CN110954499B - Mixed identification method and system for producing areas of imported salmon - Google Patents
Mixed identification method and system for producing areas of imported salmon Download PDFInfo
- Publication number
- CN110954499B CN110954499B CN201911141295.3A CN201911141295A CN110954499B CN 110954499 B CN110954499 B CN 110954499B CN 201911141295 A CN201911141295 A CN 201911141295A CN 110954499 B CN110954499 B CN 110954499B
- Authority
- CN
- China
- Prior art keywords
- data
- salmon
- sample
- classifier based
- imported
- 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.)
- Active
Links
- 241000972773 Aulopiformes Species 0.000 title claims abstract description 432
- 235000019515 salmon Nutrition 0.000 title claims abstract description 432
- 238000000034 method Methods 0.000 title claims abstract description 89
- 150000001413 amino acids Chemical class 0.000 claims abstract description 164
- 239000002366 mineral element Substances 0.000 claims abstract description 134
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 127
- 238000001819 mass spectrum Methods 0.000 claims abstract description 104
- 229910052801 chlorine Inorganic materials 0.000 claims abstract description 33
- 229910052749 magnesium Inorganic materials 0.000 claims abstract description 33
- 229910052698 phosphorus Inorganic materials 0.000 claims abstract description 33
- 229910052700 potassium Inorganic materials 0.000 claims abstract description 33
- 229910052791 calcium Inorganic materials 0.000 claims abstract description 31
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000001228 spectrum Methods 0.000 claims description 36
- 229910052742 iron Inorganic materials 0.000 claims description 32
- 229910052711 selenium Inorganic materials 0.000 claims description 32
- 238000001514 detection method Methods 0.000 claims description 29
- 238000001035 drying Methods 0.000 claims description 29
- 230000003595 spectral effect Effects 0.000 claims description 28
- 239000002245 particle Substances 0.000 claims description 24
- 238000012706 support-vector machine Methods 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 12
- 238000012795 verification Methods 0.000 claims description 12
- 238000001914 filtration Methods 0.000 claims description 10
- 230000006870 function Effects 0.000 claims description 10
- 230000002068 genetic effect Effects 0.000 claims description 10
- 238000004519 manufacturing process Methods 0.000 claims description 10
- 238000012935 Averaging Methods 0.000 claims description 9
- 238000002790 cross-validation Methods 0.000 claims description 8
- 238000012360 testing method Methods 0.000 claims description 7
- 238000000227 grinding Methods 0.000 claims description 6
- 208000011597 CGF1 Diseases 0.000 claims description 4
- 230000004039 social cognition Effects 0.000 claims description 4
- 238000011156 evaluation Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 abstract description 5
- 229910052757 nitrogen Inorganic materials 0.000 abstract description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N iron Substances [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 32
- 239000011575 calcium Substances 0.000 description 30
- 239000000460 chlorine Substances 0.000 description 30
- 239000011777 magnesium Substances 0.000 description 30
- 239000011669 selenium Substances 0.000 description 30
- 230000008569 process Effects 0.000 description 27
- 235000013305 food Nutrition 0.000 description 15
- 241000251468 Actinopterygii Species 0.000 description 12
- 235000019688 fish Nutrition 0.000 description 12
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 12
- 230000000694 effects Effects 0.000 description 10
