Liang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Agro-Ecological Big Data Analysis & Application, Anhui University, Hefei 230601, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xi","family":"Tian","sequence":"additional","affiliation":[{"name":"Beijing Research Center of Intelligent Equipment for Agriculture, Beijing 100097, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,6,22]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"118269","DOI":"10.1016\/j.saa.2020.118269","article-title":"Pixel-level aflatoxin detecting in maize based on feature selection and hyperspectral imaging","volume":"234","author":"Gao","year":"2020","journal-title":"Spectrochim. Acta Part A Mol. Biomol. Spectrosc."},{"key":"ref_2","first-page":"1","article-title":"Review on the potential use of near infrared spectroscopy (NIRS) for measurement of chemical residues in food","volume":"1","author":"Teye","year":"2013","journal-title":"Am. J. Food Sci. Technol."},{"key":"ref_3","unstructured":"FDA (2018). Guidance for industry: Action levels for poisonous or deleterious substances in human food and animal feed, Content Current as of September."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"11","DOI":"10.1016\/j.tifs.2016.01.011","article-title":"Data mining derived from food analyses using non-invasive\/non-destructive analytical techniques; determination of food authenticity, quality & safety in tandem with computer science disciplines","volume":"50","author":"Ropodi","year":"2016","journal-title":"Trends Food Sci. Technol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"103418","DOI":"10.1016\/j.infrared.2020.103418","article-title":"Non-destructive discrimination of the variety of sweet maize seeds based on hyperspectral image coupled with wavelength selection algorithm","volume":"109","author":"Zhou","year":"2020","journal-title":"Infrared Phys. Technol."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"104888","DOI":"10.1016\/j.compag.2019.104888","article-title":"Pixel-level aflatoxin detecting based on deep learning and hyperspectral imaging","volume":"164","author":"Han","year":"2019","journal-title":"Comput. Electron. Agric."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"284","DOI":"10.1016\/j.jfoodeng.2015.09.013","article-title":"Use of Near-Infrared hyperspectral images to identify moldy peanuts","volume":"169","author":"Jiang","year":"2016","journal-title":"J. Food Eng."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"107073","DOI":"10.1016\/j.foodcont.2019.107073","article-title":"Optical detection of aflatoxins B in grained almonds using fluorescence spectroscopy and machine learning algorithms","volume":"112","author":"Bertani","year":"2020","journal-title":"Food Control"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.biosystemseng.2017.02.005","article-title":"Detection of aflatoxin B-1 (AFB(1)) in individual maize kernels using short wave infrared (SWIR) hyperspectral imaging","volume":"157","author":"Chu","year":"2017","journal-title":"Biosyst. Eng."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"785","DOI":"10.13031\/trans.59.11365","article-title":"Integration of fluorescence and reflectance visible near-infrared (VNIR) hyperspectral images for detection of aflatoxins in corn kernels","volume":"59","author":"Zhu","year":"2016","journal-title":"Trans. Asabe"},{"key":"ref_11","first-page":"56","article-title":"Detection of aflatoxin B1 on corn kernel surfaces using visible-near infrared spectra","volume":"28","author":"Tao","year":"2019","journal-title":"J. Near Infrared Spectrosc."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1007\/s13197-020-04552-w","article-title":"Non-destructive classification and prediction of aflatoxin-B1 concentration in maize kernels using Vis\u2013NIR (400\u20131000 nm) hyperspectral imaging","volume":"58","author":"Chakraborty","year":"2021","journal-title":"J. Food Sci. Technol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"150","DOI":"10.1016\/j.biosystemseng.2017.11.018","article-title":"Utilisation of visible\/near-infrared hyperspectral images to classify aflatoxin B1 contaminated maize kernels","volume":"166","author":"Kimuli","year":"2018","journal-title":"Biosyst. Eng."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1016\/j.scijus.2013.04.004","article-title":"The age estimation of blood stains up to 30 days old using visible wavelength hyperspectral image analysis and linear discriminant analysis","volume":"53","author":"Li","year":"2013","journal-title":"Sci. Justice"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"977","DOI":"10.1016\/j.snb.2007.09.036","article-title":"Quality control of industrial processes by combining a hyperspectral sensor and Fisher\u2019s linear discriminant analysis","volume":"129","author":"Conde","year":"2008","journal-title":"Sens. Actuators B Chem."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"103077","DOI":"10.1016\/j.infrared.2019.103077","article-title":"Maize seed classification using hyperspectral image coupled with multi-linear discriminant analysis","volume":"103","author":"Xia","year":"2019","journal-title":"Infrared Phys. Technol."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1016\/j.compag.2018.08.018","article-title":"Application driven key wavelengths mining method for aflatoxin detection using hyperspectral data","volume":"153","author":"Han","year":"2018","journal-title":"Comput. Electron. Agric."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"116","DOI":"10.1111\/1750-3841.12728","article-title":"Feasibility of Detecting Aflatoxin B-1 on Inoculated Maize Kernels Surface using Vis\/NIR Hyperspectral Imaging","volume":"80","author":"Wang","year":"2015","journal-title":"J. Food Sci."