CN107607485A - A kind of method for differentiating the radix tetrastigme place of production - Google Patents
A kind of method for differentiating the radix tetrastigme place of production Download PDFInfo
- Publication number
- CN107607485A CN107607485A CN201710762908.XA CN201710762908A CN107607485A CN 107607485 A CN107607485 A CN 107607485A CN 201710762908 A CN201710762908 A CN 201710762908A CN 107607485 A CN107607485 A CN 107607485A
- Authority
- CN
- China
- Prior art keywords
- sample
- vector machine
- machine model
- place
- radix tetrastigme
- 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
Landscapes
- Investigating Or Analysing Biological Materials (AREA)
Abstract
The present invention relates to Chinese herbal medicine place of production discriminating field, more particularly to a kind of method for differentiating the radix tetrastigme place of production.A kind of method for differentiating the radix tetrastigme place of production, comprises the following steps：Obtain the near infrared spectrum data and high-efficient liquid phase color modal data of the radix tetrastigme sample of different sources；The sample of predetermined number is obtained, and sample is divided into by training set and forecast set by Kennard Stone sample partitionings；Least square method supporting vector machine model is established using training set；The near infrared spectrum data and high-efficient liquid phase color modal data of testing sample, and the input using near infrared spectrum data and high-efficient liquid phase color modal data as least square method supporting vector machine model are obtained, obtains the provenance of testing sample.The discrimination method degree of accuracy is high, highly reliable, and cost is low, can overcome the difficulty of parsing collection of illustrative plates, simple to operate.
Description
Technical field
The present invention relates to Chinese herbal medicine place of production discriminating field, more particularly to a kind of method for differentiating the radix tetrastigme place of production.
Background technology
Radix tetrastigme is the distinctive rare Chinese medicine in China, mainly contain flavones, phenols, polysaccharide, amino acid, terpene etc. into
Point.Brought down a fever with significant anti-inflammatory, the extensive medical value such as dispersing swelling and dissipating binds, anti-liver injury.Three leaves due to discovered in recent years
Bluish yellow ketone composition can significantly inhibit the effect of kinds of tumor cells propagation, and price of medicinal material persistently soars, and causes its wild resource
Excessively developed, it is endangered.Artificial cultivation difficulty is big, and its medicinal part underground root tuber growth is slow, it is necessary to which 3~5 years could reach
To the requirement of commodity medicinal material.Multiple studies have shown that radix tetrastigme medicinal material germplasm mixes, chemical component difference is big, and Zheng Junxian etc. is determined
The content of general flavone, as a result shows different sources medicinal material flavones content difference most in Zhejiang and 10 parts of Guangxi place of production radix tetrastigme sample
It is big reachable 7 times.Xu Wen etc. quantitative determines 10 kinds of flavones ingredient results in 30 batches of different sources radix tetrastigmes and shows that each constituents contain
Do not detected in amount most diverse, or even some batches.Medicinal material market Top-three Leaves green grass or young crops germplasm mixes at present, different sources source
Price of medicinal material most diverse.To ensure clinical efficacy, consumers' rights and interests are safeguarded, establish a kind of side for differentiating different sources radix tetrastigme
Method is significant.
The true and false of radix tetrastigme differentiates existing a variety of methods at present, such as：Quick discriminating radix tetrastigme and its a variety of puppets mix product
PCR-RFLP methods (ZL201510016355.4), a kind of method (ZL201310373809.4) for identifying medicinal plant radix tetrastigme,
But it there is no the effective method for differentiating and distinguishing the radix tetrastigme place of production.
The content of the invention
For this reason, it may be necessary to a kind of method for differentiating the radix tetrastigme place of production is provided, to solve effectively to differentiate and distinguish three leaves
The problem of blue or green place of production.
To achieve the above object, a kind of method for differentiating the radix tetrastigme place of production is inventor provided, specific technical scheme is such as
Under：
A kind of method for differentiating the radix tetrastigme place of production, comprises the following steps：Gather the radix tetrastigme sample of different sources；Obtain not
With the near infrared spectrum data of the radix tetrastigme sample in the place of production；Obtain the high performance liquid chromatography number of the radix tetrastigme sample of different sources
According to；Obtain the sample of predetermined number, and the sample is divided into by training set and pre- by Kennard-Stone samples partitioning
Survey collection；Least square method supporting vector machine model is established using training set；Using training set and forecast set least square is supported to
Amount machine model accuracy is analyzed；The near infrared spectrum data and high-efficient liquid phase color modal data of testing sample are obtained, and it is nearly red
The input of external spectrum data and high-efficient liquid phase color modal data as least square method supporting vector machine model, obtains the production of testing sample
Ground source.
