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

Near-infrared spectral analysis method for medical fungi

A near-infrared spectroscopy, medicinal fungus technology, applied in the direction of material analysis, analysis materials, instruments, etc. by optical means, can solve problems such as loss, and achieve the effect of solving accuracy

Active Publication Date: 2019-06-14
JILIN UNIV
View PDF7 Cites 2 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

It solves the problem that a large number of noise bands affect the accuracy of feature band selection in the original near-infrared spectrum data, and the loss of some tiny features caused by relying on expert experience for artificial feature preprocessing. Human intervention to realize the automatic extraction of characteristic bands in the original near-infrared spectrum and the prediction of the content of active ingredients

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
  • Near-infrared spectral analysis method for medical fungi
  • Near-infrared spectral analysis method for medical fungi
  • Near-infrared spectral analysis method for medical fungi

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0049] 1) Collect and store the near-infrared spectra of 165 Antrodia camphorata samples and 200 Matsutake samples, such as Figure 4 As shown, the samples of Antrodia camphorata and Matsutake mushrooms were scanned using a Shimadzu UV-3150 UV-Vis-NIR spectrophotometer and a Shimadzu ISR-3100 integrating sphere accessory, with a scanning wavelength range of 800-2500 nm and a spectral band density of 12 nm. , the barium sulfate reference substance was used as the blank control, the spectral sampling interval was 1 nm, each sample was scanned 3 times, and the average value was finally taken as the spectral data of the sample, and the polysaccharide and The contents of 4 active ingredients in triterpenes and pine mushroom samples, including polysaccharide and ergosterol, were recorded in excel form as experimental data sets. The 4 groups of data sets were divided and randomly selected from each group of data sets 80% of the total number of the group is used as the training set, a...

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 near-infrared spectral analysis method for medical fungi. According to original spectroscopic data, full independent spectral pretreatment and feature band extracted near-infrared spectral analysis (ABRN) are conducted, through an Attention module, automatic pretreatment of enhancing feature bands and attenuating noise bands is conducted on an original spectrum, and then feature extraction and final content prediction are conducted on the spectroscopic data treated by the Attention module through a residual neural network. The problem that a great number of noise bandsaffect the selection accuracy of the feature bands in the original near-infrared spectrum data is solved, and the loss of certain minor features due to artificial feature pretreatment needing to relyon the expert experience is avoided, and according to the near-infrared spectral analysis method for the medical fungi, according to the situation that human intervention of the original near-infrared spectrum is not required, automatic extraction of feature bands in the original near-infrared spectrum and prediction of the active component content are realized.

Description

technical field [0001] The invention provides a near-infrared spectroscopy analysis method for medicinal fungi, which is used for rapid detection of active components of Chinese medicinal materials, and belongs to the technical field of active component analysis of traditional Chinese medicinal materials. Background technique [0002] Medicinal fungi, such as Cordyceps sinensis, Antrodia cinnamomea and Matsutake, etc., have the functions of enhancing human immunity, anti-tumor and anti-cancer. The active ingredients in medicinal fungi can be used in a wide range of clinical treatments, and these ingredients can be quickly detected by near-infrared spectroscopy , Near Infrared Spectroscopy (NIRS) is a convenient, rapid, and non-invasive analytical method that has been applied to quantitative analysis of medicinal fungi data. By scanning the near-infrared spectrum of the sample, the frequency information of a single chemical bond in the molecule can be recorded. Due to the adv...

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): G01N21/359G06N3/04
Inventor 白天郭书宇姚刚罗晓腾乐生张梦芮黄岚
Owner JILIN 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