Detecting method for NIRS abnormal samples based on Monte Carlo cross validation

A detection method and abnormal sample technology, which is applied in the detection field of NIRS abnormal samples, can solve the problems of ignoring the connection between chemical values ​​and spectral data, mistakenly deleting border data samples, etc.

Inactive Publication Date: 2017-03-08
HEILONGJIANG UNIV
View PDF6 Cites 4 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

At the same time, most of the classical methods for judging abnormal samples only focus on chemical values ​​or spectral data unilaterally. Even if the two methods of judging abnormal chemical values ​​and judging abnormal spectral data are considered comprehensively, the relationship between chemical values ​​and spectral data will still be ignored. Leading to mistaken deletion of boundary data samples
Commonly, the Mahalanobis distance method is usually only used to distinguish the abnormality of the spectral data, while the Cook distance method can only be used to identify the abnormality of the chemical value of the sample

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
  • Detecting method for NIRS abnormal samples based on Monte Carlo cross validation
  • Detecting method for NIRS abnormal samples based on Monte Carlo cross validation
  • Detecting method for NIRS abnormal samples based on Monte Carlo cross validation

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0042] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only some of the embodiments of the present invention, not all of them. Based on the embodiments of the present invention, all other embodiments obtained by persons of ordinary skill in the art without making creative efforts belong to the protection scope of the present invention.

[0043] The wheat samples came from 6 regions in 2011, including the upper reaches of the Yangtze River, the middle and lower reaches of the Yangtze River, the northeast, and the northwest, with a total of 116 samples. The near-infrared scanning and Kjeldahl method were carried out on these samples respectively, and the chemical value and spectral data of 116 groups of wheat proteins were obtained.

[0044] The present invention provides a kind of d...

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 provides a detecting method for NIRS abnormal samples based on Monte Carlo cross validation. The detecting method for NIRS abnormal samples based on Monte Carlo cross validation comprises the following steps: (1) confirming the optimal principal component of the pretreated spectroscopic data using the group-outside-judging method and establishing an O-PLSR prediction model; (2) judging the stability of the O-PLSR prediction model; (3) establishing a large number of O-PLSR models randomly by means of MCCV and recognizing the strong influence point; (4) distinguishing the abnormal values in the strong influence points by two-trial-judging method; (5) verifying whether the abnormal samples are completely removed or not by means of MCCV method again. The detecting method for NIRS abnormal samples based on Monte Carlo cross validation can verify the abnormal samples more comprehensively and accurately, therefore, the completely removing of the abnormal samples can be ensured.

Description

technical field [0001] The invention relates to a method for detecting abnormal samples, in particular to a method for detecting abnormal samples in NIRS based on Monte Carlo cross-validation. Background technique [0002] Near Infrared Spectroscopy (Near Infrared Spectrum, NIRS) analysis technology is a non-destructive testing technology based on the analysis of sample composition characteristics, and has been widely used in many fields such as crops, petrochemicals, and medicine in recent years. When using NIRS analysis technology to analyze samples quantitatively or qualitatively, the relationship model between the reference value and spectral data is firstly established according to the modeling sample, and then the model is used for spectral data analysis of unknown samples. In this process, the accuracy of the modeling samples directly determines the quality of the built model. However, under normal circumstances, due to the sample itself and collection techniques and...

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): G06F19/00
CPCG16B5/00
Inventor 叶丹丹孙来军谈文艺车文凯张丹
Owner HEILONGJIANG UNIV
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products

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