Spectral feature variable selection and optimization method based on stacking integration framework

Abstract

The invention discloses a spectral characteristic variable selection and optimization method based on the Stacking integration framework, including constructing a sample set, dividing the sample set into a training sample set and a test sample set; in the variable interval selection method, the variable information selection method, and the variable optimization selection method Select a representative feature variable selection method from the large category; build multiple base learners, use the Stacking integration framework to integrate the base learners, build a meta-learner, and use the output of the base learner as the input of the meta-learner; use The sample set trains and tests the base learner and meta-learner of the Stacking integration framework; the spectrum information to be detected is input into the base learner, and the detection result of the spectrum to be detected is obtained according to the output of the meta-learner. The spectral characteristic variable selection and optimization method based on the Stacking integration framework of the present invention overcomes the defect of a single characteristic variable selection method, has high detection accuracy for test samples, and has good stability of detection results.

Description

technical field [0001] The invention belongs to the field of spectral analysis, and in particular relates to a method for selecting and optimizing spectral characteristic variables based on a Stacking integration framework. Background technique [0002] According to the definition of the American Society for Testing and Materials Testing, the NIR (Near Infrared) region of the near-infrared spectrum refers to electromagnetic waves with a wavelength in the range of 780-2526nm. It belongs to the double frequency and main frequency absorption spectrum of the molecular vibration spectrum, and the near-infrared spectrum is mainly generated when the molecular vibration transitions from the ground state to a high energy level due to the anharmonic nature of the molecular vibration. The near-infrared spectral region is consistent with the combined frequency of vibrations of hydrogen-containing groups (O-H, N-H, C-H) in organic molecules and the absorption regions of multiple levels o...

AI Technical Summary

Problems solved by technology

[0007] The purpose of the present invention is to solve the above problems, propose a spectral feature variable selection and optimization method based on the Stacking integration framework, overcome the defect of a single feature variable selection method, and improve prediction accuracy

Images