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"675","DOI":"10.1016\/j.foodcont.2015.06.053","article-title":"Review on the natural co-occurrence of AFB1 and FB1 in maize and the combined toxicity of AFB1 and FB1","volume":"59","author":"Hove","year":"2016","journal-title":"Food Control"},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1016\/j.postharvbio.2017.09.007","article-title":"Detection of early bruises on peaches (Amygdalus persica L.) using hyperspectral imaging coupled with improved watershed segmentation algorithm","volume":"135","author":"Li","year":"2018","journal-title":"Postharvest Biol. Technol."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"235","DOI":"10.1016\/j.postharvbio.2018.12.007","article-title":"Early detection of decay on apples using hyperspectral reflectance imaging combining both principal component analysis and improved watershed segmentation method","volume":"149","author":"Li","year":"2019","journal-title":"Postharvest Biol. Technol."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"201","DOI":"10.1016\/j.isprsjprs.2019.10.005","article-title":"Using spectral Geodesic and spatial Euclidean weights of neighbourhood pixels for hyperspectral Endmember Extraction preprocessing","volume":"158","author":"Kowkabi","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"1627","DOI":"10.1021\/ac60214a047","article-title":"Smoothing and differentiation of data by simplified least squares procedures","volume":"36","author":"Savitzky","year":"1964","journal-title":"Anal. Chem."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"11889","DOI":"10.3390\/s150511889","article-title":"Fruit quality evaluation using spectroscopy technology: A review","volume":"15","author":"Wang","year":"2015","journal-title":"Sensors"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1016\/0169-7439(95)00090-9","article-title":"Discriminant analysis of high-dimensional data:a comparison of principal components analysis and partial least squares data reduction methods","volume":"33","author":"Kemsley","year":"1996","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.foodcont.2014.01.038","article-title":"Identification of aflatoxin B-1 on maize kernel surfaces using hyperspectral imaging","volume":"42","author":"Wang","year":"2014","journal-title":"Food Control"},{"key":"ref_27","first-page":"677","article-title":"PCA-based noise reduction in ambulatory ECGs","volume":"37","author":"Romero","year":"2010","journal-title":"IEEE Comput. Cardiol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"416","DOI":"10.1016\/j.fuel.2018.02.150","article-title":"An efficient classification method for fuel and crude oil types based on m\/z 256 mass chromatography by COW-PCA-LDA","volume":"222","author":"Sun","year":"2018","journal-title":"Fuel"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"5599","DOI":"10.1016\/j.ijleo.2013.04.108","article-title":"Face recognition based on PCA image reconstruction and LDA","volume":"124","author":"Zhou","year":"2013","journal-title":"Optik"},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2344","DOI":"10.1016\/j.sigpro.2009.06.004","article-title":"Post-processed LDA for face and palmprint recognition: What is the rationale","volume":"90","author":"Zuo","year":"2010","journal-title":"Signal Process."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"17","DOI":"10.4018\/JDM.2018070102","article-title":"Towards Real-Time Multi-Sensor Golf Swing Classification Using Deep CNNs","volume":"29","author":"Jiao","year":"2018","journal-title":"J. Database Manag."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"874","DOI":"10.1016\/j.engappai.2007.09.009","article-title":"About the relationship between ROC curves and Cohen\u2019s kappa","volume":"21","year":"2008","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"139","DOI":"10.1016\/j.chemolab.2011.02.008","article-title":"Waveband selection for NIR spectroscopy analysis of soil organic matter based on SG smoothing and MWPLS methods","volume":"107","author":"Chen","year":"2011","journal-title":"Chemom. Intell. Lab. Syst."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"8128","DOI":"10.1021\/jf0512297","article-title":"Rapid detection of kernel rots and mycotoxins in maize by near-infrared reflectance spectroscopy","volume":"53","author":"Berardo","year":"2005","journal-title":"J. Agric. Food Chem."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"629","DOI":"10.1016\/j.foodchem.2008.07.049","article-title":"Application of near infrared spectroscopy for rapid detection of aflatoxin B1 in maize and barley as analytical quality assessment","volume":"113","author":"Soldado","year":"2009","journal-title":"Food Chem."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"171","DOI":"10.1016\/j.foodcont.2014.11.020","article-title":"Short wave infrared (SWIR) hyperspectral imaging technique for examination of aflatoxin B-1 (AFB(1)) on corn kernels","volume":"51","author":"Kandpal","year":"2015","journal-title":"Food Control"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.inffus.2018.09.013","article-title":"Machine learning algorithms for wireless sensor networks: A survey","volume":"49","author":"Amgoth","year":"2019","journal-title":"Inf. Fusion"},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"111159","DOI":"10.1016\/j.fct.2020.111159","article-title":"Aflatoxin contaminated degree detection by hyperspectral data using band index","volume":"137","author":"Han","year":"2020","journal-title":"Food Chem. Toxicol."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4257\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:20:47Z","timestamp":1760163647000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/21\/13\/4257"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,22]]},"references-count":38,"journal-issue":{"issue":"13","published-online":{"date-parts":[[2021,7]]}},"alternative-id":["s21134257"],"URL":"https:\/\/doi.org\/10.3390\/s21134257","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,22]]}}}