Aflatoxin rapid detection based on hyperspectral with 1D-convolution neural network in the pixel level

• 1D-CNN was used to classify aflatoxin in pixel level based on hyperspectral data. • The best combination of parameters of 1D-CNN models was explored. • The test accuracy reached 96.35% for peanut, 92.11% for maize and 94.64% for mixed data. • The classification result was visualized pixel by pixel. Aflatoxin is commonly exists in moldy foods, it is classified as a class one carcinogen by the World Health Organization. In this paper, we used one dimensional convolution neural network (1D-CNN) to classify whether a pixel contains aflatoxin . Firstly we found the best combination of 1D-CNN parameters were epoch = 30, learning rate = 0.00005 and ‘relu’ for active function, the highest test accuracy reached 96.35% for peanut, 92.11% for maize and 94.64% for mix data. Then we compared 1D-CNN with feature selection and methods in other papers, result shows that neural network has greatly improved the detection efficiency than feature selection. Finally we visualized the classification result of different training 1D-CNN networks. This research provides the core algorithm for the intelligent sorter with aflatoxin detection function, which is of positive significance for grain processing and the prenatal detoxification of foreign trade enterprises.