CN110082308A - A kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model - Google Patents
A kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model Download PDFInfo
- Publication number
- CN110082308A CN110082308A CN201910370890.8A CN201910370890A CN110082308A CN 110082308 A CN110082308 A CN 110082308A CN 201910370890 A CN201910370890 A CN 201910370890A CN 110082308 A CN110082308 A CN 110082308A
- Authority
- CN
- China
- Prior art keywords
- gentianae macrophyllae
- sample
- model
- certified products
- discrimination model
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 67
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 36
- 238000005457 optimization Methods 0.000 claims abstract description 18
- 238000002360 preparation method Methods 0.000 claims abstract description 8
- 241000967672 Gentiana crassicaulis Species 0.000 claims description 19
- 238000009499 grossing Methods 0.000 claims description 19
- 241000501719 Gentiana straminea Species 0.000 claims description 18
- 241001071804 Gentianaceae Species 0.000 claims description 18
- 230000003595 spectral effect Effects 0.000 claims description 15
- 238000003672 processing method Methods 0.000 claims description 9
- 230000008676 import Effects 0.000 claims description 4
- 238000007873 sieving Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 description 6
- 239000003814 drug Substances 0.000 description 6
- 230000000694 effects Effects 0.000 description 6
- 241000196324 Embryophyta Species 0.000 description 3
- 241001071795 Gentiana Species 0.000 description 3
- 241000290619 Gentiana dahurica Species 0.000 description 2
- 241000501743 Gentiana macrophylla Species 0.000 description 2
- 241000147285 Gentiana officinalis Species 0.000 description 2
- 229940079593 drug Drugs 0.000 description 2
- 208000006820 Arthralgia Diseases 0.000 description 1
- 206010008190 Cerebrovascular accident Diseases 0.000 description 1
- 241001573881 Corolla Species 0.000 description 1
- 241001102166 Cruciata Species 0.000 description 1
- 241001269238 Data Species 0.000 description 1
- 206010023126 Jaundice Diseases 0.000 description 1
- 208000002193 Pain Diseases 0.000 description 1
- 208000025747 Rheumatic disease Diseases 0.000 description 1
- 208000006011 Stroke Diseases 0.000 description 1
- 238000002835 absorbance Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 201000010099 disease Diseases 0.000 description 1
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000011521 glass Substances 0.000 description 1
- 238000009434 installation Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 231100000862 numbness Toxicity 0.000 description 1
- 201000008482 osteoarthritis Diseases 0.000 description 1
- 230000001151 other effect Effects 0.000 description 1
- 244000052769 pathogen Species 0.000 description 1
- 230000001717 pathogenic effect Effects 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 230000000552 rheumatic effect Effects 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 239000000126 substance Substances 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)
- Investigating, Analyzing Materials By Fluorescence Or Luminescence (AREA)
Abstract
The gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model that the invention discloses a kind of, the recognition methods includes the following contents: the preparation of gentianae macrophyllae sample and the near infrared spectrum data for obtaining sample；The near infrared spectrum data of sample is imported in TQ Analysis software and establishes model；The near-infrared discrimination model after being optimized is optimized to the model；Gentianae macrophyllae classification is identified and judgeed according to the near-infrared discrimination model after optimization.By establishing two kinds of near-infrared discrimination models, certified products gentianae macrophyllae and non-certified products gentianae macrophyllae can not only be differentiated, accurately the specific type of gentianae macrophyllae can also be differentiated, and its prediction rate and discrimination reach 100%, can more rapidly and more accurately differentiate to gentianae macrophyllae type compared with clustering method.
Description
Technical field
The present invention relates to the control of Chinese medicine quality and identification technology fields, more particularly to a kind of near infrared spectrum that is based on to differentiate
The gentianae macrophyllae classification recognition methods of model.
