DON is one of the mycotoxins with the highest detection rate and the most serious harm in wheat,is the main threat to wheat yield reduction and quality deterioration.In this study,the short-wave infrared hyperspec-tral information of DON content in wholewheat flour was first collected to establish a prediction model of DON content in whole wheat flour,and the characteristic wavelength was selected by continuous projection algorithm(SPA).The partial least square method(PLS)and support vector machine(SVM)models were established based on the full wavelength range and characteristic wavelength and compared.The results indicated that the optimal prediction model for DON content in whole wheat flour was SVM model based on the whole wavelength range.The corresponding pre-diction set determination coefficient R2P was 0.640,the root mean square error of prediction set(RMSEP)was 1 904.43 μg/kg,and the residual prediction residual(RPD)was 2.00.The optimal prediction model based on the characteristic wavelength was Autoscale-SVM model(SPA-Autoscale-SVM),and the R2P,RMSEP and RPD cor-responding to the model were 0.716,1 640.41 μg/kg and 2.06,respectively.The regression coefficient R2 between the predicted value and the measured value was 0.744 9,indicating that the SPA-Autoscale-SVM model could predict the change of DON content in whole wheat flour.In order to verify the stability of the established model,wheat samples were selected again for hyperspectral image acquisition,and the independent verification set was intro-duced into the established model.The fitting regression coefficient of the verification set was 0.717 8,indicating that the model could predict DON content in whole wheat flour.
NETL
NSTL
万方数据