Further, the step " the radix tetrastigme samples of collection different sources ", in addition to step：Gather different sources
Radix tetrastigme sample, all samples are crushed with medicinal herb grinder, and the sample in each place of production is each mixed, dried, cross 200 mesh
Sieve；The example weight in each place of production is no less than 100g, and the place of production includes：Zhejiang, Yunnan, Guizhou, Guangxi, Sichuan, Fujian, river
West and Hunan.
Further, the step " near infrared spectrum data for obtaining the radix tetrastigme sample of different sources ", in addition to step
Suddenly：Weigh sample 10g every time and be placed in near-infrared rotary sample cup and scan, setting scanning range is 10000~4000cm-1, point
Resolution is 8cm-1, scan 64 times, measure the near infrared spectrum data of the sample.
Further, the step " the high-efficient liquid phase color modal data for obtaining the radix tetrastigme sample of different sources ", in addition to
Step：Set chromatographic condition as follows：Chromatographic column is Polaris C18 (2.1 × 100mm, 1.7um), mobile phase is 100% water-soluble
The acetonitrile solution of liquid -100% (98: 2)；Detection wavelength is 282nm, and volume flow is 350.0 μ L/min；The μ L of sample size 1；Column temperature is
40℃。
Further, the sample " and is divided into training set by the step by Kennard-Stone samples partitioning
And forecast set ", in addition to step：The near infrared spectrum data of the sample of all predetermined numbers is put into Excel numbers by rows
According in form, often row represents the near-infrared data of a sample；The high-efficient liquid phase color modal data of each sample is pressed into the respective place of production
Order is also stored in the Excel data forms；The Excel data read procedures write by MATLAB, read the Excel
Data form, and the form is preserved with Mat file formats；By Kennard-Stone samples partitioning by the Mat trays
Sample in formula is divided into training set and forecast set.
Further, the step " establishing least square method supporting vector machine model using training set ", in addition to step：Will
Training set random division is K subset, and a least square method supporting vector machine model is established to each subset, is built together vertical K
Least square method supporting vector machine model, take and differentiate precision highest least square method supporting vector machine model as last discriminating mould
Type.
Further, the step " establishing least square method supporting vector machine model using training set ", in addition to step：Will
Training set random division is K subset, concentrates a subset to collect as checking K son, remaining K-1 subset is as training
Collection, least square method supporting vector machine model is established using K-1 training set, and verify that the least square is supported using checking collection
Vector machine model, obtain a discriminating precision；Collect in turn using K subset as checking, repeat K checking, obtain K most
A young waiter in a wineshop or an inn multiplies supporting vector machine model and K discriminating precision；Take and differentiate precision highest least square method supporting vector machine model conduct
Last discriminating model.
Further, the step " a least square method supporting vector machine model is established to each subset ", in addition to
Step：Assuming that subset is：And xi∈Rd, yi∈ {+1, -1 }, ∮ are the anonymous mappings of kernel function, then least square branch
Holding vector machine model can be represented in the form of following
γ-penalty coefficient, ei- slack variable, defined function Lagrange：
Herein, αi>=0 is Largrange multipliers, to ω, b, ei·αiPartial derivative is sought respectively, further can obtain core after conversion
Function
Required least square method supporting vector machine model exports：
Further, the step " is carried out using training set and forecast set to least square method supporting vector machine model accuracy
Analysis ", in addition to step：Respectively using training set and forecast set as the input of least square method supporting vector machine model, instructed
Practice the provenance of collection and forecast set；The actual provenance of the provenance of acquisition and training set and forecast set is contrasted,
Obtain the precision of least square method supporting vector machine model.
The beneficial effects of the invention are as follows：The near of the radix tetrastigme sample of different sources is obtained by near-infrared spectral analysis technology
Ir data, near-infrared spectral analysis technology as a kind of novel practical analytical technology, be reflected to random sample product physics and
Chemical information, be applicable not only to solid, liquid, gas analysis sample, compared with traditional method, have quick, non-destructive,
The advantages that cheap and sample size is few.And the high-efficient liquid phase color modal data of the radix tetrastigme sample of different sources is obtained, then obtain default
The sample of quantity, and sample is divided into by training set and forecast set by Kennard-Stone sample partitionings；Utilize training set
Establish least square method supporting vector machine model；And least square method supporting vector machine model accuracy is entered using training set and forecast set
Row analysis；The provenance of recycling least square method supporting vector machine model acquisition testing sample, discrimination method degree of accuracy height,
It is highly reliable, and cost is low, can overcome the difficulty of parsing collection of illustrative plates, it is simple to operate.
