CN109668859A - The near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm - Google Patents
The near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm Download PDFInfo
- Publication number
- CN109668859A CN109668859A CN201910158130.0A CN201910158130A CN109668859A CN 109668859 A CN109668859 A CN 109668859A CN 201910158130 A CN201910158130 A CN 201910158130A CN 109668859 A CN109668859 A CN 109668859A
- Authority
- CN
- China
- Prior art keywords
- prickly ash
- chinese prickly
- production
- near infrared
- algorithm
- 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
- 238000004519 manufacturing process Methods 0.000 title claims abstract description 41
- 238000000034 method Methods 0.000 title claims abstract description 27
- 238000002329 infrared spectrum Methods 0.000 title claims abstract description 26
- 241001079064 Zanthoxylum schinifolium Species 0.000 title claims abstract 15
- 238000001228 spectrum Methods 0.000 claims abstract description 17
- 239000002245 particle Substances 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 10
- 238000012706 support-vector machine Methods 0.000 claims description 6
- 230000003595 spectral effect Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 claims 1
- 238000013178 mathematical model Methods 0.000 claims 1
- 238000002203 pretreatment Methods 0.000 claims 1
- 238000004611 spectroscopical analysis Methods 0.000 abstract description 6
- 238000001514 detection method Methods 0.000 abstract description 4
- 238000011156 evaluation Methods 0.000 abstract description 3
- 238000012545 processing Methods 0.000 abstract description 2
- 238000004364 calculation method Methods 0.000 abstract 1
- 238000004451 qualitative analysis Methods 0.000 abstract 1
- 244000089698 Zanthoxylum simulans Species 0.000 description 48
- 239000000523 sample Substances 0.000 description 45
- 238000012360 testing method Methods 0.000 description 14
- 238000004458 analytical method Methods 0.000 description 6
- 235000008534 Capsicum annuum var annuum Nutrition 0.000 description 5
- 240000008384 Capsicum annuum var. annuum Species 0.000 description 5
- 239000010453 quartz Substances 0.000 description 5
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N silicon dioxide Inorganic materials O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 description 5
- 239000006101 laboratory sample Substances 0.000 description 4
- 238000011160 research Methods 0.000 description 4
- 238000004497 NIR spectroscopy Methods 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 238000004566 IR spectroscopy Methods 0.000 description 2
- 238000004128 high performance liquid chromatography Methods 0.000 description 2
- 239000004615 ingredient Substances 0.000 description 2
- 238000004949 mass spectrometry Methods 0.000 description 2
- 238000010606 normalization Methods 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 238000003909 pattern recognition Methods 0.000 description 2
- 230000009466 transformation Effects 0.000 description 2
- 235000007650 Aralia spinosa Nutrition 0.000 description 1
- 241000345998 Calamus manan Species 0.000 description 1
- 241000949456 Zanthoxylum Species 0.000 description 1
- 238000000862 absorption spectrum Methods 0.000 description 1
- 230000000844 anti-bacterial effect Effects 0.000 description 1
- 230000003110 anti-inflammatory effect Effects 0.000 description 1
- 230000000259 anti-tumor effect Effects 0.000 description 1
- 239000003963 antioxidant agent Substances 0.000 description 1
- 230000003078 antioxidant effect Effects 0.000 description 1
- 235000006708 antioxidants Nutrition 0.000 description 1
- 230000000975 bioactive effect Effects 0.000 description 1
- 238000009614 chemical analysis method Methods 0.000 description 1
- 238000002512 chemotherapy Methods 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000001035 drying Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 229930014626 natural product Natural products 0.000 description 1
- 238000009659 non-destructive testing Methods 0.000 description 1
- 235000012950 rattan cane Nutrition 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000004575 stone 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
-
- 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
- G01N21/3563—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing solids; Preparation of samples therefor
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 present invention relates to the Fast nondestructive evaluation fields in the Chinese prickly ash place of production and kind to belong to the detection field of the Chinese prickly ash place of production and kind more particularly to a kind of near infrared light spectrum discrimination field in Chinese prickly ash place of production and kind based on SVM algorithm.This method is described in detail by how by SVM algorithm to establish disaggregated model, carries out qualitative analysis to Chinese prickly ash attribute.Firstly, performing corresponding processing to the sample of known Chinese prickly ash attribute, and the adjustment of relevant parameter is carried out to NIR instrument；Secondly, the sample prepared is acquired its atlas of near infrared spectra, spectrum is pre-processed；Then, analytical calculation is carried out to spectrogram；Finally, using spectroscopic data as the input of SVM algorithm, the best parameter group of penalty parameter c and kernel functional parameter g is established by particle swarm algorithm (PSO), so that a kind of method is provided to construct optimal disaggregated model, it is also final to provide a kind of method for the realization identification Chinese prickly ash place of production and kind.
Description
Technical field
The present invention relates to the Fast nondestructive evaluation fields in the Chinese prickly ash place of production and kind, are based on SVM algorithm more particularly to one kind
The Chinese prickly ash place of production and kind near infrared light spectrum discrimination field.
Background technique
Chinese prickly ash is important one of the industrial crops in China, first of the gross area, the world total output Jun Ju.Modern natural products
Chemistry and pharmaceutical research show that these bioactive ingredients in Chinese prickly ash have anti-oxidant, antitumor, anti-inflammatory and antibacterial anti-corrosion
Function.Due to differences such as geographical environment, climate difference, soil, kinds, Chinese prickly ash chemical component and content difference are caused.
However China still lacks corresponding evaluation criterion and technical specification for the place of production of Chinese prickly ash and the identification of kind at present, so, inspection
There is important meaning in the place of production and kind for surveying Chinese prickly ash.
The detection method in traditional the Chinese prickly ash place of production and kind, mainly taking human as organoleptic analysis based on, however according to shape face
The determination method shortage objectivity and accuracy of color, taste, relatively depend on the experience of professional, are difficult to accomplish to standardize and advise
Generalized.In addition, currently predominantly detecting technology has gas phase-Mass Spectrometry, high performance liquid chromatography and mid-infrared light spectrometry etc., root
The place of production for identifying Chinese prickly ash and the model of kind are established according to the otherness of Chinese prickly ash intrinsic chemical ingredient and content.But these methods all with
Based on laboratory applications, and the testing cost of gas phase-Mass Spectrometry and high performance liquid chromatography is all more expensive, at sample
Manage it is cumbersome, to experimental implementation require it is very high.Therefore simple, quick, the lossless Chinese prickly ash place of production of one kind and kind mirror are researched and developed
Other detection method, has important practical significance.
Compared with other chemical analysis methods, near-infrared spectrum technique have it is low in cost, quick and precisely, without sample it is pre-
The features such as handling, be lossless, not destroying sample, is pollution-free.But from the point of view of existing near infrared spectroscopy measurements, due in Chinese prickly ash
Multiple components absorption spectra is overlapped mutually, and it is almost infeasible to be identified to depend merely on spectrogram, it is necessary to by Chemical Measurement and
The methods of pattern-recognition carries out discriminatory analysis.
For this problem, the present invention proposes to utilize near-infrared spectrum technique, carries out non-destructive testing to Chinese prickly ash, in conjunction with branch
Vector machine (support vector machine, SVM) algorithm is held, the Chinese prickly ash place of production and kind are quickly identified, is traced back for the Chinese prickly ash place of production
Source and quality safety provide technical support.
Summary of the invention
Detection for traditional Chinese prickly ash place of production and kind is insufficient, and the invention proposes the Chinese prickly ash near-infrareds based on SVM algorithm
The recognition methods of spectrum.The invention realizes that steps are as follows: (1) collecting the artificial cultivation pericarpium zanthoxyli bungeani of different sources and kind and blue and white
Green pepper, and engage three or more professionals to identify each place of production and kind Chinese prickly ash, and do corresponding label；(2) it carries out close
The debugging of infrared spectroscopy instrument selects suitable near infrared spectrum parameter；(3) near infrared spectrum is carried out to the Chinese prickly ash sample of collection
Scanning constructs Chinese prickly ash place of production discriminating near infrared spectrum map library, Chinese prickly ash Variety identification near infrared spectrum map library respectively；(4) into
Row Pretreated spectra；(5) sample near infrared spectrum data is analyzed using SVM chemometrics method, establishes Chinese prickly ash production
The qualitative discrimination model on ground and kind；(6) sample is predicted using the model.