Background technique
Traditional Chinese medicine quality control research is always very popular one of the research field of Chemistry for Chinese Traditional Medicine；And gentianae macrophyllae is traditional Chinese medicine
Material, 2015 editions " Chinese Pharmacopoeia " regulation gentianae macrophyllae medicine materical crude slice are gentianae macrophyllae (Gentiana macrophylla Pall.), gentiana straminea
(G.straminea Maxim.), gentiana crassicaulis Duthie (G.crassicaulis Duthie ex Burk.) or radix gentiane dahuvicae
The dry root of (G.dahurica Fisch. also known as Da Wuli gentianae macrophyllae).It is Gentianaceae (Gentianaceae) Gentiana
(Gentiana) gentianae macrophyllae group (Sect.Cruciata) perennial herb.There are wind-damp dispelling, clearing away damp-heat, stopping numbness pain and other effects, for controlling
The diseases such as rheumatic arthralgia, apoplexy, jaundice with damp-heat pathogen are treated, including compatibility for 2015 editions " Chinese Pharmacopoeia " has the compound of gentianae macrophyllae there are 14 kinds, money
Source dosage is larger.
Yellow pipe gentianae macrophyllae (G.officinalis H.Smith) is Gentianaceae Gentiana gentianae macrophyllae group perennial herb, with thick stem
Gentianae macrophyllae provenance relationship is closer, plant height 15-35cm, corolla yellow green, is born in the ground such as mesophorbium, coryphile, shrubbery and river shoal, height above sea level 2300-
4200m.There is certain medication history on Gansu, Qinghai and other places, although research report shows that yellow pipe gentianae macrophyllae has treatment osteoarthritis
Effect, but do not recorded into 2015 editions " Chinese Pharmacopoeias ", it is considered to be non-certified products gentianae macrophyllae；And due to itself and gentiana crassicaulis Duthie kind
The closer reason of source relationship, therefore be used to adulterate by some pharmacists and be added in certified products gentianae macrophyllae, the use of certified products gentianae macrophyllae is served as,
However there are also to be determined for the clinical safety of yellow pipe gentianae macrophyllae.
Therefore, how to carry out identification judgement to the classification of gentianae macrophyllae is problem to be solved at this stage, it is existing to gentianae macrophyllae and
The identification multi-pass of its adulterant crosses microscopical characters, character identifies, biochemical identification, these methods time-consuming, effort can not quickly be reflected
The problems such as other.
Summary of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of Qin based near infrared spectrum discrimination model
Macrophylla classification recognition methods solves existing to defect existing for gentianae macrophyllae recognition methods.
The purpose of the present invention is achieved through the following technical solutions: a kind of Qin based near infrared spectrum discrimination model
Macrophylla classification recognition methods, the recognition methods includes the following contents:
The preparation of gentianae macrophyllae sample and the near infrared spectrum data for obtaining sample；
The near infrared spectrum data of sample is imported in TQ Analysis software and establishes model；
The near-infrared discrimination model after being optimized is optimized to the model；
Gentianae macrophyllae classification is identified and judgeed according to the near-infrared discrimination model after optimization.
Further, the gentianae macrophyllae sample preparation and obtain sample near infrared spectrum data the following steps are included:
It by sample clean, dries, takes medicinal part root grinding and sieving；
In 10000~4000cm-1The full spectral scan of near-infrared is carried out in range obtains the atlas of near infrared spectra of sample.
Further, establishing model in the near infrared spectrum data importing TQ Analysis software by sample includes
Will the near-infrared data of certified products gentianae macrophyllae sample and non-certified products gentianae macrophyllae sample import TQ Analysis software in establish it is non-just/certified products
Gentianae macrophyllae identification model, and the near-infrared data of a variety of gentianae macrophyllae type samples are imported in TQ Analysis software and establish gentianae macrophyllae
Category identification model.
Further, a variety of gentianae macrophyllae type samples include gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, gentianae macrophyllae and Huang Guanqin
Macrophylla.
Further, the certified products gentianae macrophyllae sample includes the gentiana straminea, the radix gentiane dahuvicae, the gentiana crassicaulis Duthie and described
One or more of gentianae macrophyllae；The non-certified products gentianae macrophyllae includes yellow pipe gentianae macrophyllae.
It is further, described that optimize the near-infrared discrimination model after being optimized to the model include to described non-
Just/certified products gentianae macrophyllae identification model optimize the near-infrared after being optimized it is non-just/certified products gentianae macrophyllae discrimination model, and to described
Gentianae macrophyllae category identification model optimizes the near-infrared gentianae macrophyllae type discrimination model after being optimized.
