CN110296955A - Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method and Radix Glycyrrhizae quality evaluating method based on kernel optimization - Google Patents
Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method and Radix Glycyrrhizae quality evaluating method based on kernel optimization Download PDFInfo
- Publication number
- CN110296955A CN110296955A CN201910546901.3A CN201910546901A CN110296955A CN 110296955 A CN110296955 A CN 110296955A CN 201910546901 A CN201910546901 A CN 201910546901A CN 110296955 A CN110296955 A CN 110296955A
- Authority
- CN
- China
- Prior art keywords
- radix glycyrrhizae
- kernel
- sample
- model
- indicate
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000004458 analytical method Methods 0.000 title claims abstract description 37
- 238000000034 method Methods 0.000 title claims abstract description 21
- 238000004497 NIR spectroscopy Methods 0.000 title claims abstract description 17
- 238000005457 optimization Methods 0.000 title claims abstract description 16
- 238000010276 construction Methods 0.000 title claims abstract description 13
- 230000002068 genetic effect Effects 0.000 claims abstract description 7
- 238000004611 spectroscopical analysis Methods 0.000 claims abstract description 7
- 238000002329 infrared spectrum Methods 0.000 claims description 21
- 238000012360 testing method Methods 0.000 claims description 14
- 238000012549 training Methods 0.000 claims description 12
- QGZKDVFQNNGYKY-UHFFFAOYSA-O Ammonium Chemical compound [NH4+] QGZKDVFQNNGYKY-UHFFFAOYSA-O 0.000 claims description 11
- 238000010238 partial least squares regression Methods 0.000 claims description 5
- 230000003595 spectral effect Effects 0.000 claims description 5
- 238000004364 calculation method Methods 0.000 claims description 3
- 238000003908 quality control method Methods 0.000 claims description 3
- 238000001228 spectrum Methods 0.000 claims description 2
- 230000007613 environmental effect Effects 0.000 claims 1
- 230000008901 benefit Effects 0.000 abstract description 6
- 238000000605 extraction Methods 0.000 abstract description 3
- 238000013441 quality evaluation Methods 0.000 abstract description 2
- 241000202807 Glycyrrhiza Species 0.000 description 8
- 235000001453 Glycyrrhiza echinata Nutrition 0.000 description 8
- 235000006200 Glycyrrhiza glabra Nutrition 0.000 description 8
- 235000017382 Glycyrrhiza lepidota Nutrition 0.000 description 8
- 229940010454 licorice Drugs 0.000 description 8
- 239000000463 material Substances 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 3
- 238000001514 detection method Methods 0.000 description 2
- 238000010183 spectrum analysis Methods 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 244000025254 Cannabis sativa Species 0.000 description 1
- 241000183712 Cerinthe major Species 0.000 description 1
- 206010011224 Cough Diseases 0.000 description 1
- 240000008917 Glycyrrhiza uralensis Species 0.000 description 1
- 235000000554 Glycyrrhiza uralensis Nutrition 0.000 description 1
- 241000594394 Hedyotis Species 0.000 description 1
- 206010062717 Increased upper airway secretion Diseases 0.000 description 1
- 208000005392 Spasm Diseases 0.000 description 1
- 238000002835 absorbance Methods 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 229910002056 binary alloy Inorganic materials 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 230000006835 compression Effects 0.000 description 1
- 238000007906 compression Methods 0.000 description 1
- 235000009508 confectionery Nutrition 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 239000003814 drug Substances 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000004836 empirical method Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000004128 high performance liquid chromatography Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 235000021374 legumes Nutrition 0.000 description 1
- 239000007791 liquid phase Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 208000026435 phlegm Diseases 0.000 description 1
- 239000000843 powder Substances 0.000 description 1
- 238000002203 pretreatment Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 210000000952 spleen Anatomy 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a kind of Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method and Radix Glycyrrhizae quality evaluating method based on kernel optimization, comprising: sample database is established according to the Radix Glycyrrhizae spectroscopic data of acquisition and sample reference value first；Radial base, multinomial and broad sense T student function is selected to realize the feature extraction of higher-dimension spectroscopic data respectively as the kernel function of core principle component analysis；Based on this, select radial basis function as the kernel function of core partial least square model.The related hyper parameter for using genetic algorithm optimization kernel function simultaneously, establishes Radix Glycyrrhizae NIR Spectroscopy Analysis Model, converts regression problem for quality evaluation problem, analyze Radix Glycyrrhizae quality.The present invention not only has many advantages, such as easy to operate, lossless, and ensure that Radix Glycyrrhizae quality safely, effectively.