Detailed description of the invention
The flow diagram of Fig. 1 the method for the invention.
Fig. 2 is used for 205 parts of Chinese prickly ash sample atlas of near infrared spectra in the place of production and Variety identification.
Specific embodiment
Present invention is further described in detail with reference to the accompanying drawing.
Implementation flow chart of the invention, as shown in Figure 1, the specific steps of which are as follows:
(1) the artificial cultivation pericarpium zanthoxyli bungeani and pericarpium zanthoxyli schinifolii of different sources and kind are collected in the selection of research object, use classics
Kennard-Stone method models collection sample to sample and selects.And engage three or more professionals to each place of production and product
The Chinese prickly ash of kind is identified, and does corresponding label；
(2) select attached integrating sphere and quartz sample pool as sample container according to research object, while near infrared spectroscopy instrument
The setting of equipment progress parameter；
(3) background signal is acquired when measuring sky integrating sphere and quartz sample pool near infrared spectroscopy instrument, under same experimental conditions,
Chinese prickly ash sample is put into quartz sample pool, sample signal is acquired, Chinese prickly ash is established to the near infrared light spectrum signal of acquisition respectively and is produced
Ground identifies near infrared spectrum map library, Chinese prickly ash Variety identification near infrared spectrum map library；
(4) use " wavelet transformation ", " first derivative+Savitzky-Golay is smooth ", " second dervative+
SavitzkyGolay is smooth ", " mean value centralization ", " minimax normalization ", " MSC ", " SNV " preprocess method is to close
Ir data is pre-processed；
(5) the optimized parameter group of penalty parameter c and kernel functional parameter g is established using particle swarm algorithm (PSO) in modeling process
It closes, disaggregated model is made to obtain best Generalization Capability while obtaining preferable classification accuracy；Using most normal in support vector machines
The method of Radial basis kernel function (radial basis function, RBF) establishes the Chinese prickly ash place of production and kind respectively
Near infrared spectrum identifies model；
(6) spectroscopic data in step (4) is established into disaggregated model by pattern-recognition SVM algorithm, Chinese prickly ash attribute is determined
Property analysis.Disaggregated model prediction result is compareed with actual sample attribute, obtains the accuracy of model.
Specifically, research material " Chinese prickly ash " in the step one, refers to the custom after artificial cultivation Chinese prickly ash kind pericarp is drying
Claim.
Specifically, in the step one Chinese prickly ash sample size be 205 parts, laboratory sample according to about 4:1 and 5:1 ratio
The Chinese prickly ash sample of different sources and kind is divided into training set and test set two parts by example, and training set is used for near-infrared analysis mould
The foundation of type, test set sample are used for the verifying of model.
Specifically, the MPA that the near infrared spectrum data acquisition in the step 2 is produced using German Brooker company
Type near infrared spectrometer.
Specifically, the triple chemo metric software of the step is 10.4 software of Unscrambler, OPUS 7.0 soft
Part and MATLAB.
Specific embodiment one:
(1) acquisition and classification of Chinese prickly ash sample
Experiment Chinese prickly ash sample collects 205 parts altogether, and for place of production discriminating, the essential information of laboratory sample is 17 parts of Sichuan Mao Wen, and four
40 parts of river Hanyuan, 49 parts of Hancheng Region, Shaanxi, 16 parts of Chongqing Jiangjin, 20 parts of Zhaotong County, Yunnan, 20 parts of Hanyuan County, sichuan Province, 24 parts of Sichuan Jinyang,
19 parts of Guanling of Guizhou, the sample place of production is numbered respectively with " 1 " ~ " 8 "；And for Variety identification, the basic letter of laboratory sample
Breath is 89 parts of clovershrub, 17 parts of right way green pepper, 20 parts of rattan green pepper, 44 parts of pericarpium zanthoxyli schinifolii, 16 parts of Chinese green prickly ash peel, 19 parts of Zanthoxylum bungeanum etc. 6
Kind, equally the kind of sample is numbered respectively with " 1 " ~ " 6 "；
(2) setting of instrument parameter
MPA type near infrared spectrometer of the near infrared spectrum data acquisition using German Brooker company production, spectra collection model
It encloses for 12500 ~ 3300 cm-1, PbS detector, attached integrating sphere and quartz sample pool.Spectra collection condition setting is suitably joined