Brief description of the drawings
Fig. 1 is a kind of flow chart for differentiating radix tetrastigme place of production method described in embodiment；
Fig. 2 is the flow chart for obtaining training set and forecast set described in embodiment by K-S samples partitioning；
Fig. 3 is three kinds of different model accuracy comparative result figures described in embodiment；
Fig. 4 is that the LS-SVM models of single establishment of spectrum are used described in embodiment and use near infrared spectrum data
The LS-SVM model accuracy comparative result figures established are combined with high-efficient liquid phase color modal data.
Embodiment
Referring to Fig. 1, first the near infrared spectrum and high performance liquid chromatography that occur in the present embodiment are done first with
Lower explanation：
Near infrared spectrum：Be between visible ray (Vis) and in electromagnetic radiation as waves between infrared (MIR), U.S. material inspection
Survey association (ASTM) and near infrared spectrum is defined as to 780-2526nm region, be that people have found in absorption spectrum first
Individual non-visible light area.Near infrared spectrum and the sum of fundamental frequencies of hydric group (O-H, N-H, C-H) vibration in organic molecule and at different levels times
The uptake zone of frequency is consistent, by scanning the near infrared spectrum of sample, can obtain the feature of organic molecule hydric group in sample
Information, and using near-infrared spectrum technique analysis sample have easily and fast, efficiently, it is accurately relatively low with cost, do not destroy sample
Product, do not consume chemical reagent, it is free from environmental pollution the advantages that.
High performance liquid chromatography：(High Performance Liquid Chromatography HPLC) also known as " high pressure liquid
Phase chromatogram ", " high-speed liquid chromatography ", " high separation liquid chromatogram ", " modern age column chromatography " etc..High performance liquid chromatography is chromatography
An important branch, using liquid as mobile phase, using high pressure transfusion system, by single solvent or difference with opposed polarity
The mobile phases such as the mixed solvent of ratio, buffer solution are pumped into the chromatographic column equipped with stationary phase, after each composition is separated in post, enter
Detector is detected, so as to realize the analysis to sample.
In the present embodiment, the collection of near infrared spectrum data produces using Thermo companies of the U.S.
The type Fourier Transformation Near-Infrared Spectroscopy Analysis instrument of ANTARIS II, equipped with InGaAs detectors, integrating sphere diffusing reflection sampling system and
Rotating quartz specimen cup, scanning range are 10000~4000cm-1, resolution ratio 8cm-1, scan 64 times.
In the present embodiment, a kind of method for differentiating the radix tetrastigme place of production is realized specific as follows：
Step S101：Gather the radix tetrastigme sample of different sources.Can be in the following way：Gather the radix tetrastigme of different sources
Sample, all samples are crushed with medicinal herb grinder, and the sample in each place of production is each mixed, dried, cross 200 mesh sieves；It is each
The example weight in the place of production is no less than 100g, and the place of production includes in the present embodiment：Zhejiang, Yunnan, Guizhou, Guangxi, Sichuan,
Fujian, Jiangxi and Hunan.After having obtained sample, deposited in standby in valve bag.
After the radix tetrastigme sample for having gathered different sources, step S102 is performed：Obtain the radix tetrastigme sample of different sources
Near infrared spectrum data.Can be in the following way：For the radix tetrastigme sample of different sources, sample 10g is weighed every time and is placed in closely
Scanned in infrared rotary sample cup, setting scanning range is 10000~4000cm-1, resolution ratio 8cm-1, scan 64 times, measure
The near infrared spectrum data of the sample.
After the radix tetrastigme sample for having gathered different sources, step S103 is performed：Obtain the radix tetrastigme sample of different sources
High-efficient liquid phase color modal data.Can be in the following way：Set chromatographic condition as follows：Chromatographic column be Polaris C18 (2.1 ×
100mm, 1.7um), mobile phase be the acetonitrile solution of 100% aqueous solution -100% (98: 2)；Detection wavelength is 282nm, volume flow
For 350.0 μ L/min；The μ L of sample size 1；Column temperature is 40 DEG C.