Further, it is described to it is described it is non-just/that certified products gentianae macrophyllae identification model optimizes the near-infrared after being optimized is non-
Just/certified products gentianae macrophyllae discrimination model the following steps are included:
It will be divided into according to a certain percentage training set with non-certified products gentianae macrophyllae sample in the certified products gentianae macrophyllae sample and verify and collect
To it is described it is non-just/certified products gentianae macrophyllae identification model is trained and verifies；
Any two in model optimization condition are set as invariant, remain it is next be set as variable, to the optimization item of variable
Part is verified, and obtains optimal variable optimal conditions, and optimal variable optimal conditions are set as verify next time two
One in invariant；
Two are repeated the above steps, until obtaining optimal modeling method, spectral manipulation method and spectrogram smoothing processing side
Method, and to it is described it is non-just/certified products gentianae macrophyllae identification model optimize to obtain near-infrared it is non-just/certified products gentianae macrophyllae discrimination model.
Further, described that the near-infrared gentianae macrophyllae type after being optimized is optimized to the gentianae macrophyllae category identification model
Discrimination model the following steps are included:
The gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, gentianae macrophyllae and yellow pipe gentianae macrophyllae sample are divided into training according to a certain percentage
Collection and verifying collection are trained and verify to the gentianae macrophyllae category identification model；
By any two in model optimization condition be set as invariant remain it is next be set as variable, to the optimal conditions of variable
It is verified, obtains optimal variable optimal conditions, and optimal variable optimal conditions are set as verify next time two not
One in variable；
Two are repeated the above steps, until obtaining optimal modeling method, spectral manipulation method and spectrogram smoothing processing side
Method, and the gentianae macrophyllae category identification model is optimized to obtain near-infrared gentianae macrophyllae classification discrimination model.
Further, it includes by certified products gentianae macrophyllae sample and non-that sample is divided into training set and verifying collection according to a certain percentage
2/3rds of certified products gentianae macrophyllae sample are divided into training set, and one third is divided into verifying collection；And by gentiana straminea, radix gentiane dahuvicae,
Gentiana crassicaulis Duthie, gentianae macrophyllae and yellow pipe gentianae macrophyllae sample 2/3rds are divided into training set, and one third is divided into verifying collection.
Further, the model optimization condition includes modeling method, spectral manipulation method and spectrogram smoothing processing side
Method.
The beneficial effects of the present invention are: a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model, passes through
Two kinds of near-infrared discrimination models are established, certified products gentianae macrophyllae and non-certified products gentianae macrophyllae can not only be differentiated, moreover it is possible to accurately to gentianae macrophyllae
Specific type differentiated that and its prediction rate and discrimination reach 100%, can more rapidly and more compared with clustering method
Accurately gentianae macrophyllae type is differentiated.
Detailed description of the invention
Fig. 1 is the flow chart of method；
Fig. 2 be near-infrared it is non-just/certified products gentianae macrophyllae discrimination model recognition result figure；
Fig. 3 is near-infrared gentianae macrophyllae type discrimination model recognition result figure；
Fig. 4 is clustering recognition result figure.
Specific embodiment
In order to make the object, technical scheme and advantages of the embodiment of the invention clearer, below in conjunction with the embodiment of the present invention
In attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is
A part of the embodiment of the present invention, instead of all the embodiments.The present invention being usually described and illustrated herein in the accompanying drawings is implemented
The component of example can be arranged and be designed with a variety of different configurations.
Therefore, the detailed description of the embodiment of the present invention provided in the accompanying drawings is not intended to limit below claimed
The scope of the present invention, but be merely representative of selected embodiment of the invention.Based on the embodiments of the present invention, this field is common
Technical staff's every other embodiment obtained without creative efforts belongs to the model that the present invention protects
It encloses.
It should also be noted that similar label and letter indicate similar terms in following attached drawing, therefore, once a certain Xiang Yi
It is defined in a attached drawing, does not then need that it is further defined and explained in subsequent attached drawing.
In the description of the present invention, it should be noted that the orientation of the instructions such as term " on ", "inner", "outside" or position are closed
System for be based on the orientation or positional relationship shown in the drawings or the invention product using when the orientation usually put or position close
System, is merely for convenience of description of the present invention and simplification of the description, rather than the device or element of indication or suggestion meaning must have
Specific orientation is constructed and operated in a specific orientation, therefore is not considered as limiting the invention.