Number, i.e. 8 cm of scanning resolution-1, scanning times 32, spectroscopic data is counted 2307 points, to Chinese prickly ash sample progress wave-number range
12500~3800 cm-1The scanning that diffuses；
(3) acquisition of near infrared spectrum
30 min of preheating that near infrared spectrometer is switched on are needed before spectral scan, to guarantee the stability of sample measurement.It was measuring
Cheng Zhong is kept for 25 DEG C of room temperature condition, 25 g is successively weighed from each sample and are fitted into quartz sample pool, using rotation
Scanning mode repeated acquisition three times, takes its averaged spectrum as the spectrum of the sample, and Fig. 2 is 205 parts of Chinese prickly ash sample near infrared lights
Spectrogram, building include 8 Chinese prickly ash place of production discriminating near infrared spectrum map libraries and 6 Chinese prickly ash Variety identification near infrared spectrum maps
Library；
(4) Pretreated spectra
Original near infrared spectrum not only contains the characteristic information of sample, and influence for instrument, external environment etc. is often
Random noise is contained, therefore is previously required to pre-process spectroscopic data establishing near-infrared analysis model.To eliminate light
The baseline drift and random noise of spectrum signal improve the forecasting accuracy and stability of model, use " wavelet transformation ", " one
Order derivative+Savitzky-Golay is smooth ", " second dervative+SavitzkyGolay is smooth " preprocess method；It is former to eliminate
The redundancy for including in beginning spectroscopic data protrudes the difference between sample spectrum signal, simplifies established near infrared spectrum mould
Type and improve model predictive ability and precision of prediction use " mean value centralization ", " minimax normalization " pretreatment side
Method；It is unevenly distributed caused scattering to eliminate sample granularity, it is pre- using " MSC ", " SNV " preprocess method progress spectrum
Processing；
(5) svm classifier prediction model is established
Using the near infrared spectrum data after Pretreated spectra as the input value of SVM model, the close of the Chinese prickly ash place of production and kind is established
Infrared spectroscopy identifies model.Widest RBF core is used for svm classifier model, a sample can be mapped to more higher-dimension by it
Space, it is thus necessary to determine that parameter it is also less.And for two parameters in RBF kernel function, punishment parametercAnd kernel functional parametergUsing punishment parameter in particle swarm algorithm (PSO) traversal setting rangecAnd kernel functional parametergCombination establish svm classifier mould
Type, and with the precision of test set sample computation model, finally select optimal parameter combination.Pass through continuous parameter optimization, flower
The PSO search parameter of green pepper place of production discriminating is specifically provided that c2=1.7, maximum changes when population maximum quantity is 30, c1=1.5
From generation to generation several 2000 when, the optimum combination of RBF kernel functional parameter (c, g) is (4.4515,0.067303)；And Chinese prickly ash Variety identification
PSO search parameter be specifically provided that when population maximum quantity 25, c1=1.4, c2=1.6, greatest iteration algebra 2000
When, the optimum combination of RBF kernel functional parameter (c, g) is (2.7179,0.0165560).Make under optimal parameter combination respectively
Identify model with the near infrared spectrum that SVM algorithm establishes the Chinese prickly ash place of production and kind, the accuracy rate of model is 100%.
Concrete operations are as follows: laboratory sample according to about 4:1 and 5:1 ratio, by the Chinese prickly ash sample of different sources and kind
It is divided into training set and test set two parts, training set is used for the foundation of near-infrared analysis model, and test set sample is for model
Verifying.Identification for the Chinese prickly ash place of production, 164 samples of training set establish SVM model, and 41 samples of test set are used to verify the mould
Type, and the identification of Chinese prickly ash kind, then training set 172, test set 33, and class label assignment is carried out to sample.It is built using SVM
Vertical qualitative discrimination model, it is necessary first to which solution is selection kernel function, is all made of Radial basis kernel function, this method to classification problem
Non-linear sample data can be mapped to high-dimensional feature space, also can handle the sample number with non-linear sample relationship
According to.Using PSO optimizing algorithm, radial base kernel functional parameter penalty parameter c, kernel functional parameter g are optimized, so that classifier
The test set data that can calculate to a nicety unknown.