Description
Technical field
The invention belongs to near-infrared spectrum analysis detection technique fields, are related to licorice medicinal materials near infrared spectrum detection and analysis
Model building method.
Background technique
Radix Glycyrrhizae, also known as Herba Hedyotis cantonensis root, honeywort, be glycyrrhizic legume Glycyrrhiza uralensis Fisch. root and
Rhizome, have invigorate the spleen and benefit qi, the medical values such as expelling phlegm and arresting coughing, relieving spasm to stop pain.Licorice medicinal materials currently on the market are also mostly artificial
Plantation influences treatment effect since the diversification of planting patterns and the otherness of planting environment cause Radix Glycyrrhizae quality irregular
Fruit.Radix Glycyrrhizae quality evaluating method mainly has artificial empirical method and ultra micro waveforms method, DNA bar code identification method, efficient liquid phase at present
The methods of chromatography, exist be affected by subjective factor, be complicated for operation, analytical cycle is long, needs to consume the disadvantages such as a large amount of reagents
End.
Near-infrared spectral analysis technology is one kind quickly analysis set up by substance to the absorption of near infrared light
Method, with analysis speed, fast, lossless, sample is without many advantages such as pretreatments.Chemistry is combined using near-infrared spectrum technique
Meterological, it can be achieved that licorice ingredient content quick predict, provide reference for Radix Glycyrrhizae quality evaluation.
Summary of the invention
The purpose of the present invention is to provide a kind of Radix Glycyrrhizae NIR Spectroscopy Analysis Model building side based on kernel optimization
Method and Radix Glycyrrhizae quality evaluating method.
To achieve the above object, the present invention adopts the following technical scheme:
Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method based on kernel optimization, includes the following steps:
Step 1: collecting Radix Glycyrrhizae sample, and be numbered；
Step 2: the Radix Glycyrrhizae being collected into for step 1 chooses quality control index of the ammonium glycyrrhetate as Radix Glycyrrhizae, and carries out
Its assay；
Step 3: obtaining the corresponding near infrared spectrum data of Radix Glycyrrhizae sample；
Step 4: single sample data include the near infrared spectrum data and ammonium glycyrrhetate content of sample, by sample data set
It is divided into training set and test set；
Step 5: using training set as the input of core principle component analysis-Kernel partial least squares regression model, being calculated using heredity
Method carries out kernel functional parameter optimizing, obtains the core principle component analysis with optimal parameter-core partial least square model；
Step 6: test set sample is predicted using trained core principle component analysis-core partial least square model,
It is related to actual value based on predicted root mean square error PRMSE, relative error PRSE and related coefficient index R assessment prediction value
Property.
Preferably, near infrared spectrum scanning condition described in step 3 are as follows: spectral region 10001.03cm-1-
3999.6400cm-1, resolution ratio 4cm-1, scanning times 64 times, it is averaged the original spectrum as Radix Glycyrrhizae sample；Environment item
Part is 22 DEG C ± 0.5 DEG C of temperature, relative humidity 40% ± 2%.
Preferably, in step 5, kernel function using radial basis function as core principle component analysis, model are as follows:
K(xi,xj)=exp (- | xi-xj|2/2σ1 2)
Preferably, in step 5, kernel function using polynomial function as core principle component analysis, model are as follows:
K(xi,xj)=(xi Txj)d
Preferably, in step 5, kernel function using broad sense T student function as core principle component analysis, model are as follows:
K(xi,xj(1+ (the x of)=1/i Txj)α)
Preferably, in step 5, kernel function using radial basis function as Kernel partial least squares regression, model are as follows:
K(xi,xj)=exp (- | xi-xj|2/2σ2 2)
Preferably, predicted root mean square error PRMSE, relative error PRSE described in step 6 and coefficient R index are specific
Calculation formula are as follows:
Wherein l2Indicate training samples number, piIndicate the reference value of training sample, siIndicate that core principle component analysis-core is inclined
The regression forecasting of least square model as a result,Indicate the mean value of all test sample reference values,Indicate core principle component analysis-
The regression forecasting mean value of core partial least square model.