Wherein step S102 and step S103 has no sequencing relation, can simultaneously carry out, also can one in front and one in back carry out.Through
Step S102 and step S103 are crossed, finally collects Zhejiang, Yunnan, Guizhou, Guangxi, Sichuan, Fujian, Jiangxi, three leaves in Hunan
The near infrared spectrum data and high-efficient liquid phase color modal data of blue or green sample totally 240 samples.
Step S104：The sample of predetermined number is obtained, and is drawn the sample by Kennard-Stone samples partitioning
It is divided into training set and forecast set.Can be in the following way：In the present embodiment, predetermined number is 240, in other embodiment party
In formula, any number of sample can be obtained according to actual conditions.Referring to Fig. 2, will by Kennard-Stone samples partitioning
The sample is divided into training set and forecast set, specifically can be in the following way：
Step S201：The near infrared spectrum data of the sample of all predetermined numbers is put into Excel tables of data by rows
In lattice, often row represents the near-infrared data of a sample.Step S202：By the high-efficient liquid phase color modal data of each sample by respective
Place of production order is also stored in the Excel data forms.The Excel data forms can be named with data1.Then step is performed
S203：The Excel data read procedures write by MATLAB, the Excel data forms are read, and with Mat file formats
Preserve the form.Data1.mat can be named as.Step S204：It is by Kennard-Stone samples partitioning that the Mat is literary
Sample in part form is divided into training set and forecast set.
After having obtained training set and forecast set, step S105 is performed：Least square method supporting vector machine is established using training set
Model.Can be in the following way：It is K subset by training set random division, a least square branch is established to each subset
Vector machine model is held, vertical K least square method supporting vector machine model of building together, takes and differentiates precision highest least square supporting vector
Machine model is as last discriminating model.The average value of K discriminating precision is taken in the present embodiment as last discriminating mould
The performance indications of type, highest can also be directly taken to differentiate accuracy value as last discriminating model in other embodiments
Performance indications.
In other embodiments, also can be in the following way：It is K subset by training set random division, by K subset
Middle a subset collects as checking, and remaining K-1 subset is established least square using K-1 training set and supported as training set
Vector machine model, and the least square method supporting vector machine model is verified using checking collection, obtain a discriminating precision；In turn will
K subset collects respectively as checking, repeats K checking, obtains K least square method supporting vector machine model and K discriminating precision；
Take and differentiate precision highest least square method supporting vector machine model as last discriminating model.K are taken in the present embodiment
Differentiate performance indications of the average value of precision as last discriminating model, can also directly take highest in other embodiments
Performance indications of the discriminating accuracy value as last discriminating model.
Wherein, the step " a least square method supporting vector machine model is established to each subset ", in addition to step：
Assuming that subset is：And xi∈Rd, yi∈ {+1, -1 }, ∮ are the anonymous mappings of kernel function, then a most young waiter in a wineshop or an inn
Multiplying supporting vector machine model can be represented in the form of following
γ-penalty coefficient, ei- slack variable, defined function Lagrange：
Herein, αi>=0 is Largrange multipliers, to ω, b, ei·αiPartial derivative is sought respectively, further can obtain core after conversion
Function
Required least square method supporting vector machine model exports：
I.e.：(1) start with from the loss function of machine learning, two norms are used in the object function of its optimization problem；
(2) the inequality constraints condition in SVM canonical algorithms is replaced using equality constraint so that LS-SVM methods
The solution of optimization problem is changed into the solution of the one group of system of linear equations obtained by Kuhn-Tucker conditions.
Obtain and differentiate precision highest least square method supporting vector machine model (the i.e. optimal least square support vector machines mould of performance
Type) after, perform step S106：Least square method supporting vector machine model accuracy is analyzed using training set and forecast set.Can
In the following way：Respectively using training set and forecast set as the input of least square method supporting vector machine model, training set is obtained
With the provenance of forecast set；The actual provenance of the provenance of acquisition and training set and forecast set is contrasted, obtained
The precision of least square method supporting vector machine model.In the present embodiment, the discriminating model of two existing radix tetrastigmes has also been used
PLS-DA models and mRVM models, the input using same training set and forecast set as above-mentioned two model, obtain this two
The precision of model, its result and least square method supporting vector machine model accuracy in present embodiment are contrasted, comparing result
It refer to Fig. 3, what LS-SVM was represented in figure is then least square method supporting vector machine model.As can be seen from the figure by different sources
LS-SVM models, PLS-DA models and the mRVM models that sample is established differentiate for the training set of totality and the sample of forecast set
Accuracy rate is more than 90%, wherein LS-SVM discrimination models best results, and it is to Zhejiang, Yunnan, Guizhou, Guangxi, Sichuan, good fortune
Build, Jiangxi, the radix tetrastigme training set differentiation rate in eight, Hunan etc. place of production reaches 100%, and forecast set differentiation rate is respectively reached
98.3%th, 96.7%, 100%, 100%, 98.0%, 100.0%, 100.0% and 98.5%.
In the present embodiment, the LS-SVM models of single establishment of spectrum are also used, by same training set and prediction
Collect the input as the model, obtain the precision of the model, near infrared spectrum will be used in the precision result and present embodiment
The precision result for the LS-SVM models for being combined to obtain with high performance liquid chromatography is contrasted, and as a result refers to Fig. 4.Can from figure
Go out, near infrared spectrum is combined LS- of the degree of accuracy higher than single establishment of spectrum of obtained LS-SVM models with high performance liquid chromatography
SVM models.
Finally perform step S107：The near infrared spectrum data and high-efficient liquid phase color modal data of testing sample are obtained, and will
The input of near infrared spectrum data and high-efficient liquid phase color modal data as least square method supporting vector machine model, obtain testing sample
Provenance.
The near infrared spectrum data of the radix tetrastigme sample of different sources, near-infrared are obtained by near-infrared spectral analysis technology
Spectral analysis technique is reflected to the physics and chemical information of random sample product, is applicable not only to as a kind of novel practical analytical technology
Solid, liquid, gas analysis sample, compared with traditional method, have quick, non-destructive, cheap and sample size few etc. excellent
Point.And the high-efficient liquid phase color modal data of the radix tetrastigme sample of different sources is obtained, then the sample of predetermined number is obtained, and pass through
Sample is divided into training set and forecast set by Kennard-Stone sample partitionings；Least square is established using training set to support
Vector machine model；And least square method supporting vector machine model accuracy is analyzed using training set and forecast set；Recycle most
A young waiter in a wineshop or an inn multiplies the provenance that supporting vector machine model obtains testing sample, and the discrimination method degree of accuracy is high, highly reliable, and cost
It is low, the difficulty of parsing collection of illustrative plates can be overcome, it is simple to operate.
It should be noted that herein, such as first and second or the like relational terms are used merely to a reality
Body or operation make a distinction with another entity or operation, and not necessarily require or imply and deposited between these entities or operation
In any this actual relation or order.Moreover, term " comprising ", "comprising" or its any other variant are intended to
Nonexcludability includes, so that process, method, article or terminal device including a series of elements not only include those
Key element, but also the other element including being not expressly set out, or it is this process, method, article or end also to include
The intrinsic key element of end equipment.In the absence of more restrictions, limited by sentence " including ... " or " including ... "
Key element, it is not excluded that other key element in the process including the key element, method, article or terminal device also be present.This
Outside, herein, " being more than ", " being less than ", " exceeding " etc. are interpreted as not including this number；" more than ", " following ", " within " etc. understand
It is to include this number.
It should be understood by those skilled in the art that, the various embodiments described above can be provided as method, apparatus or computer program production
Product.These embodiments can use the embodiment in terms of complete hardware embodiment, complete software embodiment or combination software and hardware
Form.All or part of step in the method that the various embodiments described above are related to can by program come instruct the hardware of correlation come
Complete, described program can be stored in the storage medium that computer equipment can be read, for performing the various embodiments described above side
All or part of step described in method.The computer equipment, include but is not limited to：Personal computer, server, general-purpose computations
It is machine, special-purpose computer, the network equipment, embedded device, programmable device, intelligent mobile terminal, intelligent home device, wearable
Smart machine, vehicle intelligent equipment etc.；Described storage medium, include but is not limited to：RAM, ROM, magnetic disc, tape, CD, sudden strain of a muscle
Deposit, USB flash disk, mobile hard disk, storage card, memory stick, webserver storage, network cloud storage etc..
The various embodiments described above are with reference to method, equipment (system) and the computer program product according to embodiment
Flow chart and/or block diagram describe.It should be understood that can be by every in computer program instructions implementation process figure and/or block diagram
One flow and/or the flow in square frame and flow chart and/or block diagram and/or the combination of square frame.These computers can be provided
Programmed instruction is to the processor of computer equipment to produce a machine so that passes through the finger of the computing device of computer equipment
Order, which produces, to be used to realize what is specified in one flow of flow chart or multiple flows and/or one square frame of block diagram or multiple square frames
The device of function.
These computer program instructions may be alternatively stored in the computer that computer equipment can be guided to work in a specific way and set
In standby readable memory so that the instruction being stored in the computer equipment readable memory produces the manufacture for including command device
Product, the command device is realized to be referred in one flow of flow chart or multiple flows and/or one square frame of block diagram or multiple square frames
Fixed function.
These computer program instructions can be also loaded on computer equipment so that performed on a computing device a series of
Operating procedure is to produce computer implemented processing, so as to which the instruction performed on a computing device is provided for realizing in flow
The step of function of being specified in one flow of figure or multiple flows and/or one square frame of block diagram or multiple square frames.
Although the various embodiments described above are described, those skilled in the art once know basic wound
The property made concept, then other change and modification can be made to these embodiments, so embodiments of the invention are the foregoing is only,
Not thereby the scope of patent protection of the present invention, every equivalent structure made using description of the invention and accompanying drawing content are limited
Or equivalent flow conversion, or other related technical areas are directly or indirectly used in, similarly it is included in the patent of the present invention
Within protection domain.
Claims (9)
- A kind of 1. method for differentiating the radix tetrastigme place of production, it is characterised in that comprise the following steps：Gather the radix tetrastigme sample of different sources；Obtain the near infrared spectrum data of the radix tetrastigme sample of different sources；Obtain the high-efficient liquid phase color modal data of the radix tetrastigme sample of different sources；Obtain predetermined number sample, and by Kennard-Stone samples partitioning by the sample be divided into training set and Forecast set；Least square method supporting vector machine model is established using training set；Least square method supporting vector machine model accuracy is analyzed using training set and forecast set；The near infrared spectrum data and high-efficient liquid phase color modal data of testing sample are obtained, and by near infrared spectrum data and efficient liquid Input of the phase chromatographic data as least square method supporting vector machine model, obtain the provenance of testing sample.
- 2. a kind of method for differentiating the radix tetrastigme place of production according to claim 1, it is characterised in that " collection is or not the step With the radix tetrastigme sample in the place of production ", in addition to step：The radix tetrastigme sample of different sources is gathered, all samples are crushed with medicinal herb grinder, and by the sample in each place of production each Mix, dry, cross 200 mesh sieves；The example weight in each place of production is no less than 100g, and the place of production includes：Zhejiang, Yunnan, Guizhou, Guangxi, Sichuan, Fujian, Jiangxi and Hunan.
- 3. a kind of method for differentiating the radix tetrastigme place of production according to claim 1, it is characterised in that the step " obtains not With the near infrared spectrum data of the radix tetrastigme sample in the place of production ", in addition to step：Weigh sample 10g every time and be placed in near-infrared rotary sample cup and scan, setting scanning range is 10000~4000cm-1, point Resolution is 8cm-1, scan 64 times, measure the near infrared spectrum data of the sample.
- 4. a kind of method for differentiating the radix tetrastigme place of production according to claim 1, it is characterised in that the step " obtains not With the high-efficient liquid phase color modal data of the radix tetrastigme sample in the place of production ", in addition to step：Set chromatographic condition as follows：Chromatographic column is Polaris C18 (2.1 × 100mm, 1.7um), mobile phase is the acetonitrile solution of 100% aqueous solution -100% (98∶2)；Detection wavelength is 282nm, and volume flow is 350.0 μ L/min；The μ L of sample size 1；Column temperature is 40 DEG C.
- A kind of 5. method for differentiating the radix tetrastigme place of production according to claim 1, it is characterised in that the step " and pass through The sample is divided into training set and forecast set by Kennard-Stone samples partitioning ", in addition to step：The near infrared spectrum data of the sample of all predetermined numbers is put into Excel data forms by rows, often row represents The near-infrared data of one sample；The high-efficient liquid phase color modal data of each sample is also stored in the Excel data forms by respective place of production order；The Excel data read procedures write by MATLAB, the Excel data forms are read, and protected with Mat file formats Deposit the form；Sample in the Mat file formats is divided into by training set and forecast set by Kennard-Stone samples partitioning.
- 6. a kind of method for differentiating the radix tetrastigme place of production according to claim 1, it is characterised in that the step " utilizes instruction Practice collection and establish least square method supporting vector machine model ", in addition to step：It is K subset by training set random division, a least square method supporting vector machine model is established to each subset, is built together K least square method supporting vector machine model is found, takes and differentiates precision highest least square method supporting vector machine model as last Differentiate model.
- 7. a kind of method for differentiating the radix tetrastigme place of production according to claim 1, it is characterised in that the step " utilizes instruction Practice collection and establish least square method supporting vector machine model ", in addition to step：It is K subset by training set random division, concentrates a subset to collect as checking K son, remaining K-1 subset conduct Training set, least square method supporting vector machine model is established using K-1 training set, and the least square is verified using checking collection Supporting vector machine model, obtain a discriminating precision；Collect in turn using K subset as checking, repeat K checking, obtain K least square method supporting vector machine model and K Individual discriminating precision；Take and differentiate precision highest least square method supporting vector machine model as last discriminating model.
- 8. a kind of method for differentiating the radix tetrastigme place of production according to claim 6, it is characterised in that the step is " to each Subset establishes a least square method supporting vector machine model ", in addition to step：Assuming that subset is：And xt∈Rd, yi∈ {+1, -1 }, ∮ are the anonymous mappings of kernel function, then least square branch Holding vector machine model can be represented in the form of following<mrow> <munder> <mi>min</mi> <mrow> <mi>&omega;</mi> <mo>,</mo> <mi>b</mi> <mo>,</mo> <mi>e</mi> </mrow> </munder> <mi>&phi;</mi> <mrow> <mo>(</mo> <mi>&omega;</mi> <mo>,</mo> <mi>b</mi> <mo>,</mo> <mi>e</mi> <mo>)</mo> </mrow> <mo>=</mo> <mfrac> <mn>1</mn> <mn>2</mn> </mfrac> <mo>|</mo> <mo>|</mo> <mi>&omega;</mi> <mo>|</mo> <msup> <mo>|</mo> <mn>2</mn> </msup> <mo>+</mo> <mi>&gamma;</mi> <mfrac> <mn>1</mn> <mn>2</mn> </mfrac> <munderover> <mo>&Sigma;</mo> <mrow> <mi>i</mi> <mo>=</mo> <mn>1</mn> </mrow> <mi>n</mi> </munderover> <msub> <mi>e</mi> <mi>i</mi> </msub> </mrow>γ-penalty coefficient, ei- slack variable, defined function Lagrange：Herein, ai>=0 is Largrange multipliers, to ω, b, ei, aiPartial derivative is sought respectively, further can obtain kernel function after conversionRequired least square method supporting vector machine model exports：
- 9. a kind of method for differentiating the radix tetrastigme place of production according to claim 1, it is characterised in that the step " utilizes instruction Practice collection and forecast set analyzed least square method supporting vector machine model accuracy ", in addition to step：Input using training set and forecast set as least square method supporting vector machine model respectively, obtain training set and forecast set Provenance；The actual provenance of the provenance of acquisition and training set and forecast set is contrasted, obtains least square supporting vector The precision of machine model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710762908.XA CN107607485A (en) | 2017-08-30 | 2017-08-30 | A kind of method for differentiating the radix tetrastigme place of production |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710762908.XA CN107607485A (en) | 2017-08-30 | 2017-08-30 | A kind of method for differentiating the radix tetrastigme place of production |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107607485A true CN107607485A (en) | 2018-01-19 |
Family
ID=61056465
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710762908.XA Pending CN107607485A (en) | 2017-08-30 | 2017-08-30 | A kind of method for differentiating the radix tetrastigme place of production |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107607485A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109632696A (en) * | 2018-12-13 | 2019-04-16 | 宜宾学院 | A kind of inexpensive near-infrared spectrum method identifying medicinal tablet source |
| CN109975236A (en) * | 2019-04-04 | 2019-07-05 | 山东省农业科学院农业质量标准与检测技术研究所 | A method of identifying the honeysuckle place of production using near-infrared spectrum technique |
| CN110823828A (en) * | 2018-08-09 | 2020-02-21 | 中国科学院西北高原生物研究所 | Method for identifying Wumai green wormwood in different producing areas |
| CN113466224A (en) * | 2021-06-30 | 2021-10-01 | 中国科学院宁波材料技术与工程研究所慈溪生物医学工程研究所 | Array sensor for identifying radix tetrastigme producing area and preparation method and application thereof |
Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106560698A (en) * | 2016-10-20 | 2017-04-12 | 中国计量大学 | Identification method for producing area of plant based on multiple detection technologies |
-
2017
- 2017-08-30 CN CN201710762908.XA patent/CN107607485A/en active Pending
Patent Citations (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106560698A (en) * | 2016-10-20 | 2017-04-12 | 中国计量大学 | Identification method for producing area of plant based on multiple detection technologies |