In the description of the present invention, it is also necessary to which explanation is unless specifically defined or limited otherwise, term " setting ",
" installation ", " connection " shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integrally connect
It connects；It can be mechanical connection, be also possible to be electrically connected；It can be directly connected, can also indirectly connected through an intermediary, it can
To be the connection inside two elements.For the ordinary skill in the art, above-mentioned term can be understood with concrete condition
Concrete meaning in the present invention.
Technical solution of the present invention is described in further detail with reference to the accompanying drawing, but protection scope of the present invention is not limited to
It is as described below.
As shown in Figure 1, a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model, the recognition methods packet
Include the following contents:
The near infrared spectrum data of S1, the preparation of gentianae macrophyllae sample and acquisition sample；
S2, the near infrared spectrum data of sample is imported in TQ Analysis software and establishes model；
S3, the near-infrared discrimination model after being optimized is optimized to the model；
S4, gentianae macrophyllae classification is identified and judgeed according to the near-infrared discrimination model after optimization.
Further, the gentianae macrophyllae sample preparation and obtain sample near infrared spectrum data the following steps are included:
S11, by sample clean, dry, take medicinal part root to smash it through 100 meshes；Take 0.135~0.138g (accidentally
Poor 0.0005) sample is placed in glass sample cup, and dress sample thickness is about 0.1cm；
S12, in 10000~4000cm-1The full spectral scan of near-infrared is carried out in range obtains the atlas of near infrared spectra of sample；
Scanning resolution is 8cm-1, scanning times are 64 times.
Further, the preparation of sample and the acquisition of near infrared spectrum diagram data acquisition are all made of existing routine techniques.
Further, establishing model in the near infrared spectrum data importing TQ Analysis software by sample includes
Will the near-infrared data of certified products gentianae macrophyllae sample and non-certified products gentianae macrophyllae sample import TQ Analysis software in establish it is non-just/certified products
Gentianae macrophyllae identification model, and the near-infrared data of a variety of gentianae macrophyllae type samples are imported in TQ Analysis software and establish gentianae macrophyllae
Category identification model.
Further, a variety of gentianae macrophyllae type samples include gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, gentianae macrophyllae and Huang Guanqin
Macrophylla.
Further, the certified products gentianae macrophyllae sample includes the gentiana straminea, the radix gentiane dahuvicae, the gentiana crassicaulis Duthie and described
One or more of gentianae macrophyllae；The non-certified products gentianae macrophyllae includes yellow pipe gentianae macrophyllae.
It is further, described that optimize the near-infrared discrimination model after being optimized to the model include to described non-
Just/certified products gentianae macrophyllae identification model optimize the near-infrared after being optimized it is non-just/certified products gentianae macrophyllae discrimination model, and to described
Gentianae macrophyllae category identification model optimizes the near-infrared gentianae macrophyllae type discrimination model after being optimized.
Wherein, near-infrared it is non-just/certified products gentianae macrophyllae discrimination model is for knowledge to certified products gentianae macrophyllae in sample and non-certified products gentianae macrophyllae
Do not judge；Near-infrared gentianae macrophyllae type discrimination model is for carrying out identification judgement to gentianae macrophyllae type specific in sample.
Further, it is described to it is described it is non-just/that certified products gentianae macrophyllae identification model optimizes the near-infrared after being optimized is non-
Just/certified products gentianae macrophyllae discrimination model the following steps are included:
It will be divided into according to a certain percentage training set with non-gentianae macrophyllae sample in the certified products gentianae macrophyllae sample and verify and collect to institute
State it is non-just/certified products gentianae macrophyllae identification model is trained and verifies；
Any two in model optimization condition are set as invariant, remain it is next be set as variable, to the optimization item of variable
Part is verified, and obtains optimal variable optimal conditions, and optimal variable optimal conditions are set as verify next time two
One in invariant；
Two are repeated the above steps, until obtaining optimal modeling method, spectral manipulation method and spectrogram smoothing processing side
Method, and to it is described it is non-just/certified products gentianae macrophyllae identification model optimize to obtain near-infrared it is non-just/certified products gentianae macrophyllae discrimination model.
Further, described that the near-infrared gentianae macrophyllae type after being optimized is optimized to the gentianae macrophyllae category identification model
Discrimination model the following steps are included:
The gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, gentianae macrophyllae and yellow pipe gentianae macrophyllae sample are divided into training according to a certain percentage
Collection and verifying collection are trained and verify to the gentianae macrophyllae category identification model；
Any two in model optimization condition are set as invariant, remain it is next be set as variable, to the optimization item of variable
Part is verified, and obtains optimal variable optimal conditions, and optimal variable optimal conditions are set as verify next time two
One in invariant；
Two are repeated the above steps, until obtaining optimal modeling method, spectral manipulation method and spectrogram smoothing processing side
Method, and the gentianae macrophyllae category identification model is optimized to obtain near-infrared gentianae macrophyllae classification discrimination model.
Further, it includes by certified products gentianae macrophyllae sample and non-that sample is divided into training set and verifying collection according to a certain percentage
2/3rds of certified products gentianae macrophyllae sample are divided into training set, and one third is divided into verifying collection；Its certified products gentianae macrophyllae and the non-certified products Qin
The training set and verifying collection quantity such as following table of Macrophylla sample；
Table 1: the training set of certified products and non-certified products sample and verifying collection quantity table
It further, further include by 2/3rds of gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, gentianae macrophyllae and yellow pipe gentianae macrophyllae sample
It is divided into training set, one third is divided into verifying collection；The training set and verifying collection quantity of its 5 kinds of gentianae macrophyllae type samples are as follows
Table；
Table 2: the training set and verifying collection quantity table of specific gentianae macrophyllae type sample
Further, the model optimization condition includes modeling method, spectral manipulation method and spectrogram smoothing processing side
Method.
Further, modeling method includes discriminant analysis method and distance match method,
Spectrogram is excellent to two kinds of modeling methods progress under conditions of former spectrogram (and spectrogram smoothing processing method be no smoothing processing)
Chemical examination card, as a result as shown in the table, the discrimination and prediction rate of discriminant analysis method known to following table are high
In distance match method, therefore the optimum choice discriminant analysis method of modeling method.
Table 3: modeling method contrast table
Further, spectral manipulation method includes former spectrogram, first derivative spectrogram, second dervative spectrogram, in modeling method
For discriminant analysis and spectrogram is without optimizing verifying to spectral manipulation method under conditions of smooth；By following table
It is found that model discrimination and prediction rate have reached 100%, and effect is higher than former spectrogram and second order when first derivative spectrogram models
The modeling of derivative spectrogram, therefore model optimization time spectrum processing method uses first derivative spectrogram.
Table 4: spectrogram processing method contrast table
Further, smoothing processing method includes no smoothing processing, SG smoothing processing and Norris smoothing processing；It is modeling
Method is discriminant analysis and spectrogram is the priority condition of spectral manipulation method treated first derivative spectrogram
Under, verifying is optimized to smoothing processing method；As a result such as following table it is found that the model established with former spectrogram (no smoothing processing)
Discrimination and prediction rate have reached 100%, and therefore, model optimization makes all spectrograms without smoothing processing.
Table 5: smoothing processing method contrast table
As shown in Figures 2 and 3, G.dahurica: radix gentiane dahuvicae, G.crassicaulis: gentiana crassicaulis Duthie,
G.macrophylla: gentianae macrophyllae, G.straminea: gentiana straminea, G.officinalis: yellow pipe gentianae macrophyllae；QJ indicates certified products gentianae macrophyllae,
FQJ indicates non-certified products gentianae macrophyllae；
Near-infrared is non-just/and certified products gentianae macrophyllae discrimination model to certified products gentianae macrophyllae and divides certified products gentianae macrophyllae to differentiate that effect is good, sample between classification
Product are without intersection；Near-infrared gentianae macrophyllae type discrimination model differentiates that effect is preferable to 5 kinds of gentianae macrophyllae types, only gentianae macrophyllae and gentiana crassicaulis Duthie sample
Product have a small amount of intersection, remaining gentianae macrophyllae type good separating effect；Prediction rate and discrimination in conjunction with two models are 100%, are said
Bright this method can not only determine certified products gentianae macrophyllae and non-certified products gentianae macrophyllae, moreover it is possible to accurate to carry out the specific kind of differentiation of gentianae macrophyllae.