Based on the Radix Glycyrrhizae quality evaluating method of above-mentioned Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method, obtain to be detected sweet
Near infrared spectrum data is inputted trained Radix Glycyrrhizae NIR Spectroscopy Analysis Model by the near infrared spectrum data of grass, output to
Detect the ammonium glycyrrhetate content of Radix Glycyrrhizae.
The utility model has the advantages that the present invention by near-infrared spectrum technique combination Chemical Measurement establish licorice medicinal materials spectral information at
Divide the relational model of information, realizes the Fast Evaluation analysis of Radix Glycyrrhizae quality.
Present invention introduces the feature extractions that core principle component analysis realizes higher-dimension spectroscopic data, and using genetic algorithm to core letter
Several related hyper parameter carries out optimizing, have many advantages, such as it is quick, be not easy to fall into local optimum.
Present invention introduces core offset minimum binary building regression models to be used to express the non-linear of input data and output data
Relationship, while introducing genetic algorithm and optimizing is carried out to the related hyper parameter of kernel function, have quickly, be not easy to fall into local optimum
The advantages that.
Detailed description of the invention
Fig. 1 flow chart of the method for the present invention；
The near-infrared original absorbance spectrogram of Fig. 2 licorice medicinal materials powder；
(a) in Fig. 3, (b), (c) be respectively ammonium glycyrrhetate content near-infrared model model1 in gained test set,
The linear relationship chart of model2, model3 predicted value and actual value.
Specific embodiment
Technical solution of the present invention is described in detail with reference to the accompanying drawing, but the contents of the present invention are not limited to this.
The present invention provides licorice medicinal materials Near-Infrared Quantitative Analysis model and method for building up, can Fast nondestructive evaluation Radix Glycyrrhizae medicine
Material, specifically includes the following steps:
Radix Glycyrrhizae sample is collected from different sources, and is numbered.
Quality control index of the ammonium glycyrrhetate as licorice medicinal materials is chosen, is measured using high performance liquid chromatography.
Using near-infrared spectrum technique, spectral scanning range 10001.03cm-1-3999.6400cm-1, resolution ratio is
4cm-1, each Sample Scan 64 times, original near infrared spectrum of the average value as sample obtain the near infrared spectrum number of Radix Glycyrrhizae
According to.The near-infrared absorption spectrum of Radix Glycyrrhizae sample is as shown in Figure 2.
Data set division mode uses random division, and saves ready-portioned training set and test set data, guarantees each
The training set of model is identical as test set.
Each sample spectral data includes 1557 characteristic points, has high dimensional nonlinear feature.Present invention introduces core it is main at
The feature extraction of high dimensional data is realized in analysis, realizes dimension compression.
(1) kernel function of the radial basis function as core principle component analysis, model are used are as follows:
K(xi,xj)=exp (- | xi-xj|2/2σ1 2)
(2) kernel function of the polynomial function as core principle component analysis, model are used are as follows:
K(xi,xj)=(xi Txj)d
(3) kernel function of the broad sense T student function as core principle component analysis, model are used are as follows:
K(xi,xj(1+ (the x of)=1/i Txj)α)
Based on the data after dimensionality reduction, training set Radix Glycyrrhizae near infrared spectrum and corresponding reference value are established using core offset minimum binary
Between quantitative calibration models, the kernel function using radial basis function as Kernel partial least squares regression, model are as follows:
K(xi,xj)=exp (- | xi-xj|2/2σ2 2)
Genetic algorithm is introduced respectively to three groups of kernel functional parameter (1) radial basis function bandwidth σ1With radial basis function σ2、(2)
Polynomial function number d and radial basis function σ2, (3) broad sense T student function number α and radial basis function σ2Carry out optimizing.Specifically
Step is as shown in Figure 3:
(1) three groups of hyper parameters of algorithm are initialized, and is encoded using binary system；
(2) decoding calculates fitness value and judges whether to meet termination condition, if satisfied, turning (4)；
(3) selection cross and variation operation is carried out, progeny population is generated, turns (2)；
(4) termination algorithm is run, the hyper parameter that decoded output optimization is completed.