Non-Patent Citations (2)
| Title |
|---|
| 李运等: "FTIR结合化学计量学对三七产地鉴别及皂苷含量预测研究", 《光谱学与光谱分析》 * |
| 梁锦锦等: "稀疏L1范数最小二乘支持向量机", 《计算机工程与设计》 * |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110823828A (en) * | 2018-08-09 | 2020-02-21 | 中国科学院西北高原生物研究所 | Method for identifying Wumai green wormwood in different producing areas |
| CN109632696A (en) * | 2018-12-13 | 2019-04-16 | 宜宾学院 | A kind of inexpensive near-infrared spectrum method identifying medicinal tablet source |
| CN109975236A (en) * | 2019-04-04 | 2019-07-05 | 山东省农业科学院农业质量标准与检测技术研究所 | A method of identifying the honeysuckle place of production using near-infrared spectrum technique |
| CN113466224A (en) * | 2021-06-30 | 2021-10-01 | 中国科学院宁波材料技术与工程研究所慈溪生物医学工程研究所 | Array sensor for identifying radix tetrastigme producing area and preparation method and application thereof |
| CN113466224B (en) * | 2021-06-30 | 2024-05-14 | 宁波慈溪生物医学工程研究所 | Array sensor for identifying origin of radix tetrastigme, and preparation method and application thereof |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107607485A (en) | A kind of method for differentiating the radix tetrastigme place of production | |
| Cheng et al. | Infrared spectroscopic studies of Chinese medicines | |
| Xin et al. | Application of genetic algorithm‐support vector regression (GA‐SVR) for quantitative analysis of herbal medicines | |
| CN103364362B (en) | A kind of THz-TDS that utilizes is in conjunction with the method for Chemical Measurement qualification Chinese herbal medicine | |
| CN103033486B (en) | Method for near infrared spectrum monitoring of quality of pericarpium citri reticulatae and citrus chachiensis hortorum medicinal materials | |
| CN101256177A (en) | System for evaluation of Chinese medicine numeralization color spectrum dactylogram similarity | |
| CN102288551A (en) | Method for distinguishing traditional Chinese medicinal material by utilizing hyperspectral data | |
| CN104730030A (en) | Method for true and false identification and place of origin judgment of codonopsis pilosula based on near infrared analysis technology | |
| CN103293118A (en) | Hogwash oil identification method based on near infrared reflectance spectroscopy | |
| Meng et al. | Discrimination and content analysis of fritillaria using near infrared spectroscopy | |
| Nie et al. | Enhanced accuracy of near-infrared spectroscopy for traditional Chinese medicine with competitive adaptive reweighted sampling | |
| CN111024643A (en) | Near infrared spectrum detection method for quality evaluation of gentiana straminea maxim medicinal materials | |
| CN107917896A (en) | Radix glycyrrhizae method for quick identification based near infrared spectrum and Clustering Analysis Technology | |
| Li et al. | Characteristic fingerprint based on low polar constituents for discrimination of Wolfiporia extensa according to geographical origin using UV spectroscopy and chemometrics methods | |
| CN106018452A (en) | Peanut variety nondestructive testing method based on nuclear magnetic resonance technology | |
| CN105588892A (en) | Method for identifying dalbergia cochinchinensis species in microdamage mode based on fingerprint spectrum | |
| Yang et al. | Characterization of Paris polyphylla var. yunnanensis by infrared and ultraviolet spectroscopies with chemometric data fusion | |
| Li et al. | Integrative quantitative and qualitative analysis for the quality evaluation and monitoring of Danshen medicines from different sources using HPLC-DAD and NIR combined with chemometrics | |
| CN104458941A (en) | QAMS detection method for multi-components in fructus psoraleae based on UHPLC technique and application thereof | |
| Li et al. | Non-targeted analytical technology in herbal medicines: applications, challenges, and perspectives | |
| CN103760130A (en) | Method for measuring tween-80 content in compound musk injection by using near-infrared spectrum | |
| CN105784951A (en) | Multiple indicator rapid detection method for raw medicinal powder of condensed pill of six drugs with rehmannia | |
| Liu et al. | Chemical fingerprinting of wild germplasm resource of Ophiopogon japonicus from Sichuan basin, China by RP-HPLC coupled with hierarchical cluster analysis | |
| CN112345511A (en) | Method for detecting organic chlorine pesticide residue of astragalus membranaceus | |
| CN102998279A (en) | Method for fast identifying authenticity of Ganoderma lucidum spore powder |
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 | ||
| WD01 | Invention patent application deemed withdrawn after publication | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20180119 |