Spectral characteristic variable selection and optimization method based on Stacking integrated framework
A spectral feature and variable selection technology, applied in the field of spectral analysis, to achieve the effect of reducing the amount of calculation, avoiding over-fitting, and reducing computing time
- Summary
- Abstract
- Description
- Claims
- Application Information
AI Technical Summary
Problems solved by technology
Method used
Image
Examples
Embodiment Construction
[0059] Such as figure 1 As shown, the spectral feature variable selection and optimization method based on the Stacking integration framework includes the following steps,
[0060] Step 1: Configure multiple ethanol samples with a predetermined concentration range, and obtain each sample with a thickness of 12000-4000 cm -1 Near-infrared spectral information in the wavenumber range, the sample is divided into a training sample set and a test sample set in proportion;
[0061] Step 2: Select representative SiPLS, UVE, and PSO from the categories of variable interval selection method, variable information selection method, and variable optimization selection method;
[0062] Step 3: Use the feature variable selection method selected in step 2 to construct three base learners, and use the Stacking integration framework to integrate the base learners to build a meta-learner. The meta-learner uses a non-linear support vector regression method to learn the basic The output of the ...
PUM
Abstract
Description
Claims
Application Information
- R&D Engineer
- R&D Manager
- IP Professional
- Industry Leading Data Capabilities
- Powerful AI technology
- Patent DNA Extraction
Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic.
© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap