CN106596453A - Method for discriminating wild and cultured sea bass based on near infrared spectroscopy technology - Google Patents
Method for discriminating wild and cultured sea bass based on near infrared spectroscopy technology Download PDFInfo
- Publication number
- CN106596453A CN106596453A CN201611165236.6A CN201611165236A CN106596453A CN 106596453 A CN106596453 A CN 106596453A CN 201611165236 A CN201611165236 A CN 201611165236A CN 106596453 A CN106596453 A CN 106596453A
- Authority
- CN
- China
- Prior art keywords
- spectrum
- wild
- sample
- fiss
- cultivation
- 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
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000005516 engineering process Methods 0.000 title abstract description 10
- 238000004497 NIR spectroscopy Methods 0.000 title abstract description 4
- 241000723298 Dicentrarchus labrax Species 0.000 title abstract 4
- 238000001228 spectrum Methods 0.000 claims abstract description 35
- 238000007781 pre-processing Methods 0.000 claims abstract description 10
- 238000005457 optimization Methods 0.000 claims abstract description 9
- 238000002329 infrared spectrum Methods 0.000 claims description 11
- 235000013372 meat Nutrition 0.000 claims description 9
- 230000003595 spectral effect Effects 0.000 claims description 9
- 238000000513 principal component analysis Methods 0.000 claims description 8
- 238000012937 correction Methods 0.000 claims description 6
- 239000002245 particle Substances 0.000 claims description 6
- 210000001835 viscera Anatomy 0.000 claims description 6
- 239000000470 constituent Substances 0.000 claims description 5
- 238000012360 testing method Methods 0.000 claims description 5
- 238000005033 Fourier transform infrared spectroscopy Methods 0.000 claims description 4
- 238000002835 absorbance Methods 0.000 claims description 4
- 238000006243 chemical reaction Methods 0.000 claims description 4
- 230000002068 genetic effect Effects 0.000 claims description 4
- 238000004611 spectroscopical analysis Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 238000013519 translation Methods 0.000 claims description 3
- 238000002790 cross-validation Methods 0.000 claims description 2
- 238000013144 data compression Methods 0.000 claims description 2
- 238000009795 derivation Methods 0.000 claims description 2
- 238000009826 distribution Methods 0.000 claims description 2
- 238000000605 extraction Methods 0.000 claims description 2
- 238000012417 linear regression Methods 0.000 claims description 2
- 238000002203 pretreatment Methods 0.000 claims description 2
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000011835 investigation Methods 0.000 abstract description 2
- 238000010276 construction Methods 0.000 abstract 1
- 241000269795 Lateolabrax japonicus Species 0.000 description 8
- 241000251468 Actinopterygii Species 0.000 description 7
- 240000004542 Capparis mitchellii Species 0.000 description 4
- 241000321429 Epinephelus itajara Species 0.000 description 4
- 235000004098 Prunus caroliniana Nutrition 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000011109 contamination Methods 0.000 description 3
- 238000010183 spectrum analysis Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 241000269799 Perca fluviatilis Species 0.000 description 2
- 241000656145 Thyrsites atun Species 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 239000008280 blood Substances 0.000 description 2
- 210000004369 blood Anatomy 0.000 description 2
- 210000005252 bulbus oculi Anatomy 0.000 description 2
- 229910052799 carbon Inorganic materials 0.000 description 2
- 210000004087 cornea Anatomy 0.000 description 2
- 238000001514 detection method Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 235000013305 food Nutrition 0.000 description 2
- 239000000203 mixture Substances 0.000 description 2
- 210000003097 mucus Anatomy 0.000 description 2
- 229910052757 nitrogen Inorganic materials 0.000 description 2
- 235000014593 oils and fats Nutrition 0.000 description 2
- 229910052760 oxygen Inorganic materials 0.000 description 2
- 210000000952 spleen Anatomy 0.000 description 2
- 229910052717 sulfur Inorganic materials 0.000 description 2
- 239000003643 water by type Substances 0.000 description 2
- 206010000087 Abdominal pain upper Diseases 0.000 description 1
- 206010006100 Bradykinesia Diseases 0.000 description 1
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 1
- 244000025254 Cannabis sativa Species 0.000 description 1
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 1
- 241001463995 Ctenoides Species 0.000 description 1
- 241000238557 Decapoda Species 0.000 description 1
- 206010012735 Diarrhoea Diseases 0.000 description 1
- 101100117236 Drosophila melanogaster speck gene Proteins 0.000 description 1
- 241000196324 Embryophyta Species 0.000 description 1
- 208000006083 Hypokinesia Diseases 0.000 description 1
- 208000015817 Infant Nutrition disease Diseases 0.000 description 1
- 208000019395 Lactation disease Diseases 0.000 description 1
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 description 1
- 201000005702 Pertussis Diseases 0.000 description 1
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 1
- 206010042576 Suppressed lactation Diseases 0.000 description 1
- 229930003270 Vitamin B Natural products 0.000 description 1
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 1
- 230000003187 abdominal effect Effects 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 230000037396 body weight Effects 0.000 description 1
- 229910052791 calcium Inorganic materials 0.000 description 1
- 239000011575 calcium Substances 0.000 description 1
- 238000009614 chemical analysis method Methods 0.000 description 1
- 230000001684 chronic effect Effects 0.000 description 1
- 229910052802 copper Inorganic materials 0.000 description 1
- 239000010949 copper Substances 0.000 description 1
- 230000002950 deficient Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 201000006549 dyspepsia Diseases 0.000 description 1
- 235000019197 fats Nutrition 0.000 description 1
- 230000001605 fetal effect Effects 0.000 description 1
- 239000000835 fiber Substances 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 230000005283 ground state Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000000366 juvenile effect Effects 0.000 description 1
- 229910052749 magnesium Inorganic materials 0.000 description 1
- 239000011777 magnesium Substances 0.000 description 1
- 238000012423 maintenance Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 239000008239 natural water Substances 0.000 description 1
- 210000000653 nervous system Anatomy 0.000 description 1
- 235000015097 nutrients Nutrition 0.000 description 1
- 230000000050 nutritive effect Effects 0.000 description 1
- 150000002894 organic compounds Chemical class 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 102000004169 proteins and genes Human genes 0.000 description 1
- 238000007634 remodeling Methods 0.000 description 1
- 239000004576 sand Substances 0.000 description 1
- 229910052711 selenium Inorganic materials 0.000 description 1
- 239000011669 selenium Substances 0.000 description 1
- 241000894007 species Species 0.000 description 1
- 230000007704 transition Effects 0.000 description 1
- 235000019156 vitamin B Nutrition 0.000 description 1
- 239000011720 vitamin B Substances 0.000 description 1
- 238000009941 weaving Methods 0.000 description 1
- 239000011701 zinc Substances 0.000 description 1
- 229910052725 zinc Inorganic materials 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
- G01N21/3563—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
-
- 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
- G01N2021/3595—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using FTIR
Landscapes
- Physics & Mathematics (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention discloses a method for discriminating wild and cultured sea bass based on a near infrared spectroscopy technology. The method comprises the following steps: 1, sample preprocessing; 2, atlas acquisition; 3, spectrum preprocessing; 4, main component analysis; 5, libsvm options parameter optimization; and 6, model construction. A wild and cultured sea bass discriminating model is established through combining the near infrared spectroscopy technology with a chemometrics technology. Methodological investigation shows that the method has the advantages of good repeatability, strong stability, model requirement meeting, rapidness, good accuracy, no pollution, and high wild and cultured sea bass discriminating accuracy reaching 100%.
Description
Technical field
The present invention relates to one kind is based on, near-infrared spectrum technique is quick, accurate, free of contamination discriminating is wild and cultivates jewfish
The method of fish, belongs to technical field of food detection.
Background technology
Orange rock-fiss, scientific name day reality perch, also known as Lateolabrax japonicus, seven-star perch etc..Orange rock-fiss natural disposition is violent, and juvenile fish eats shrimp and fry,
Adult fish ichthyophagy.Orange rock-fiss is all distributed in Pacific Ocean waters and Atlantic waters, wherein the sea of Japan in Asia, the Huanghai Sea, the Bohai Sea, beautiful
The Peru fishing ground of the West Coast and South America of state, the ground such as the North Sea fishing ground of Britain and Mediterranean are the main places of production.
