Vis-NIR spectroscopic discriminant analysis of aflatoxin B₁ excessive standard in peanut meal as feedstuff materials

A fast, simple and reagent-free detection method for aflatoxin B₁ (AFB₁) is of great significance to food safety and human health. Visible and near-infrared (Vis-NIR) spectroscopy was applied to the discriminant analysis of AFB₁ excessive standard of peanut meal as feedstuff materials. Two types of excessive standard discriminant models based on spectral quantitative analysis with partial least squares (PLS) and direct pattern recognition with partial least squares-discrimination analysis (PLS-DA) were established, respectively. Multi-parameter optimization of Norris derivative filtering (NDF) was used for spectral preprocessing; the two-stage wavelength screening method based on equidistant combination-wavelength step-by-step phase-out (EC-WSP) was used for wavelength optimization. A rigorous sample experimental design of calibration-prediction-validation was utilized. The calibration and prediction samples were used for modeling and parameter optimization, and the selected model was validated using the independent validation samples. For quantitative analysis-based, the positive, negative and total recognition-accuracy rates in validation (RAR_V⁺, RAR_V^-, and RAR_V) were 84.8 %, 74.6 % and 79.8 %, respectively; but, the relative root mean square error of prediction was as high as 51.0 %. For pattern recognition-based, the RAR_V⁺, RAR_V^-, and RAR_V were 93.3 %, 90.5 % and 91.9 %, respectively. Moreover, the number of wavelengths N was drastically reduced to 17, and the discrete wavelength combination was in NIR overtone frequency region. The results indicated that, the EC-WSP-PLS-DA model achieved significantly better discrimination effect. Thus demonstrated that Vis-NIR spectroscopy has feasibility for the excessive standard discrimination of aflatoxin B₁ in feedstuff materials.