Principal component analysis is carried out to the sample of modeling, first three principal component as shown in the table reaches the contribution rate of accumulative total of model
95.717%, the most information of sample is represented, illustrates that the model has good confidence level, wherein first principal component
Contribution rate is 72.566%, and Second principal component, contribution rate is 19.060%, and third principal component contributor rate is 4.091%.
Table 6: principal component contributor rate contrast table
As shown in figure 4, M indicates that gentiana straminea maxim, XQ indicate that radix gentiane dahuvicae, Q indicate that gentianae macrophyllae, C indicate that gentiana crassicaulis Duthie and H indicate yellow
Pipe gentianae macrophyllae；5 kinds of gentianae macrophyllae group plant absorbance datas are imported into PC-ORD software, missing values are handled with random forest, range determination
For correlation, contact method is Ward ' s Methood between group, obtains sample clustering result.It is in information reserved
When 75%, sample is divided into two classes, and one kind is yellow pipe gentianae macrophyllae, i.e., non-certified products gentianae macrophyllae, one kind is gentiana straminea, gentianae macrophyllae, radix gentiane dahuvicae, thick stem
Gentianae macrophyllae, i.e. certified products gentianae macrophyllae, accuracy is 100% when clustering differentiates to certified products gentianae macrophyllae and non-certified products gentianae macrophyllae, but clusters and divide
Analysis cannot distinguish 5 kinds of plants, differentiate effect not as good as the recognition methods of the built discrimination model of the present invention.
The above description is only an embodiment of the present invention, is not intended to limit the scope of the invention, all to utilize this hair
Equivalent structure or equivalent flow shift made by bright specification and accompanying drawing content is applied directly or indirectly in other relevant skills
Art field, is included within the scope of the present invention.
Claims (10)
1. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model, it is characterised in that: the recognition methods packet
Include the following contents:
The preparation of gentianae macrophyllae sample and the near infrared spectrum data for obtaining gentianae macrophyllae sample；
The near infrared spectrum data of sample is imported in TQ Analysis software and establishes model；
The near-infrared discrimination model after being optimized is optimized to the model；
Gentianae macrophyllae classification is identified and judgeed according to the near-infrared discrimination model after optimization.
2. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 1, feature
Be: the preparation of the gentianae macrophyllae sample and obtain gentianae macrophyllae sample near infrared spectrum data the following steps are included:
It by sample clean, dries, takes medicinal part root grinding and sieving；
In 10000~4000cm-1The full spectral scan of near-infrared is carried out in range obtains the atlas of near infrared spectra of sample.
3. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 1, feature
Be: it includes by certified products gentianae macrophyllae sample that the near infrared spectrum data by sample, which imports and establishes model in TQ Analysis software,
The near-infrared data of product and non-certified products gentianae macrophyllae sample import TQ Analysis software in establish it is non-just/certified products gentianae macrophyllae identification model,
And the near-infrared data of a variety of gentianae macrophyllae type samples are imported in TQ Analysis software and establish gentianae macrophyllae category identification model.
4. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 3, feature
Be: a variety of gentianae macrophyllae type samples include gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, gentianae macrophyllae and yellow pipe gentianae macrophyllae.
5. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 4, feature
Be: the certified products gentianae macrophyllae sample includes one of the gentiana straminea, the radix gentiane dahuvicae, the gentiana crassicaulis Duthie and described gentianae macrophyllae
Or it is a variety of；The non-certified products gentianae macrophyllae includes yellow pipe gentianae macrophyllae.
6. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 4, feature
Be: it is described the model is optimized the near-infrared discrimination model after being optimized include to it is described it is non-just/certified products gentianae macrophyllae
Identification model optimize the near-infrared after being optimized it is non-just/certified products gentianae macrophyllae discrimination model, and to the gentianae macrophyllae type know
Other model optimizes the near-infrared gentianae macrophyllae type discrimination model after being optimized.
7. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 6, feature
Be: it is described to it is described it is non-just/certified products gentianae macrophyllae identification model optimize the near-infrared after being optimized it is non-just/certified products gentianae macrophyllae sentences
Other model the following steps are included:
It will be divided into according to a certain percentage training set with non-gentianae macrophyllae sample in the certified products gentianae macrophyllae sample and verify and collect to described non-
Just/certified products gentianae macrophyllae identification model is trained and verifies；
Any two in model optimization condition are set as invariant, remain it is next be set as variable, to the optimal conditions of variable into
Row verifying, obtains optimal variable optimal conditions, and by optimal variable optimal conditions be set as verify next time two it is constant
One in amount；
Repeat the above steps two, until obtaining optimal modeling method, spectral manipulation method and spectrogram smoothing processing method, and
To it is described it is non-just/certified products gentianae macrophyllae identification model optimize to obtain near-infrared it is non-just/certified products gentianae macrophyllae discrimination model.
8. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 6, feature
It is: described to optimize the near-infrared gentianae macrophyllae type discrimination model after being optimized to the gentianae macrophyllae category identification model and include
Following steps:
By the gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, gentianae macrophyllae and yellow pipe gentianae macrophyllae sample be divided into according to a certain percentage training set and
Verifying collection is trained and verifies to the gentianae macrophyllae category identification model；
Any two in model optimization condition are set as invariant, remain it is next be set as variable, to the optimal conditions of variable into
Row verifying, obtains optimal variable optimal conditions, and by optimal variable optimal conditions be set as verify next time two it is constant
One in amount；
Repeat the above steps two, until obtaining optimal modeling method, spectral manipulation method and spectrogram smoothing processing method, and
The gentianae macrophyllae category identification model is optimized to obtain near-infrared gentianae macrophyllae classification discrimination model.
9. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 7 or 8, special
Sign is: it includes by certified products gentianae macrophyllae sample and non-certified products gentianae macrophyllae sample that sample is divided into training set and verifying collection according to a certain percentage
2/3rds of product are divided into training set, and one third is divided into verifying collection；And by gentiana straminea, radix gentiane dahuvicae, gentiana crassicaulis Duthie, the Qin
Macrophylla is divided into training set with 2/3rds of yellow pipe gentianae macrophyllae sample, and one third is divided into verifying collection.
10. a kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model according to claim 7 or 8,
Be characterized in that: the model optimization condition includes modeling method, spectral manipulation method and spectrogram smoothing processing method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910370890.8A CN110082308B (en) | 2019-05-06 | 2019-05-06 | Near infrared spectrum discrimination model-based gentiana macrophylla class identification method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910370890.8A CN110082308B (en) | 2019-05-06 | 2019-05-06 | Near infrared spectrum discrimination model-based gentiana macrophylla class identification method |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110082308A true CN110082308A (en) | 2019-08-02 |
| CN110082308B CN110082308B (en) | 2021-12-03 |
Family
ID=67418725
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910370890.8A Active CN110082308B (en) | 2019-05-06 | 2019-05-06 | Near infrared spectrum discrimination model-based gentiana macrophylla class identification method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110082308B (en) |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100523793C (en) * | 2006-10-12 | 2009-08-05 | 中国林业科学研究院木材工业研究所 | Method for identifying red sandalwood by near-infrared ray |
| CN106092950A (en) * | 2016-06-08 | 2016-11-09 | 常熟雷允上制药有限公司 | A kind of method differentiating dendrobium candidum medicinal material based near infrared spectrum |
