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

Sample component measurement method based on PCR-ELM algorithm

A technology of PCR-ELM and determination method, which is applied in the field of sample component determination based on PCR-ELM algorithm, can solve the problems of over-fitting and error instability, and achieve the goal of improving accuracy, increasing sample size and reducing multicollinearity Effect

Active Publication Date: 2015-11-25
NORTHEASTERN UNIV
View PDF3 Cites 5 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0004] The purpose of the present invention is to provide a method for determining sample components based on the PCR-ELM algorithm, which can effectively solve the problems in the prior art, especially the overfitting and errors in the determination of sample components using extreme learning machines unstable problem

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
  • Sample component measurement method based on PCR-ELM algorithm
  • Sample component measurement method based on PCR-ELM algorithm
  • Sample component measurement method based on PCR-ELM algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0115] Embodiments of the present invention: a kind of sample component determination method based on PCR-ELM algorithm, such as Figure 33 shown, including the following steps:

[0116] S1, collecting infrared spectrum data of the sample to be tested;

[0117] S2, obtain the content of each component in the sample corresponding to the infrared spectrum data through the PCR-ELM model; the PCR-ELM model is obtained by reducing the dimensionality of the ELM hidden layer output matrix of the high-dimensional small sample by using the PCR algorithm ; Specifically established by the following methods:

[0118] a. Collect the infrared spectrum data of n samples X and the content data of each component in the corresponding samples as training samples, wherein each sample contains m attributes, that is, X is an n*m dimensional matrix;

[0119] b. Centralize the training samples;

[0120]c. After the centralization process, calculate the ELM hidden layer output of each sample to obt...

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 a sample component measurement method based on a PCR-ELM algorithm. The sample component measurement method comprises the following steps: S1, acquiring infrared spectrum data of a sample to be measured; S2, obtaining the contents of the respective components in the sample corresponding to the infrared spectrum data according to a PCR-ELM model. According to the sample component measurement method, the PCR-ELM model is used for processing the infrared spectrum data of the sample to be measured to obtain the contents of the respective components in the sample corresponding to the infrared spectrum data. Compared with the method adopting a conventional model for data processing, the method disclosed by the invention has the advantages that the phenomenon of overfitting is avoided, and the multicollinearity among variables is reduced; furthermore, the fitting precision is improved, the forecasting precision of the spectrum data with a small sample amount and high dimension, and the stability of the forecasting precision are improved, and the application range of the ELM algorithm is expanded.

Description

technical field [0001] The invention relates to a component determination method, in particular to a sample component determination method based on PCR-ELM algorithm. Background technique [0002] Infrared (Infrared:IR) spectral analysis is a process of quantitative and qualitative analysis of the information characteristics of infrared spectrum by means of computer technology and chemometrics. Due to the advantages of convenient, fast, low cost, and no damage to samples, infrared spectroscopy is favored, especially in the fields of food industry, agricultural production, and pharmaceutical manufacturing. In the practical application of food, agriculture, industry and other fields, IR spectral detection technology relies on the correlation algorithm of chemometrics to establish a quantitative functional relationship between chemical composition and spectral absorption, relying on the function between variables and independent variables relationship, the composition and cont...

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
Patent Type & Authority Applications(China)
IPC IPC(8): G01N21/35
Inventor 单鹏赵煜辉周琳刘福来马海涛于长永
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