Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Infrared spectrum modeling method based on consensus selection technique

A selection technology, infrared spectroscopy technology, applied in color/spectral characteristic measurement, special data processing applications, instruments, etc., can solve the problems of low prediction accuracy of quantitative analysis model, insufficient mining of sample spectral information, strong dependence of quantitative analysis model, etc. , to achieve the effect of improved modeling effect, representativeness and reasonable correction set

Active Publication Date: 2016-08-10
NORTHEASTERN UNIV
View PDF5 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0012] The purpose of the present invention is to provide a method of infrared spectral modeling based on consensus selection technology to solve the shortcomings mentioned in the above-mentioned background technology, especially the correction set selection method is only carried out in a single spectral space, resulting in the established quantitative The performance of the analysis model has a strong dependence on the quality of a single spectral space, and there is a problem of insufficient mining of sample spectral information during the division of the calibration set (for example, some spectral characteristic peaks with weaker intensity cannot be detected), which leads to the final The defects of the established quantitative analysis model are low prediction accuracy and poor stability

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Infrared spectrum modeling method based on consensus selection technique
  • Infrared spectrum modeling method based on consensus selection technique
  • Infrared spectrum modeling method based on consensus selection technique

Examples

Experimental program
Comparison scheme
Effect test

Embodiment

[0042] Embodiment: a kind of infrared spectrum modeling method based on consensus selection technology, such as Figure 1 ~ Figure 3 shown, including the following steps:

[0043] S1. Construct a plurality of derivative spectral spaces of different orders according to the original infrared spectral data of the sample; the derivative spectral spaces of different orders include: zero-order derivative spectral space, first-order derivative spectral space and second-order derivative spectral space; Design derivative spectrum estimator according to singular perturbation technology, in order to construct derivative spectrum space, described derivative spectrum estimator is DSE derivative spectrum estimator, concrete design is as follows:

[0044] x · 1 ( v ) ...

experiment example

[0051] Taking the spectral quantitative analysis of 60 beer samples as an example to further illustrate the method flow of the present invention, wherein the spatial distribution of the beer data set samples is as follows: Figure 4 As shown, the division and construction process of the CKS sample space are as follows:

[0052] Step 1. Construct zero-order derivative spectral space, first-order derivative spectral space and second-order derivative spectral space;

[0053] Step 2. In the respective derivative spectral spaces, use the KS strategy to construct the correction set 2 of the zero-order derivative spectral space, the correction set 3 of the first-order derivative spectral space, and the correction set 4 of the second-order derivative spectral space (correction of each order derivative spectral space Each set contains 45 samples of the set);

[0054] Step 3. Obtain the intersection of the above three derivative spectral space correction sets through consensus selectio...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention discloses an infrared spectrum modeling method based on a consensus selection technique. The infrared spectrum modeling method comprises the steps: according to original infrared spectroscopy data of samples, building a plurality of derivative spectrum spaces with different orders; in the plurality of derivative spectrum spaces with different orders, building respective calibration sets; treating the calibration sets of the derivative spectrum spaces by using the consensus selection technique, to obtain a basic calibration set; according to the basic calibration set, treating remaining samples in the derivative spectrum spaces with different orders, to obtain an extending calibration set; according to the basic calibration set and the extending calibration set, forming a final calibration set; and using the final calibration set and a validation set, and carrying out regression modeling. Through building the plurality of derivative spectrum spaces with different orders, then the derivative spectrum spaces with different orders are subjected to calibration set partitioning by using the consensus selection technique, the final calibration set formed from the basic calibration set and the extending calibration set is used for regression modeling, the model prediction accuracy is high, and the stability is good.

Description

technical field [0001] The invention relates to an infrared spectrum modeling method based on a consensus selection technology, and belongs to the technical field of spectrum analysis. Background technique [0002] Multivariate correction methods are widely used in the field of spectral quantitative analysis. The most commonly used method in the multivariate calibration process is PLS (Partial Least Squares) regression, the performance of which model depends heavily on the quality of the calibration set. However, it is a challenging problem to select informative and representative samples as the calibration set. [0003] At present, there have been several classic methods for selecting and constructing calibration sets, which are mainly divided into two categories, one is cluster analysis, and the other is uniform design. The goal of cluster analysis is to cluster the sample set according to certain rules, and select representative samples according to the clustering resul...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
IPC IPC(8): G01N21/35G06F17/50
CPCG01N21/35G06F30/367
Inventor 李志刚吕江涛王巧云
Owner NORTHEASTERN UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products

Browse by: Latest US Patents, China's latest patents, Technical Efficacy Thesaurus, Application Domain, Technology Topic, Popular Technical Reports.

© 2024 PatSnap. All rights reserved.Legal|Privacy policy|Modern Slavery Act Transparency Statement|Sitemap|About US| Contact US: help@patsnap.com