Artificial and Algorithmic Screening of Infrared Spectral Feature Bands of Gastrodia Elata to Achieve Rapid Identification of its Species

Gastrodia elata is a traditional Chinese medicine with medicinal and edible values. In this paper, two kinds of datasets were acquired: partial spectra (artificially obtained peak segment spectra) and full spectra (4000-400 cm-1). Competitive adaptive reweighted sampling algorithm (CARS) and successive projection algorithm (SPA) were utilized to extract the characteristic variables of the two datasets, and Partial Least Squares Discriminant Analysis (PLS-DA) models, Support Vector Machines (SVM) models, Random Forests (RF) models, and Deep Learning models were established. It was found that among the PLS-DA models whole-MSC-CARS-PLS-DA was optimal, with an RMSEP of 0.0658; among the SVM models Partial-SNV+SPA-SVM was the best, with a kernel parameter of 0.1768 and the lowest number of support vectors; among the RF models Partial-SNV-RF is optimal, but not as effective as the first two models. The loss value of the deep learning model built based on effective information is 0.001, and the model building time is short and directly uses the original data. Therefore, the deep learning model based on feature bands is the most suitable for practical application compared with other models.