Rapid and non-destructive detection of aflatoxin contamination of peanut kernels using visible/near-infrared (Vis/NIR) spectroscopy

Authors: TAO, FEIFEI - Mississippi State University; YAO, HAIBO - Mississippi State University; HRUSKA, ZUZANA - Mississippi State University; Liu, Yongliang; Rajasekaran, Kanniah - Rajah; Bhatnagar, Deepak

Submitted to: Proceedings of SPIE
Publication Type: Proceedings
Publication Acceptance Date: 5/15/2018
Publication Date: 5/15/2018
Citation: Tao, F., Yao, H., Hruska, Z., Liu, Y., Rajasekaran, K., Bhatnagar, D. 2018. Rapid and non-destructive detection of aflatoxin contamination of peanut kernels using visible/near-infrared (Vis/NIR) spectroscopy. Proceedings of SPIE, Sensing for Agriculture and Food Quality and Safety X. Paper No. 106650K. https://doi.org/10.1117/12.2304399.
DOI: https://doi.org/10.1117/12.2304399

Interpretive Summary:

Technical Abstract: Aflatoxin contamination can occur in a wide variety of agricultural products pre- and post-harvest, posing potential severe health hazards to human and livestock. However, current methods for detecting aflatoxins are generally based on wet chemical analyses, which are time-consuming, destructive to test samples and require skilled personnel to perform, making them impossible for large-scale non-destructive screening and on-site detection. In this study, we utilized the visible/near-infrared (Vis/NIR) spectroscopy over the spectral range of 400-2500 nm to detect contamination of shelled commercial peanut kernels with the predominant aflatoxin B1 (AFB1). Our results indicated the usefulness of Vis/NIR spectroscopy combined with the chemometric techniques of partial least squares discriminant analysis (PLS-DA) and least squares support vector machine (LS-SVM) in identifying the AFB1 contamination of peanut kernels. Both PLS-DA and LS-SVM methods provided satisfactory classification results using the full spectral information over the ranges of 410-1070 (I), 1120-2470 nm (II) and I+II. Based on the classification thresholds of 20 and 100 ppb, the best PLS-DA prediction results using the full spectra yielded average accuracies of 87.9% and 94.0%. The overall accuracies were 88.6% and 91.4%. Correspondingly, with the classification thresholds of 20 and 100 ppb, the best average accuracies recorded using LS-SVM were 90.9% and 98.0%. The best overall accuracies were 90.0% and 97.1%. In addition, the simplified models of CARS-PLS-DA and CARS-LS-SVM also demonstrated good prediction capability in identifying the AFB1 contamination from peanut surface. Based on both classification thresholds of 20 and 100 ppb, the best CARS-PLS-DA and CARS-LS-SVM prediction results were = 90.0% in both average accuracy and overall accuracy. Most importantly, the computation complexity and the employed data dimensionality were significantly reduced by using the simplified models.