Identification of adulterated honey with different varieties and concentrations based on hyperspectral imaging technology combined with deep learning

Abstract

Honey is an important agricultural and sideline product in China, which contains the high nutritional value and commercial value. An advanced honey adulteration identification model can help beekeepers and consumers better identify honey and avoid losses. Given the complex operation and high technical requirements of traditional honey identification experimental instruments, a new model for quickly and efficiently identifying honey adulteration with different kinds and concentrations was developed in this study. Based on the data of adulterated honey with different varieties and concentrations obtained by hyperspectral imaging technology, a large number of regions of interest were randomly selected as samples. Then, the classification model is established by adopting preprocessing methods such as standardization, centralization, multivariate scattering correction, standard variable transformation, first-order difference, and second-order difference, combining the advantages of convolutional neural network and support vector machine. Finally, the accuracy of the results is compared, and D1-CNN-SVM is determined as the best classification prediction model, with an accuracy rate of 100%. At the same time, through the analysis of the confusion matrix of experimental results, this study summarizes the difficulties in identifying adulterated honey of different varieties and concentrations.