The optimization aim of model is defined as the root-mean-square error of training sample, fitness model are as follows:
Wherein l1Indicate training samples number, piIndicate the reference value of training sample, siIndicate that core principle component analysis-core is inclined
The regression forecasting result of least square model.
The optimized parameter obtained by genetic algorithm optimizing successively establishes 3 best near-infrared quantitative models respectively, specifically
Are as follows:
(1) (kernel function is respectively radial basis function, radial base to core principle component analysis-core partial least square model model1
Function)；
(2) (kernel function is respectively polynomial function, radial base to core principle component analysis-core partial least square model model2
Function)；
(3) (kernel function is respectively broad sense T student function, radial direction to core principle component analysis-core partial least square model model3
Basic function).
Best near-infrared quantitative model verifying, is based on predicted root mean square error PRMSE, relative error PRSE and related coefficient
Index R calculates the correlation of predicted value and actual value, specific formula for calculation are as follows:
Wherein l2Indicate test sample quantity, piIndicate the reference value of test sample, siIndicate that core principle component analysis-core is inclined
The regression forecasting of least square model as a result,Indicate the mean value of all test sample reference values,Indicate core principle component analysis-
The regression forecasting mean value of core partial least square model.
1 model performance evaluation result of table
As can be seen from Table 1, the prediction optimal result of ammonium glycyrrhetate content in external unknown licorice medicinal materials sample is generated
In core principle component analysis-core partial least square model model1 (kernel function is respectively radial basis function, radial basis function), just
Root error is 0.291, relative error 0.104, related coefficient 0.96, the experimental results showed that the Radix Glycyrrhizae based on kernel optimization
NIR Spectroscopy Analysis Model has preferable predictive ability and precision of prediction.
Wherein (kernel function is respectively polynomial function, radial base to core principle component analysis-core partial least square model model2
Function) precision of prediction is only second to model1, root-mean-square error 0.296, relative error 0.106, related coefficient 0.96.Core
Principal component analysis-core partial least square model model3 (kernel function is respectively broad sense T student function, radial basis function) with only exist
The experimental result that kernel function is introduced in partial least square model is close, and performance is superior to introduce the quantitative correction mould before kernel function
Type.
The experimental results showed that introduce kernel function can the preferable non-linear relation that must be expressed between spectroscopic data and reference value,
The genetic algorithm being introduced into can preferably optimize related hyper parameter in kernel function.
Near infrared spectrum data is inputted trained Radix Glycyrrhizae near-infrared by the near infrared spectrum data for obtaining Radix Glycyrrhizae to be detected
Spectrum analysis model, exports the ammonium glycyrrhetate content of Radix Glycyrrhizae to be detected, and ammonium glycyrrhetate content is more than or equal to 2% and determines the Radix Glycyrrhizae matter
Amount is qualified, otherwise unqualified.
The above content is a further detailed description of the present invention in conjunction with specific preferred embodiments, and it cannot be said that
Specific implementation of the invention is only limited to these instructions.The technical side that any interest field covered with the application patent is implemented
Case or anyone skilled in the art make many possible changes and modifications using the disclosure above method content
Scheme, all belong to the scope of protection of the present invention.
Claims (8)
1. the Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method based on kernel optimization, which comprises the steps of:
Step 1: collecting Radix Glycyrrhizae sample, and be numbered；
Step 2: the Radix Glycyrrhizae being collected into for step 1 chooses quality control index of the ammonium glycyrrhetate as Radix Glycyrrhizae, and carries out it and contain
It is fixed to measure；
Step 3: obtaining the corresponding near infrared spectrum data of Radix Glycyrrhizae sample；
Step 4: single sample data include the near infrared spectrum data and ammonium glycyrrhetate content of sample, and sample data set is divided
For training set and test set；
Step 5: using training set as the input of core principle component analysis-Kernel partial least squares regression model, using genetic algorithm into
Row kernel functional parameter optimizing obtains the core principle component analysis with optimal parameter-core partial least square model；
Step 6: test set sample being predicted using trained core principle component analysis-core partial least square model, is based on
The correlation of predicted root mean square error PRMSE, relative error PRSE and related coefficient index R assessment prediction value and actual value.