Orange rock-fiss build is slightly grown, and back is slightly swelled, mouth end position, and lower chin is slightly beyond upper chin.Preopercle trailing edge has
Sawtooth, body is by little ctenoid scale, body back cinerouss, both sides and abdominal part silvery white.Irregular black speck, general height are arranged at side top
110-120cm, body weight 15-18kg.
The cheek of orange rock-fiss, meat can all be used as medicine, and can be used to treat infantile pertussis, chronic gastralgia, diarrhea due to hypofunction of the spleen, children's infantile malnutrition
Product, dyspepsia, the disease such as become thin;Containing nutrients such as abundant copper, calcium, magnesium, zinc, selenium in Lateolabrax japonicus (Cuvier et Va-lenciennes) (Lateolabracis) blood, with protection
The effects such as heart, maintenance nervous system, slow down aging, life lengthening;Orange rock-fiss rich in proteins, A, vitamin B group and fiber
Deng can control frequent fetal movement, produce the disease such as hypogalactia, be body-building is enriched blood, invigorating the spleen and benefiting QI and beneficial body are safe and comfortable good merchantable brand.
, due to living in natural water, range of activity is wide for wild orange rock-fiss, and space of looking for food is big, thus build is tall and thin, squama
Piece is thin, gloss is bright, few internal organs oils and fatss, fine and tender taste, delicious flavour;And cultivate fish and live in net cage, range of activity is little, trip
Dynamic speed is slow, bradykinesia, because it is edible feed feedstuff make that its speed of growth quickening, adult fish cycle time, internal organs oils and fatss be more, body
Type is more fat, scale is thick, matt, meat is rougher, have dense mud fishy smell.In recent years, due to overfishing and marine pollution
Etc. reason, coastal ocean fishery resources are progressively deficient, and wild jewfish fish crop cannot meet consumption demand.At present, on market
A big chunk orange rock-fiss is cage culture, and wild and cultivation orange rock-fiss has larger difference in organoleptic quality and nutritive value
It is different, also differ greatly in price.Some retailers pretend to be wild orange rock-fiss to sell by orange rock-fiss is cultivated, and compromise the power of consumer
Benefit, it is therefore necessary to set up it is a kind of quick and precisely differentiate it is wild and cultivation orange rock-fiss method.
Near-infrared spectral analysis technology has been widely used in agricultural, weaving, system as a kind of quick modern analytical technique
The fields such as medicine, petrochemical industry.Near infrared spectrum makes molecular vibration from ground state to height mainly due to the anharmonicity of molecular vibration
Produce during energy state transitions, record be single chemical bond in molecule fundamental vibration sum of fundamental frequencies and frequency multiplication information, it usually receives
The overlap of the sum of fundamental frequencies and frequency multiplication of hydric group X-H (X is C, N, O, S) is dominated, wherein containing most of type organic compound
Composition and molecular structure information.There are certain functional relationship, Jing between near infrared spectrum and the composition and structure of sample
Overcorrect, it is possible to according to the near infrared spectrum of sample, quickly calculate the chemical substance containing X-H (X is C, N, O, S)
Species and content.Near infrared spectroscopy is a kind of quick, accurate, free of contamination detection method, with Chemical Measurement modeling side
Method combines, and can be used for wild and cultivation orange rock-fiss discriminating.
The content of the invention
The technical problem to be solved is:A kind of quick, accurate, free of contamination discriminating of offer is wild and cultivation is extra large
The method of Lateolabrax japonicus (Cuvier et Va-lenciennes) (Lateolabracis).
To solve above-mentioned technical problem, the technical solution used in the present invention is:
(1) pre-treatment of sample:Respectively wild and cultivation orange rock-fiss is scaled, removes the peel, removes internal organs, meat is adopted along back, used
Meat grinder is rubbed and is mixed, and is loaded in culture dish, is gently compacted exclude the bubble of culture dish bottom.
(2) collection of illustrative plates collection:Using Fourier transform infrared spectrometer, it is 10000~4000cm to arrange scanning wave-number range-1, scanning times 64, resolution 8cm-1, 3 spectrum of each sample repeated acquisition take average spectrum as primary light spectrogram, structure
Build wild and cultivation orange rock-fiss near infrared spectrum picture library.
(3) Pretreated spectra:Preprocessing procedures include untreated, multiplicative scatter correction (MSC), standard normal variable
Conversion (SNV), first derivative (FD), second dervative (SD), it is smooth in one or more, select optimum Pretreated spectra side
Method.
(4) principal component analysiss:Pretreated spectroscopic data is carried out into principal component analysiss, obtaining for front 10 main constituents is chosen
Input of the score value as support vector machine.
(5) libsvm options parameter optimizations:Using the net under validation-cross (cross validation, CV) meaning
Lattice search (grid search), genetic algorithm (genetic algorithm, GA), particle swarm optimization algorithm (particle
Swarm optimization, PSO) find optimal parameter c and g.
(6) structure of model:, used as training set, remaining 1/3rd used as forecast set for 2/3rds of selection sample number.
Near-infrared spectrum technique involved by such scheme is used for the qualitative analyses of sample, with conventional chemical analysis method
Difference, it is a kind of indirect analyses technology, is fully to excavate spectrum and tested sample quality parameter by chemometrics method
Between dependency, both qualitative relationships are set up with this, that is, set up polytomy variable calibration model;After model is built up, only need by
In the near infrared spectrum data information input model of unknown sample, it is possible to the kind of information of fast prediction sample.
Preprocessing procedures in the step (3) are comprised the concrete steps that:
(1) multiplicative scatter correction (MSC) is to eliminate test sample because of size and the uneven generation of distribution of particles
Scattering affect, the specific algorithm of MSC is as follows:
A. calculate averaged spectrum:
B. linear regression is made to averaged spectrum:
C. MSC corrections are made to each spectrum:
In formula, XiRepresent the spectroscopic data of i-th sample;Represent averaged spectrum;miRepresent XiWithSlope;biTable
Show intercept;
(2) standard normal variable conversion (SNV) between correcting sample because of spectral error that scattering causes:
In formula:X represents sample spectra value,Averaged spectrum is represented, std (x) represents spectral standard deviation;
(3) derivative algorithm is used for the impact for eliminating needle position misalignment or gentle ambient interferences, and wherein first derivative (FD) is used for
Baseline translation is eliminated, second dervative (SD) can eliminate translation and linear tilt simultaneously;The near infrared light few for wavelength sampled point
Spectrum, is calculated by Savitzky-Golay convolution method of derivation;
In formula, x is the spectral absorbance before differentiating, and g is derivative window width, and X is the spectral absorbance after differentiating;
(4) it is that, using Savitzky-Golay methods, it is to set up filter function using least square fitting coefficient, is to smooth
Polynomial least mean square fitting is carried out to the spectrum in moving section, it is also possible to it is thought that a kind of Weighted Average Algorithm.
Preferably, the selection of step (3), (5) optimum preprocessing procedures and optimal parameter is by establishing
What disaggregated model was determined to the classification accuracy rate of forecast set.Further, the optimum Pretreated spectra side for adopting in the present invention
Method is standard normal variable conversion (SNV) and second dervative (SD).
Preferably, step (4) principal component analysiss are mainly used in data compression and the extraction of characteristic information, select rational
Main constituent component, not only can avoid data redundancy, and will not lose spectral information.
As an instantiation, using 19 wild Lateolabrax japonicus (Cuvier et Va-lenciennes) (Lateolabracis) and 18 cultivation Lateolabrax japonicus (Cuvier et Va-lenciennes) (Lateolabracis) as training set in step (6), 9
Wild Lateolabrax japonicus (Cuvier et Va-lenciennes) (Lateolabracis) and 7 cultivation Lateolabrax japonicus (Cuvier et Va-lenciennes) (Lateolabracis) carry out differentiation checking as forecast set, set up wild and cultivation orange rock-fiss svm classifier mould
Type.
The invention has the beneficial effects as follows:
(1) present invention establishes wild and cultivation jewfish with reference to chemometrics method using near-infrared spectral analysis technology
The discriminating model of fish, deemed-to-satisfy4 investigation show that the method is reproducible, and stability is strong, meets the requirement of model.
(2) the method is quick, accurate, pollution-free, is up to 100% to wild and cultivation orange rock-fiss discriminating accuracy.
Description of the drawings
Below in conjunction with the accompanying drawings the specific embodiment of the present invention is described in further detail.
Fig. 1 is wild and cultivates the near-infrared primary light spectrogram of orange rock-fiss.
Fig. 2 is wild and cultivates the spectrogram after orange rock-fiss Jing SNV+SD pretreatment.
Fitness curves of the Fig. 3 using PSO parameters optimization.Wherein, parameter c1=1.5, c2=1.7, termination algebraically=
200, population quantity pop=20.
Fig. 4 test set classification results figures.
Specific embodiment
Embodiment 1
Wild orange rock-fiss in the present embodiment is collected in Qingdao City's Laoshan District sand mouth harbour, and cultivation orange rock-fiss is collected in green grass or young crops
Island city Jiangnan Lingshan Island individuality raiser.Selected sample body surface is rich in that gloss, the cheek be transparent in cerise, mucus, eyeball is full
Full, cornea is clear.
The sample of collection is scaled, removes the peel, removes internal organs, meat is adopted along back, rubbed with meat grinder and mixed, load culture dish
In, gently it is compacted exclude the bubble of culture dish bottom.
(German Bruker is public for Bruker Tensor27 Fourier transform infrared spectrometer for the instrument that the present embodiment is adopted
Department), the instrument is furnished with near-infrared integrating sphere accessory (Pike companies of the U.S.);Signals collecting software is OPUS7.0.
Spectra collection parameter setting:Scanning 10000~4000cm of wave-number range-1, scanning times 64, resolution 8cm-1, often
3 spectrum of individual sample repeated acquisition.Average spectrum is taken as primary light spectrogram.
Take 28 wild orange rock-fisses and 25 cultivate orange rock-fiss totally 53 samples.Measured primary light spectrogram such as Fig. 1 institutes
Show.19 wild samples and 18 cultivation samples have been randomly selected as training set, 9 wild samples of residue and 7 cultivation samples
This is used as forecast set.
Through comparison draw optimum preprocessing procedures be SNV+SD, the spectrogram after pretreatment as shown in Fig. 2
Pretreated spectrum is carried out into principal component analysiss, front 10 principal component scores values is chosen as the input of support vector machine;Jing
PSO parameters optimization, show that optimal penalty parameter c is 34.1822, and optimal kernel functional parameter g is 0.13228, such as Fig. 3;Gained SVM
Model to the classification accuracy rate of test set up to 100%, test set classification results figure such as Fig. 4.
Near-infrared spectral analysis technology can realize wild and cultivation jewfish with precise and high efficiency with reference to chemometrics method
The discriminating of fish.
Embodiment 2
Wild and cultivation Lateolabrax japonicus (Cuvier et Va-lenciennes) (Lateolabracis) in the present embodiment is collected in Qingdao City's Ji meter precipices harbour and one plant of Jiangnan each 5 respectively
Bar, selected sample body surface be rich in gloss, the cheek in cerise, mucus is transparent, eyeball is full, cornea is clear.
The sample of collection is scaled, removes the peel, removes internal organs, meat is adopted along back, rubbed with meat grinder and mixed, load culture dish
In, gently it is compacted exclude the bubble of culture dish bottom.
(German Bruker is public for Bruker Tensor27 Fourier transform infrared spectrometer for the instrument that the present embodiment is adopted
Department), the instrument is furnished with near-infrared integrating sphere accessory (Pike companies of the U.S.);Signals collecting software is OPUS7.0.
Spectra collection parameter setting:Scanning 10000~4000cm of wave-number range-1, scanning times 64, resolution 8cm-1, often
3 spectrum of individual sample repeated acquisition.Average spectrum is taken as primary light spectrogram.
