Journal of Food Science and Biotechnology
Abstract
[Objective ] This study aims to achieve rapid detection of AFB 1 contamination levels in peanuts through dual-band hyperspectral imaging and machine learning.[Method ] A peanut AFB 1 contamination level warning model was constructed via a dual-band hyperspectral imaging system consisting of visible near-infrared spectroscopy at 400~1 000 nm and short-wave near-infrared spectroscopy at 900~1 700 nm,combined with machine learning.Peanut samples with four contamination levels were collected,in which the mass fraction of AFB 1 was determined by ultra-high performance liquid chromatography-tandem mass spectrometry.The effects of four pretreatment methods [first derivative,second derivative,multiplicative scatter correction,and standard normal variate (SNV )],two characteristic wavelength selection methods [successive projections algorithm and uninformative variables elimination (UVE )],and two machine learning methods [support vector machine (SVM ) and back-propagation neural network ] on classification performance were compared.[Result ] The combined model SNV-UVE-SVM effectively determined AFB 1 contamination levels in both bands,with optimal performance in the 900~1 700 nm band.The characteristic wavelengths were primarily concentrated in the ranges of 1 126~1 308 nm and 1 588~1 720 nm,achieving 100.00% accuracy in both the training and test sets.[Conclusion ] This paper pioneered the construction of an intelligent early-warning model for AFB 1 contamination levels in peanuts by using dual-band hyperspectral imaging and machine learning algorithms,providing a novel technical paradigm for non-destructive detection of mycotoxin contamination in agricultural products.This approach holds significant engineering application value for real-time online monitoring in processing stages.
Publication Date
12-15-2025
First Page
135
Last Page
145
DOI
10.12441/spyswjs.20250710001
Recommended Citation
REN, Lu; SHEN, Shuyue; SHI, Wanrong; RUI, Chuang; DONG, Maofeng; and LI, Tingting
(2025)
"Rapid Detection of Aflatoxin B 1 Contamination Levels in Peanuts Based on Dual-band Hyperspectral Imaging and Machine Learning,"
Journal of Food Science and Biotechnology: Vol. 44:
Iss.
12, Article 14.
DOI: 10.12441/spyswjs.20250710001
Available at:
https://spsw.spyswjs.cnjournals.com/journal/vol44/iss12/14
References
［1］ 中华人民共和国 国家卫生和计划生育委员会，国家食品药品监督管理总局.食品安全国家标准 食品中真菌毒素限量：GB 2761—2017［S］.北京：中国标准出版社，2017.
［2］ 尹玉云，陶健，焦强，等.用于黄曲霉毒素 B1快速检测的胶体金试剂盒质量评价 ［J］.食品与生物技术学报，2024，43（5）：130-137.YIN Y Y，TAO J，JIAO Q，et al.Quality evaluation of colloidal gold kits for rapid detection of aflatoxin B 1［J］.Journal of Food Science and Biotechnology，2024，43（5）：130-137.（in Chinese ）
［3］ 韩仲志，刘杰.高光谱亚像元分解预测花生中的黄曲霉毒素 B1［J］.中国食品学报，2020，20（3）：244-250.HAN Z Z，LIU J.Detecting aflatoxin B 1 in peanuts by hyperspectral subpixel decomposition ［J］.Journal of Chinese Institute of Food Science and Technology，2020，20（3）：244-250.（in Chinese ）
［4］ CHAHARAEIN M，SADEGHI E，MOHAMMADI R，et al.The effect of β-glucan and inulin on the reduction of aflatoxin B 1 level and assessment of textural and sensory properties in chicken sausages ［J］.Current Research inFood Science，2021，4：765-772.
［5］ DALIRI A，SHAMS-GHAHFAROKHI M，RAZZAGHI-ABYANEH M.Detection of Aflatoxin B 1-producing Aspergillus flavus strains from pistachio orchards soil in Iran by multiplex polymerase chain reaction method ［J］.Current Medical Mycology，2023，9（3）：1-7.
［6］ WANG Y Z，HOU C，DAI Y Q，et al.Determination of aflatoxin B 1 by novel nanofiber-packed solid-phase extraction coupled with a high performance liquid ch romatography-fluorescence detector ［J］.Analytical Methods，2023，15（4）：472-481.
［7］ SAILAJA O，MANORANJANI M，KRISHNAVENI G.Simultaneous estimation of aflatoxins （B1，B2，G1 and G 2） by liquidchromatography coupled with mass spectrometry （LC-MS） in corn samples ［J］.Asian Journal of Chemistry，2021，33（3）：521-526.
［8］ 赵昕，郑树亮，牛晓颖，等.基于高光谱成像技术和近红外光谱技术的金冠苹果货架期判别及其品质分析 ［J］.食品工业科技，2025，46（11）：302-312.ZHAO X，ZHENG S L，NIU X Y，et al.Shelf life identification and quality analysis of golden delicious apples based on hyperspectral imaging and near infrared spectroscopy ［J］.Science and Technology of Food Industry，2025，46（11）：302-312.（in Chinese ）
［9］ LI X F，LIU L Q，SONG S S，et al.Colloidal gold immunochromatographic assay for the detection of total aflatoxins in cereals ［J］.Food Chemistry，2025，472：142877.
［10］ LANDGREBE D.Hyperspectral image data analysis ［J］.IEEE Signal Processing Magazine，2002，19（1）：17-28.［11］ 朱宏飞.基于深度学习的花生黄曲霉毒素高光谱检测关键技术研究 ［D］.天津：天津工业大学，2023：1-84.
［12］ ZHANG S，LI Z X，AN J，et al.Identification of aflatoxin B 1 in peanut using near-infrared spectroscopy combined with naive Bayes classifier ［J］.Spectroscopy Letters，2021，54（5）：340-351.
［13］ 朱昊宇，王俊杰，杨一，等.基于近红外高光谱图像的花生内部霉变快速判别方法研究 ［J］.食品安全质量检测学报，2024，15（1）：85-91.ZHU H Y，WANG J J，YANG Y，et al.Research on rapid discrimination for internal mold detection in peanuts based on near-infrared hyperspectral image ［J］.Journal of Food Safety & Quality，2024，15（1）：85-91.（in Chinese ）
［14］ 中华人民共和国 国家卫生和计划生育委员会，国家食品药品监督管理总局.食品安全国家标准 食品中黄曲霉毒素B族和 G族的测定：GB 5009.22—2016［S］.北京：中国标准出版社，2017.
［15］ BIAN X H.Spectral dimensionality reduction methods［M］.Singapore：Springer Nature Singapore，2022：209-236.
［16］ LI Z X，TANG X Y，SHEN Z X，et al.Comprehensive comparison of multiple quantitative near-infrared spectroscopy models for Aspergillus flavus contamination detection in peanut［J］.Journal of the Science of Food and Agriculture，2019，99（13）：5671 -5679.
［17］ DACHOUPAKAN S C，PUTTHANG R，SIRISOMBOON P.Application of near infrared spectroscopy to detect aflatoxigenic fungal contamination in rice ［J］.Food Control，2013，33（1）：207-214.