2. the Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method according to claim 1 based on kernel optimization, special
Sign is, near infrared spectrum scanning condition described in step 3 are as follows: spectral region 10001.03cm-1-3999.6400cm-1, point
Resolution is 4cm-1, scanning times 64 times, it is averaged the original spectrum as Radix Glycyrrhizae sample；Environmental condition be 22 DEG C of temperature ±
0.5 DEG C, relative humidity 40% ± 2%.
3. the Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method according to claim 1 based on kernel optimization, special
Sign is, in step 5, kernel function using radial basis function as core principle component analysis, and model are as follows:
K(xi,xj)=exp (- | xi-xj|2/2σ1 2)
Wherein, xi,xjIndicate the spectroscopic data of i-th, j sample in sample set, σ1Indicate the bandwidth of Gaussian kernel.
4. the Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method according to claim 1 based on kernel optimization, special
Sign is, in step 5, kernel function using polynomial function as core principle component analysis, and model are as follows:
K(xi,xj)=(xi Txj)d
Wherein, xi,xjIndicate the spectroscopic data of i-th, j sample in sample set, the number of d representative polynomial.
5. the Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method according to claim 1 based on kernel optimization, special
Sign is, in step 5, kernel function using broad sense T student function as core principle component analysis, and model are as follows:
K(xi,xj(1+ (the x of)=1/i Txj)α)
Wherein, xi,xjIndicate the spectroscopic data of i-th, j sample in sample set, the number of α representative polynomial.
6. the Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method according to claim 1 based on kernel optimization, special
Sign is, in step 5, kernel function using radial basis function as Kernel partial least squares regression, and model are as follows:
K(xi,xj)=exp (- | xi-xj|2/2σ2 2)
Wherein, xi,xjIndicate i-th, j sample data in sample set, σ2Indicate the bandwidth of Gaussian kernel.
7. the Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method according to claim 1 based on kernel optimization, special
Sign is, predicted root mean square error PRMSE, relative error PRSE described in step 6 and coefficient R index specific formula for calculation
Are as follows:
Wherein l2Indicate test sample quantity, piIndicate the reference value of test sample, siIndicate that core principle component analysis-core is partially minimum
Two multiply the regression forecasting of model as a result,Indicate the mean value of all test sample reference values,Indicate core principle component analysis-core partially most
Small two multiply the regression forecasting mean value of model.
8. special based on the Radix Glycyrrhizae quality evaluating method of Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method described in claim 1
Sign is, obtains the near infrared spectrum data of Radix Glycyrrhizae to be detected, and near infrared spectrum data is inputted trained Radix Glycyrrhizae near-infrared
Spectrum analysis model exports the ammonium glycyrrhetate content of Radix Glycyrrhizae to be detected.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910546901.3A CN110296955A (en) | 2019-06-24 | 2019-06-24 | Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method and Radix Glycyrrhizae quality evaluating method based on kernel optimization |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910546901.3A CN110296955A (en) | 2019-06-24 | 2019-06-24 | Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method and Radix Glycyrrhizae quality evaluating method based on kernel optimization |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110296955A true CN110296955A (en) | 2019-10-01 |
Family
ID=68028741
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910546901.3A Pending CN110296955A (en) | 2019-06-24 | 2019-06-24 | Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method and Radix Glycyrrhizae quality evaluating method based on kernel optimization |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110296955A (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107064054A (en) * | 2017-02-28 | 2017-08-18 | 浙江大学 | A kind of near-infrared spectral analytical method based on CC PLS RBFNN Optimized models |
