A practical method superior to traditional spectral identification: Two-dimensional correlation spectroscopy combined with deep learning to identify Paris species

Abstract

Spectral analysis has the characteristics of fast and nondestructive. In order to conform to the development of the times, a practical method beyond the traditional spectral analysis was established. For the first time, the two-dimensional correlation spectroscopy (2DCOS) images of Fourier-transform mid-infrared spectroscopy combined with the Residual Neural Network (ResNet) was used for the identification and analysis of 12 Paris species, and the second derivative 2DCOS rarely involved in previous researchers was established. Besides, the fusion strategy of 2DCOS images based on feature bands was first proposed for modeling analysis. From the results, (1) 2DCOS combined with ResNet can successfully identify 12 Paris species. (2) 2DCOS is a powerful tool for identification, whether it is used for image visual analysis or modeling analysis. (3) Compared with asynchronous 2DCOS, synchronous 2DCOS is more suitable for the identification and analysis of complex mixed systems such as traditional Chinese medicine. (4) The modeling based on feature bands fusion strategy of 2DCOS has better model performance and is also suitable for the analysis of small samples. To sum up, what we proposed is an innovative and feasible method with wide applicability, which can not only solve the problem of identifying Paris, provide ideas and methods for the selection of spectral types and feature bands, but also provide practical reference for the research in analytical chemistry and other related fields.