SNV+SD Pretreated spectras are carried out to original spectrum, pretreated spectrum is carried out into principal component analysiss, by front 10
Individual main constituent is input to the model of foundation, obtains prediction label, and 10 sample standard deviations differentiate correct.
The above, is only presently preferred embodiments of the present invention, is not the restriction for making other forms to the present invention, is appointed
What those skilled in the art possibly also with the disclosure above technology contents changed or be modified as equivalent variations etc.
Effect embodiment.But it is every without departing from technical solution of the present invention content, according to the technical spirit of the present invention to above example institute
Any simple modification, equivalent variations and the remodeling made, still falls within the protection domain of technical solution of the present invention.
Claims (5)
1. it is a kind of that wild and cultivation orange rock-fiss method is differentiated based on near-infrared spectrum technique, it is characterised in that methods described bag
Include following steps:
(1) pre-treatment of sample:Respectively wild and cultivation orange rock-fiss is scaled, removes the peel, removes internal organs, meat is adopted along back, use Minced Steak
Machine is rubbed and is mixed, and is loaded in culture dish, is gently compacted exclude the bubble of culture dish bottom;
(2) collection of illustrative plates collection:Using Fourier transform infrared spectrometer, it is 10000~4000cm to arrange scanning wave-number range-1, sweep
Retouch number of times 64, resolution 8cm-1, 3 spectrum of each sample repeated acquisition take average spectrum as primary light spectrogram, build wild
With the near infrared spectrum picture library of cultivation orange rock-fiss;
(3) Pretreated spectra:Preprocessing procedures are converted selected from untreated, multiplicative scatter correction (MSC), standard normal variable
(SNV), first derivative (FD), second dervative (SD), it is smooth in one or more;
(4) principal component analysiss:Pretreated spectroscopic data is carried out into principal component analysiss, the score value of front 10 main constituents is chosen
As the input of support vector machine;
(5) libsvm options parameter optimizations:Searched using the grid under validation-cross (cross validation, CV) meaning
Seek (grid search), genetic algorithm (genetic algorithm, GA), particle swarm optimization algorithm (particle swarm
Optimization, PSO) find optimal parameter c and g;
(6) structure of model:Used as training set, remaining 1/3rd are sentenced 2/3rds of selection sample number as forecast set
Do not verify, set up wild and cultivation orange rock-fiss svm classifier model.
2. the method described in claim 1, it is characterised in that:Preprocessing procedures in the step (3) are comprised the concrete steps that:
(1) multiplicative scatter correction (MSC) is to eliminate test sample dissipating because of size and the uneven generation of distribution of particles
Projection is rung, and the specific algorithm of MSC is as follows:
A. calculate averaged spectrum:
B. linear regression is made to averaged spectrum:
C. MSC corrections are made to each spectrum:
In formula, XiRepresent the spectroscopic data of i-th sample;Represent averaged spectrum;miRepresent XiWithSlope;biRepresent and cut
Away from;
(2) standard normal variable conversion (SNV) between correcting sample because of spectral error that scattering causes:
In formula:X represents sample spectra value,Averaged spectrum is represented, std (x) represents spectral standard deviation;
(3) derivative algorithm is used to eliminating the impact of needle position misalignment or gentle ambient interferences, and wherein first derivative (FD) is for eliminating
Baseline is translated, and second dervative (SD) can eliminate translation and linear tilt simultaneously;The near infrared spectrum few for wavelength sampled point, leads to
Cross the calculating of Savitzky-Golay convolution method of derivation;
In formula, x is the spectral absorbance before differentiating, and g is derivative window width, and X is the spectral absorbance after differentiating;
(4) it is that, using Savitzky-Golay methods, it is to set up filter function using least square fitting coefficient to smooth, and is to moving
Spectrum in dynamic interval carries out polynomial least mean square fitting.
3. the method described in claim 1, it is characterised in that:The step (3), (5) preprocessing procedures and optimal parameter
Selection be determining by the disaggregated model for establishing to the classification accuracy rate of forecast set.
