Two dimensional correlation spectroscopy combined with ResNet: Efficient method to identify bolete species compared to traditional machine learning

Different species of bolete have different nutritional and medicinal value, which leads to the phenomenon of shoddy in the market from time to time. Therefore, consumers need a fast and effective detection method to identify their species. In this paper, different data pretreatment was carried out for the Fourier transform near infrared (FT-NIR) spectra, and the modeling results of partial least squares discrimination analysis (PLS-DA), support vector machines (SVM) and residual neural network (ResNet) were compared. The results show that PLS-DA and SVM models need a suitable combination of pretreatment for spectral data. The purpose is to improve the accuracy of the model and avoid over fitting. After spectral pretreatment, the accuracy of PLS-DA model were improved to 99.63% and 97.38% respectively. In order to ensure that the SVM model does not have the risk of over fitting, the accuracy of the SVM model after pretreatment were reduced to 98.5% and 93.63%. The ResNet model was established based on the original spectrum. The accuracy of the model was 100%, and there is no over fitting phenomenon, which is one of the advantages of the model. Comparing the above three models, ResNet is the best model for bolete species identification. •The spectral modeling results of different pretreatment were compared.•ResNet model was used to accurately identify 801 fruiting bodies of bolete.•Synchronous 2DCOS spectral model has good discrimination performance.•ResNet model has good performance and does not have the problem of over fitting.