2026-09-14T05:45:30Zhttps://gredos.usal.es/oai/request

oai:gredos.usal.es:10366/1689242026-01-17T01:00:40Zcom_10366_4613com_10366_4576com_10366_3823col_10366_4616

Moradi Chekan, Ahmad Mesri Gundoshmian, Tarahom Latifi Amoghin, Meysam Shahgholi, Gholamhossein Shirzad Iraj, Mohammad Arribas, Juan Ignacio 2026-01-16T12:21:22Z 2026-01-16T12:21:22Z 2026-01 0889-1575 http://hdl.handle.net/10366/168924 10.1016/j.jfca.2025.108804 1096-0481 [EN] Aflatoxins are toxic and carcinogenic mycotoxins posing a significant threat to human health and food safety. A non-destructive hyperspectral imaging (HSI) system to automatically detect aflatoxin contamination in olive fruit and powder by machine learning was proposed. Imaging was conducted in the 418–1072 nm wavelength range. For whole fruit analysis, Linear Discriminant Analysis (LDA) achieved 100 % accuracy in binary classifying healthy and contaminated samples. The Support Vector Machine method also reached 98.75 % accuracy for the same purpose. For powdered olive samples, PLSR based on full spectral data, yielded coefficient of determination (R2) values of 0.9986 and 0.9858, for calibration and validation disjoint data sets, respectively. Furthermore, combining Decision Tree with a Learning Automata algorithm extracted the 15 optimal most discriminant (effective) wavelength (EW) values, enabling data dimension reduction without a significant loss of discrimination power. Using 15 effective wavelengths, LDA model had a maximum accuracy of 100 %. PLSR model developed using the selected effective wavelengths also had robust performance, with R2 of 0.89, validation set. Findings confirm the high potential of hyperspectral imaging for non-destructive and accurate detection of fungal toxin contamination in plant food, suggesting its potential as a rapid and reliable method in food industry. This research was supported by Spanish Ministry of Science and Innovation (MCIU) through the MCIN/AEI/10.13039/501100011033 under project PID2021-122210OB-I00, and cofunded by the European Regional Development Fund (FEDER/ERDF), ”A way of making Europe.” This work also received funding from strategic research programmes of excellence promoted by the regional government of Castilla y Leon, co-financed by the EU ERDF Operational Programme, through the iBRAINS-IN-CyL Unit of Excellence at the Castilla y Leon Neuroscience Institute (INCyL), Salamanca, Spain, under contract number CLU-2023-1-01. eng Elsevier Atribución-NoComercial 4.0 Internacional http://creativecommons.org/licenses/by-nc/4.0/ info:eu-repo/semantics/openAccess Aflatoxins Effective wavelengths (EW) Food safety Hyperspectral imaging (HSI) Olive fruit and powder Regression 3309.20 Propiedades de Los Alimentos 3309.15 Higiene de Los Alimentos 3309.90 Microbiología de Alimentos Non-destructive hyperspectral imaging in both olive fruit and powder for aflatoxin detection and estimation by machine learning info:eu-repo/semantics/article info:eu-repo/semantics/publishedVersion https://doi.org/10.1016/j.jfca.2025.108804 PID2021-122210OB-I00 CLU-2023-1-01 MCIN/AEI/10.13039/501100011033 Journal of Food Composition and Analysis 149 108804