4. the method described in claim 1, it is characterised in that:The preprocessing procedures that the step (3) adopts be standard just
State variable converts (SNV) and second dervative (SD).
5. the method described in claim 1, it is characterised in that:Step (4) principal component analysiss are used for data compression and feature
The extraction of information, selects rational main constituent component.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611165236.6A CN106596453A (en) | 2016-12-16 | 2016-12-16 | Method for discriminating wild and cultured sea bass based on near infrared spectroscopy technology |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201611165236.6A CN106596453A (en) | 2016-12-16 | 2016-12-16 | Method for discriminating wild and cultured sea bass based on near infrared spectroscopy technology |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106596453A true CN106596453A (en) | 2017-04-26 |
Family
ID=58801720
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201611165236.6A Pending CN106596453A (en) | 2016-12-16 | 2016-12-16 | Method for discriminating wild and cultured sea bass based on near infrared spectroscopy technology |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106596453A (en) |
Cited By (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107094689A (en) * | 2017-06-22 | 2017-08-29 | 广西红树林研究中心 | A kind of method for the fresh and alive Bostrichthys sinensis for differentiating separate sources |
CN107220625A (en) * | 2017-06-01 | 2017-09-29 | 中国海洋大学 | A kind of LIBS spectrum automatic recognition classification methods to sample |
CN108717497A (en) * | 2018-05-23 | 2018-10-30 | 大连海事大学 | Imitative stichopus japonicus place of production discrimination method based on PCA-SVM |
CN109001146A (en) * | 2018-07-26 | 2018-12-14 | 江苏大学 | A kind of method for quick identification of chilled beef and the fresh beef of jellyization |
CN109142269A (en) * | 2018-07-26 | 2019-01-04 | 江苏大学 | A kind of method for quick identification of chilled beef difference storage time |
CN109211830A (en) * | 2018-08-01 | 2019-01-15 | 嘉兴市皮毛和制鞋工业研究所 | A kind of method of principal component analysis and the easily mixed fur of multicategory discriminant combination identification |
CN109765196A (en) * | 2019-02-20 | 2019-05-17 | 江苏大学 | A kind of method for quick identification of atlantic salmon and rainbow trout |
CN109765197A (en) * | 2019-02-20 | 2019-05-17 | 江苏大学 | A kind of method for quick identification of chilled atlantic salmon and freeze thawing atlantic salmon |
CN111191488A (en) * | 2018-11-15 | 2020-05-22 | 中国电信股份有限公司 | Living body detection method, living body detection device, living body detection system, and computer-readable storage medium |
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 |
-
2016
- 2016-12-16 CN CN201611165236.6A patent/CN106596453A/en active Pending
Non-Patent Citations (4)
Title |
---|
MATTEO OTTAVIAN ET AL.: "Use of Near-Infrared Spectroscopy for Fast Fraud Detection in Seafood: Application to the Authentication of Wild European Sea Bass(Dicentrarchus labrax)", 《JOURNAL OF AGRICULTURE AND FOOD CHEMISTRY》 * |
尚廷义 等: "《基于光谱技术的寒地水稻稻瘟病害分析及机理研究》", 30 June 2016, 哈尔滨工程大学出版社 * |
张晓敏: "近红外光谱技术快速评估鲈鱼新鲜度的方法研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅰ辑》 * |
郭小溪 等: "水产品产地溯源技术研究进展", 《食品科学》 * |
Cited By (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107220625A (en) * | 2017-06-01 | 2017-09-29 | 中国海洋大学 | A kind of LIBS spectrum automatic recognition classification methods to sample |
CN107094689A (en) * | 2017-06-22 | 2017-08-29 | 广西红树林研究中心 | A kind of method for the fresh and alive Bostrichthys sinensis for differentiating separate sources |
CN107094689B (en) * | 2017-06-22 | 2019-05-14 | 广西红树林研究中心 | A method of identifying the fresh and alive Bostrichthys sinensis of separate sources |
CN108717497A (en) * | 2018-05-23 | 2018-10-30 | 大连海事大学 | Imitative stichopus japonicus place of production discrimination method based on PCA-SVM |
CN109001146A (en) * | 2018-07-26 | 2018-12-14 | 江苏大学 | A kind of method for quick identification of chilled beef and the fresh beef of jellyization |
CN109142269A (en) * | 2018-07-26 | 2019-01-04 | 江苏大学 | A kind of method for quick identification of chilled beef difference storage time |
CN109211830A (en) * | 2018-08-01 | 2019-01-15 | 嘉兴市皮毛和制鞋工业研究所 | A kind of method of principal component analysis and the easily mixed fur of multicategory discriminant combination identification |
CN111191488A (en) * | 2018-11-15 | 2020-05-22 | 中国电信股份有限公司 | Living body detection method, living body detection device, living body detection system, and computer-readable storage medium |
CN111191488B (en) * | 2018-11-15 | 2023-06-27 | 中国电信股份有限公司 | Living body detection method, device, system and computer readable storage medium |
CN109765196A (en) * | 2019-02-20 | 2019-05-17 | 江苏大学 | A kind of method for quick identification of atlantic salmon and rainbow trout |
CN109765197A (en) * | 2019-02-20 | 2019-05-17 | 江苏大学 | A kind of method for quick identification of chilled atlantic salmon and freeze thawing atlantic salmon |
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 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN106596453A (en) | Method for discriminating wild and cultured sea bass based on near infrared spectroscopy technology | |
Li et al. | Authentication of fishery and aquaculture products by multi-element and stable isotope analysis | |
CN107228924B (en) | A kind of adequate proteins processing peanut raw material quality determination and its evaluation method | |
CN108519339B (en) | WT-L SSVR-based leaf cadmium content Vis-NIR spectral feature modeling method | |
CN103954734B (en) | A kind of mensuration of lichee quality of suitable fruit juice production and evaluation method | |
CN103300221B (en) | Favorite forage grass of Qinling Mountain forest musk deer and collecting time of favorite forage grass | |
Niquil et al. | 9.07–inverse modeling in modern ecology and application to coastal ecosystems | |
CN109325626A (en) | Method based on apple feedstock specifications prediction dried product integrated quality | |
CN110646407A (en) | Method for rapidly detecting content of phosphorus element in aquatic product based on laser-induced breakdown spectroscopy technology | |
CN104199027A (en) | Method for realizing large-area near real-time monitoring on phenological period of rice based on compactly polarimetric radar | |
CN110954499B (en) | Mixed identification method and system for producing areas of imported salmon | |
CN113033066A (en) | Method for establishing near infrared spectrum identification model of sargassum fusiforme production area, strain and cultivation mode and identification method | |
Feng et al. | A hyperspectral imaging system for an accurate prediction of the above-ground biomass of individual rice plants | |
CN107024445A (en) | The modeling method and detection method of the quick detection of Nitrate in Vegetable | |
CN110487746A (en) | A method of baby cabbage quality is detected based near infrared spectrum | |
Xu et al. | Near‐infrared spectroscopy combined with multivariate calibration to predict the yield of sesame oil produced by traditional aqueous extraction process | |
Aceto | Food forensics | |
Wang et al. | Nondestructive determination of IMP content in chilled chicken based on hyperspectral data combined with chemometrics | |
CN104101579A (en) | Hairtail producing area rapid detection method | |
Phanomsophon et al. | Rapid measurement of classification levels of primary macronutrients in durian (Durio zibethinus Murray CV. Mon Thong) leaves using FT-NIR spectrometer and comparing the effect of imbalanced and balanced data for modelling | |
Faivre et al. | Marine radiocarbon reservoir age of the coralline intertidal alga Lithophyllum byssoides in the Mediterranean | |
Phillips et al. | Effect of season on the sensory quality of sea urchin (Evechinus chloroticus) roe | |
CN112285031A (en) | Method for rapidly representing umami intensity of salmon based on hyperspectral imaging technology | |
CN107860746A (en) | A kind of Yunnan local chicken muscle freeze-dried powder lysine content near infrared detection method | |
CN109613040A (en) | A method of Growth Op Tilapia is influenced based on NMR metabonomic technology parsing taurine |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20170426 |