| CN108562557A (en) * | 2018-06-29 | 2018-09-21 | 无锡济民可信山禾药业股份有限公司 | A kind of near infrared spectrum detection method of licorice medicinal materials |
-
2019
- 2019-06-24 CN CN201910546901.3A patent/CN110296955A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107064054A (en) * | 2017-02-28 | 2017-08-18 | 浙江大学 | A kind of near-infrared spectral analytical method based on CC PLS RBFNN Optimized models |
| CN108562557A (en) * | 2018-06-29 | 2018-09-21 | 无锡济民可信山禾药业股份有限公司 | A kind of near infrared spectrum detection method of licorice medicinal materials |
Non-Patent Citations (3)
| Title |
|---|
| KYUNGPIL KIM等: "A novel multivariate regression approach based on kernel partial least squares with orthogonal signal correction", 《CHEMOMETRICS AND INTELLIGENT LABORATORY SYSTEMS》 * |
| 谢天华: "基于核函数的非线性分析探讨", 《中国优秀硕士学位论文全文数据库 基础科学辑》 * |
| 郭凤娟: "应用红外光谱和化学计量学进行疾病诊断及甘草指标成分含量测定的研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108133313B (en) | Artificial intelligent sensory evaluation food flavor system and construction method thereof | |
| CN103364362B (en) | A kind of THz-TDS that utilizes is in conjunction with the method for Chemical Measurement qualification Chinese herbal medicine | |
| Jiang et al. | Comparison of algorithms for wavelength variables selection from near-infrared (NIR) spectra for quantitative monitoring of yeast (Saccharomyces cerevisiae) cultivations | |
| CN107677647A (en) | Chinese medicine place of production discrimination method based on principal component analysis and BP neural network | |
| Yang et al. | Integration of SIMCA and near-infrared spectroscopy for rapid and precise identification of herbal medicines | |
| CN109145873B (en) | Spectral Gaussian peak feature extraction algorithm based on genetic algorithm | |
| CN106841083A (en) | Sesame oil quality detecting method based on near-infrared spectrum technique | |
| CN104020127A (en) | Method for rapidly measuring inorganic element in tobacco by near infrared spectrum | |
| Yuan et al. | Selecting key wavelengths of hyperspectral imagine for nondestructive classification of moldy peanuts using ensemble classifier | |
| CN106529008B (en) | A kind of double integrated offset minimum binary modeling methods based on Monte Carlo and LASSO | |
| Shao et al. | Fast determination of two atractylenolides in Rhizoma Atractylodis Macrocephalae by Fourier transform near-infrared spectroscopy with partial least squares | |
| CN111965140B (en) | Wavelength point recombination method based on characteristic peak | |
| Pan et al. | Rapid On-site identification of geographical origin and storage age of tangerine peel by Near-infrared spectroscopy | |
| CN101231274A (en) | Method for rapid measuring allantoin content in yam using near infrared spectrum | |
| CN112595692A (en) | Establishment method of fruit total sugar content prediction model and fruit total sugar content prediction method | |
| Fu et al. | Rapid recognition of geoherbalism and authenticity of a Chinese herb by data fusion of near-infrared spectroscopy (NIR) and mid-infrared (MIR) spectroscopy combined with chemometrics | |
| Wang et al. | NIR based wireless sensing approach for fruit monitoring | |
| CN106770005B (en) | A kind of division methods of calibration set for near-infrared spectrum analysis and verification collection | |
| CN106226267B (en) | A kind of near-infrared assay method of dry chili color value | |
| CN114577967B (en) | Chromatographic analysis method for traditional Chinese medicine compound sample based on artificial neural network and difference spectrum | |
| Feng et al. | Rapid quality assessment of Succus Bambusae oral liquid based on near infrared spectroscopy and chemometrics | |
| CN109507123A (en) | A kind of discrimination method of Radix Angelicae Sinensis based on UV-vis DRS spectrum and Chemical Pattern Recognition and its similar product | |
| CN110296955A (en) | Radix Glycyrrhizae NIR Spectroscopy Analysis Model construction method and Radix Glycyrrhizae quality evaluating method based on kernel optimization | |
| Yang et al. | A robust identification model for herbal medicine using near infrared spectroscopy and artificial neural network | |
| He et al. | Non-Destructive Classification of Chrysanthemum Tea Using Near-Infrared Spectroscopy (NIRS) and Fuzzy Improved Pseudoinverse Linear Discriminant Analysis (FIPLDA) |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191001 |
|
| RJ01 | Rejection of invention patent application after publication |