Identification for the Chinese prickly ash place of production and kind uses 164 and 172 sample spectrum data of training set, 8 productions respectively
The class label that ground and 6 kinds assign, the optimal parameter (c, g) searched out using PSO is to SVM model is established, respectively using survey
Examination collection 41 and 33 samples are verified.The prediction result that svm classifier identifies model is as follows: the sample in 8 places of production of test set
It can be correctly validated with 100%, test set totally identifies accuracy 100%, and the sample standard deviation of 6 kinds of test set can be with 100%
It is correctly validated, it is 100% that test set, which totally identifies accuracy,.
In conclusion parameter optimization, under the premise of correct preference pattern parameter, SVM algorithm is to flower by model training
Green pepper sample training collection, the place of production of test set and assortment accuracy rate are attained by 100%.Finally, it is stated that above embodiments
It is only used to illustrate the technical scheme of the present invention and not to limit it, although being described the invention in detail referring to preferred embodiment,
Those skilled in the art should understand that can with modification or equivalent replacement of the technical solution of the present invention are made, without
It is detached from the objective and range of technical solution of the present invention, is intended to be within the scope of the claims of the invention.
Claims (5)
1. the near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm, it is characterised in that: according to 12500 ~
3300 cm-1Sample near infrared spectrum in wave-length coverage is established by combination supporting vector machine (SVM) algorithm and is based near infrared light
The Chinese prickly ash place of production of spectrum and the disaggregated model of kind；Then, punishment parameter is established using particle swarm algorithm (PSO)cJoin with kernel function
NumbergBest parameter group；By particle swarm algorithm available optimal punishment parameter and kernel functional parameter, most optimal sorting is established
Class model obtains the classification under SVM algorithm then by comparing the sample properties of actual sample attribute and disaggregated model prediction
Model prediction accuracy rate.
2. the near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm according to claim 1, feature
Be, algorithm content the following steps are included:
(1) SVM algorithm parameter is initialized, comprising: punishment parametercAnd kernel functional parameterg；
(2) according to the mathematical model of support vector machines (SVM), punishment parameter is established by particle swarm algorithm (PSO)cAnd kernel function
ParametergBest parameter group, wherein use most common Radial basis kernel function (radial basis in support vector machines
Function, RBF) method establish model；
(3) prediction model established using support vector machines (SVM) algorithm is imported the data of training set and forecast set sample, obtained
The predictablity rate of model out.
3. the near infrared prediction model in the Chinese prickly ash place of production and kind according to claim 1 based on SVM algorithm, special
Sign is, establishes model using support vector machines (SVM) algorithm.
4. the near infrared prediction model in the Chinese prickly ash place of production and kind according to claim 1 based on SVM algorithm, special
Sign is, various pretreatments is carried out by the near infrared light spectral curve to original Chinese prickly ash sample, under the best pretreatment of effect
Carry out the foundation of identification model.
5. the near infrared prediction model in the Chinese prickly ash place of production and kind according to claim 1 based on SVM algorithm, special
Sign is that particle swarm algorithm (PSO) establishes punishment parametercAnd kernel functional parametergBest parameter group is devised and is calculated based on SVM
The Chinese prickly ash place of production of method and the near infrared prediction model of kind.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910158130.0A CN109668859A (en) | 2019-03-03 | 2019-03-03 | The near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910158130.0A CN109668859A (en) | 2019-03-03 | 2019-03-03 | The near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109668859A true CN109668859A (en) | 2019-04-23 |
Family
ID=66151894
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910158130.0A Pending CN109668859A (en) | 2019-03-03 | 2019-03-03 | The near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109668859A (en) |
Cited By (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111398233A (en) * | 2020-04-07 | 2020-07-10 | 安徽理工大学 | Laser spectrum detection method for red wine quality |
| CN111398212A (en) * | 2020-04-08 | 2020-07-10 | 四川虹微技术有限公司 | Method for establishing pepper detection model based on portable near-infrared spectrometer |
| CN111488851A (en) * | 2020-04-17 | 2020-08-04 | 成都曙光光纤网络有限责任公司 | Traceability detection method, device, equipment and medium for fruit production place |
| CN111595802A (en) * | 2020-04-30 | 2020-08-28 | 珠海大横琴科技发展有限公司 | Construction method and application of Clinacanthus nutans seed source place classification model based on NIR (near infrared spectroscopy) |
| CN112697888A (en) * | 2019-10-22 | 2021-04-23 | 重庆德庄农产品开发有限公司 | Method for measuring capsaicin content |
| CN113033066A (en) * | 2021-04-07 | 2021-06-25 | 温州大学 | Method for establishing near infrared spectrum identification model of sargassum fusiforme production area, strain and cultivation mode and identification method |
| CN113191618A (en) * | 2021-04-25 | 2021-07-30 | 南京财经大学 | Millet producing area tracing method based on mid-infrared spectrum technology and feature extraction |
| CN113313157A (en) * | 2021-05-22 | 2021-08-27 | 福州大学 | Lotus root starch producing area distinguishing method based on machine learning |
| CN114720420A (en) * | 2022-03-24 | 2022-07-08 | 中国中医科学院中药研究所 | Method and system for identifying production area of Chinese prickly ash based on hyperspectral imaging technology |
| CN114881113A (en) * | 2022-04-01 | 2022-08-09 | 燕山大学 | Flame-retardant plastic classification method based on improved badger algorithm combined with near infrared spectrum |
| CN114994150A (en) * | 2022-05-31 | 2022-09-02 | 中国标准化研究院 | Electronic tongue rapid classification method for spicy degree of zanthoxylum schinifolium |
| CN115326739A (en) * | 2022-07-25 | 2022-11-11 | 五邑大学 | Method and device for predicting producing area of dried orange peel and storage medium |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907564A (en) * | 2010-06-24 | 2010-12-08 | 江苏大学 | Rapeseed quality non-destructive testing method and device based on near infrared spectrum technology |
| CN102393376A (en) * | 2011-10-14 | 2012-03-28 | 上海海洋大学 | Support vector regression-based near infrared spectroscopy for detecting content of multiple components of fish ball |
| CN103235095A (en) * | 2013-04-18 | 2013-08-07 | 北京工商大学 | Water-injected meat detection method and device |
| CN105866063A (en) * | 2016-04-08 | 2016-08-17 | 北京工商大学 | Detection method for quality grade of sausage |
| KR20180122955A (en) * | 2017-05-04 | 2018-11-14 | 비아비 솔루션즈 아이엔씨. | Endpoint detection in manufacturing process by near infrared spectroscopy and machine learning techniques |
-
2019
- 2019-03-03 CN CN201910158130.0A patent/CN109668859A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101907564A (en) * | 2010-06-24 | 2010-12-08 | 江苏大学 | Rapeseed quality non-destructive testing method and device based on near infrared spectrum technology |
| CN102393376A (en) * | 2011-10-14 | 2012-03-28 | 上海海洋大学 | Support vector regression-based near infrared spectroscopy for detecting content of multiple components of fish ball |
| CN103235095A (en) * | 2013-04-18 | 2013-08-07 | 北京工商大学 | Water-injected meat detection method and device |
| CN105866063A (en) * | 2016-04-08 | 2016-08-17 | 北京工商大学 | Detection method for quality grade of sausage |
| KR20180122955A (en) * | 2017-05-04 | 2018-11-14 | 비아비 솔루션즈 아이엔씨. | Endpoint detection in manufacturing process by near infrared spectroscopy and machine learning techniques |
Non-Patent Citations (1)
| Title |
|---|
| 吴习宇: ""花椒产地、新陈度及掺伪的近红外光谱鉴别方法研究"", 《中国博士学位论文全文数据库》 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112697888A (en) * | 2019-10-22 | 2021-04-23 | 重庆德庄农产品开发有限公司 | Method for measuring capsaicin content |
| CN111398233A (en) * | 2020-04-07 | 2020-07-10 | 安徽理工大学 | Laser spectrum detection method for red wine quality |
| CN111398212A (en) * | 2020-04-08 | 2020-07-10 | 四川虹微技术有限公司 | Method for establishing pepper detection model based on portable near-infrared spectrometer |
| CN111488851A (en) * | 2020-04-17 | 2020-08-04 | 成都曙光光纤网络有限责任公司 | Traceability detection method, device, equipment and medium for fruit production place |
| CN111595802A (en) * | 2020-04-30 | 2020-08-28 | 珠海大横琴科技发展有限公司 | Construction method and application of Clinacanthus nutans seed source place classification model based on NIR (near infrared spectroscopy) |
| CN113033066A (en) * | 2021-04-07 | 2021-06-25 | 温州大学 | Method for establishing near infrared spectrum identification model of sargassum fusiforme production area, strain and cultivation mode and identification method |
| CN113191618A (en) * | 2021-04-25 | 2021-07-30 | 南京财经大学 | Millet producing area tracing method based on mid-infrared spectrum technology and feature extraction |
| CN113313157A (en) * | 2021-05-22 | 2021-08-27 | 福州大学 | Lotus root starch producing area distinguishing method based on machine learning |
| CN114720420A (en) * | 2022-03-24 | 2022-07-08 | 中国中医科学院中药研究所 | Method and system for identifying production area of Chinese prickly ash based on hyperspectral imaging technology |
| CN114881113A (en) * | 2022-04-01 | 2022-08-09 | 燕山大学 | Flame-retardant plastic classification method based on improved badger algorithm combined with near infrared spectrum |
| CN114994150A (en) * | 2022-05-31 | 2022-09-02 | 中国标准化研究院 | Electronic tongue rapid classification method for spicy degree of zanthoxylum schinifolium |
| CN114994150B (en) * | 2022-05-31 | 2023-10-27 | 中国标准化研究院 | Electronic tongue rapid classification method for redpepper tingling degree |
| CN115326739A (en) * | 2022-07-25 | 2022-11-11 | 五邑大学 | Method and device for predicting producing area of dried orange peel and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109668859A (en) | The near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm | |
| CN102879353B (en) | The method of content of protein components near infrared detection peanut | |
| Chen et al. | Discrimination of Ganoderma lucidum according to geographical origin with near infrared diffuse reflectance spectroscopy and pattern recognition techniques | |
| CN102590129B (en) | Method for detecting content of amino acid in peanuts by near infrared method | |
| CN105486655B (en) | The soil organism rapid detection method of model is intelligently identified based on infrared spectroscopy | |
| CN104849232B (en) | A kind of method of quick detection royal jelly moisture and protein content | |
| CN109799207A (en) | The quantitative detecting method of talcum powder is mixed in the root of Dahurain angelica based on near-infrared spectrum analysis | |
| CN106841083A (en) | Sesame oil quality detecting method based on near-infrared spectrum technique | |
| CN109669023A (en) | A kind of soil attribute prediction technique based on Multi-sensor Fusion | |
| CN105044022B (en) | A kind of method and application based on near-infrared spectrum technique Fast nondestructive evaluation wheat hardness | |
| CN106770003A (en) | Wood Identification Method and system based on near-infrared spectrum technique | |
| CN106950192A (en) | A kind of method of Contents of Main Components quick detection in vegetable protein beverage based on near-infrared spectral analysis technology | |
| CN106198447A (en) | Chemical Mixed Fertilizer main component harmless quantitative detection method based on near-infrared spectrum technique | |
| CN103411895B (en) | Pseudo-near infrared spectrum identification method mixed by pearl powder | |
| CN109738380A (en) | A kind of high-spectrum remote-sensing judgment method of soil salinization degree | |
| CN109142263A (en) | A kind of component dispersing uniformity on-line testing method of solid propellant preparation process | |
| CN107421912A (en) | A kind of apparatus and method of the liquid diary product quality testing based on near-infrared transmission technology | |
| CN109187443A (en) | Water body bacterial micro-organism based on multi-wavelength transmitted spectrum accurately identifies method | |
| CN106053383A (en) | Near-infrared online detection method for tobacco processing process | |
| CN106950186A (en) | Countryside Egg or foreign egg kind detection means and its method based on fiber spectrum | |
| Chen et al. | Rapid identification of three varieties of Chrysanthemum with near infrared spectroscopy | |
| CN103760130B (en) | The method of Tween-80 content near infrared ray compound Moschus injection | |
| CN110210005A (en) | A kind of spectrum wave number selection method of no reference value | |
| CN106872398A (en) | A kind of HMX explosives moisture method for fast measuring | |
| CN113092403B (en) | Terahertz spectrum qualitative detection method for textile material of school uniform for students |
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: 20190423 |