| CN108509997A (en) * | 2018-04-03 | 2018-09-07 | 深圳市药品检验研究院（深圳市医疗器械检测中心） | A method of Chemical Pattern Recognition is carried out to the true and false that Chinese medicine Chinese honey locust is pierced based on near-infrared spectrum technique |
-
2019
- 2019-05-06 CN CN201910370890.8A patent/CN110082308B/en active Active
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN100523793C (en) * | 2006-10-12 | 2009-08-05 | 中国林业科学研究院木材工业研究所 | Method for identifying red sandalwood by near-infrared ray |
| CN106092950A (en) * | 2016-06-08 | 2016-11-09 | 常熟雷允上制药有限公司 | A kind of method differentiating dendrobium candidum medicinal material based near infrared spectrum |
| CN108509997A (en) * | 2018-04-03 | 2018-09-07 | 深圳市药品检验研究院（深圳市医疗器械检测中心） | A method of Chemical Pattern Recognition is carried out to the true and false that Chinese medicine Chinese honey locust is pierced based on near-infrared spectrum technique |
Non-Patent Citations (4)
| Title |
|---|
| 付海燕 等: "近红外光谱技术结合化学模式识别用于藏药麻花秦艽真伪品鉴别", 《中国化学会第28届学术年会第14分会场摘要集》 * |
| 李四海 等: "基于FTIR技术和稀疏线性判别分析的秦艽种类鉴别", 《光谱学与光谱分析》 * |
| 牛晓颖: "基于傅里叶变换近红外光谱的绍兴黄酒风味成分定量分析及其酒龄鉴别的研究", 《中国博士学位论文全文数据库工程科技Ⅰ辑》 * |
| 罗阳: "同时快速鉴别中国药典收载的三种麻黄药材的近红外光谱法研究", 《中国优秀硕士学位论文全文数据库 医药卫生科技辑》 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110082308B (en) | 2021-12-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Hernández-Hierro et al. | Feasibility study on the use of near-infrared hyperspectral imaging for the screening of anthocyanins in intact grapes during ripening | |
| Wu et al. | Rapid determination and origin identification of total polysaccharides contents in Schisandra chinensis by near-infrared spectroscopy | |
| CN104237060A (en) | Multi-index quick detection method of honeysuckle | |
| CN203203920U (en) | Online detection device of extraction process of traditional Chinese medicine | |
| CN103033486B (en) | Method for near infrared spectrum monitoring of quality of pericarpium citri reticulatae and citrus chachiensis hortorum medicinal materials | |
| CN102636452B (en) | NIR (Near Infrared Spectrum) undamaged identification authenticity method for wild ginseng | |
| CN102028859B (en) | Detection method for Chinese medicinal preparation for treating asthma | |
| CN105092725B (en) | The HPLC detection method of Herba Gentianae Algidae | |
| CN104048941A (en) | Method for quickly measuring content of multiple index components in radix ophiopogonis through near infrared spectroscopy | |
| CN104730030A (en) | Method for true and false identification and place of origin judgment of codonopsis pilosula based on near infrared analysis technology | |
| CN101766655A (en) | Method for analyzing quality of Chinese medicinal materials, decoction pieces and Chinese patent drugs by utilizing micrographic atlases | |
| CN109856084A (en) | A kind of stomach pill of aucklandia and amomum fruit condensed pill preparation process quality monitoring method | |
| Zou et al. | Progress in quality control of herbal medicine with IR fingerprint spectra | |
| Ali et al. | 1H HR-MAS NMR-Based metabolomic fingerprinting to distinguish morphological similarities and metabolic profiles of Maytenus ilicifolia, a Brazilian medicinal plant | |
| CN101664495A (en) | On-line detection method of near infrared spectrum for production process of traditional Chinese medicine, pill of six ingredients with rehmannia | |
| CN110195126A (en) | SSR core primers group and its application based on bitter buckwheat full-length genome data mining | |
| CN109633012A (en) | A kind of discrimination method of Zhejiang Radix Ophiopogonis | |
| CN106018320A (en) | Carotenoid detection method based on near infrared spectroscopy analysis | |
| CN102048941A (en) | Quality control method of children-welfare tablets serving as Chinese medicinal preparation | |
| CN110082308A (en) | A kind of gentianae macrophyllae classification recognition methods based near infrared spectrum discrimination model | |
| Lin et al. | A rapid analysis method of safflower (Carthamus tinctorius L.) using combination of computer vision and near-infrared | |
| CN105784951B (en) | A kind of Liuwei Dihuang Wan condensed pill crude drug powder multiple index quick detecting method | |
| CN110346323B (en) | Method for detecting Huagaisan concentrated solution on line based on near infrared spectrum technology | |
| CN105241838B (en) | A kind of Seabuckthorm Seed Oil mixes the detection method of puppet | |
| CN110068547A (en) | A kind of method of discrimination of Huang pipe gentianae macrophyllae |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |