Raman spectrum classification and identification of COVID-19 based on RFE-RF

Abstract

The Raman spectral data feature is generally the Raman wavelength of the sample, and there is a correlation between the feature attributes. Too many features will lead to weak generalization ability of the model, so a Recursive Feature Elimination (RFE) dimensionality reduction method combined with BP neural network is proposed to classify the Raman spectrum of the COVID-19. Firstly, the collected serum Raman spectral data of the population were processed, the maximum and minimum standard scaling method (Min-Max), the Savitzky-Golay smoothing filter method, and then the recursive feature elimination (RFE-RF) based on the random forest base model and two different dimensionality reduction methods of PCA reduce the dimensionality of Raman spectral data and classify them through the BP neural network algorithm model. The experimental results show that the RFE-RF dimensionality reduction method can improve the accuracy of the classification algorithm, providing a new idea for the detection of the COVID-19, with high accuracy, and the classification accuracy of the model is 92.47%