- 239000002689 soil Substances 0.000 description 10
- VEXZGXHMUGYJMC-UHFFFAOYSA-N Hydrochloric acid Chemical compound Cl VEXZGXHMUGYJMC-UHFFFAOYSA-N 0.000 description 8
- 239000000203 mixture Substances 0.000 description 8
- 239000000126 substance Substances 0.000 description 8
- 230000008901 benefit Effects 0.000 description 7
- 229910052799 carbon Inorganic materials 0.000 description 7
- 241000196324 Embryophyta Species 0.000 description 6
- 230000029087 digestion Effects 0.000 description 6
- 238000005516 engineering process Methods 0.000 description 6
- 229910052739 hydrogen Inorganic materials 0.000 description 6
- 239000000047 product Substances 0.000 description 6
- IJGRMHOSHXDMSA-UHFFFAOYSA-N Atomic nitrogen Chemical compound N#N IJGRMHOSHXDMSA-UHFFFAOYSA-N 0.000 description 4
- MHAJPDPJQMAIIY-UHFFFAOYSA-N Hydrogen peroxide Chemical compound OO MHAJPDPJQMAIIY-UHFFFAOYSA-N 0.000 description 4
- 241001465754 Metazoa Species 0.000 description 4
- ATJFFYVFTNAWJD-UHFFFAOYSA-N Tin Chemical compound [Sn] ATJFFYVFTNAWJD-UHFFFAOYSA-N 0.000 description 4
- 238000010521 absorption reaction Methods 0.000 description 4
- 238000000862 absorption spectrum Methods 0.000 description 4
- 238000013528 artificial neural network Methods 0.000 description 4
- 238000002485 combustion reaction Methods 0.000 description 4
- 238000013480 data collection Methods 0.000 description 4
- 235000019197 fats Nutrition 0.000 description 4
- 239000000706 filtrate Substances 0.000 description 4
- 125000004435 hydrogen atom Chemical group [H]* 0.000 description 4
- 230000007062 hydrolysis Effects 0.000 description 4
- 238000006460 hydrolysis reaction Methods 0.000 description 4
- 235000013372 meat Nutrition 0.000 description 4
- 239000011259 mixed solution Substances 0.000 description 4
- 210000003205 muscle Anatomy 0.000 description 4
- 239000005416 organic matter Substances 0.000 description 4
- 102000004169 proteins and genes Human genes 0.000 description 4
- 108090000623 proteins and genes Proteins 0.000 description 4
- 230000009467 reduction Effects 0.000 description 4
- 241000277331 Salmonidae Species 0.000 description 3
- 239000002253 acid Substances 0.000 description 3
- 230000007613 environmental effect Effects 0.000 description 3
- 230000036541 health Effects 0.000 description 3
- OYPRJOBELJOOCE-UHFFFAOYSA-N Calcium Chemical compound [Ca] OYPRJOBELJOOCE-UHFFFAOYSA-N 0.000 description 2
- OKTJSMMVPCPJKN-UHFFFAOYSA-N Carbon Chemical compound [C] OKTJSMMVPCPJKN-UHFFFAOYSA-N 0.000 description 2
- ZAMOUSCENKQFHK-UHFFFAOYSA-N Chlorine atom Chemical compound [Cl] ZAMOUSCENKQFHK-UHFFFAOYSA-N 0.000 description 2
- VYZAMTAEIAYCRO-UHFFFAOYSA-N Chromium Chemical compound [Cr] VYZAMTAEIAYCRO-UHFFFAOYSA-N 0.000 description 2
- RYGMFSIKBFXOCR-UHFFFAOYSA-N Copper Chemical compound [Cu] RYGMFSIKBFXOCR-UHFFFAOYSA-N 0.000 description 2
- UFHFLCQGNIYNRP-UHFFFAOYSA-N Hydrogen Chemical compound [H][H] UFHFLCQGNIYNRP-UHFFFAOYSA-N 0.000 description 2
- DGAQECJNVWCQMB-PUAWFVPOSA-M Ilexoside XXIX Chemical compound C[C@@H]1CC[C@@]2(CC[C@@]3(C(=CC[C@H]4[C@]3(CC[C@@H]5[C@@]4(CC[C@@H](C5(C)C)OS(=O)(=O)[O-])C)C)[C@@H]2[C@]1(C)O)C)C(=O)O[C@H]6[C@@H]([C@H]([C@@H]([C@H](O6)CO)O)O)O.[Na+] DGAQECJNVWCQMB-PUAWFVPOSA-M 0.000 description 2
- FYYHWMGAXLPEAU-UHFFFAOYSA-N Magnesium Chemical compound [Mg] FYYHWMGAXLPEAU-UHFFFAOYSA-N 0.000 description 2
- 238000004497 NIR spectroscopy Methods 0.000 description 2
- GRYLNZFGIOXLOG-UHFFFAOYSA-N Nitric acid Chemical compound O[N+]([O-])=O GRYLNZFGIOXLOG-UHFFFAOYSA-N 0.000 description 2
- 241000277334 Oncorhynchus Species 0.000 description 2
- OAICVXFJPJFONN-UHFFFAOYSA-N Phosphorus Chemical compound [P] OAICVXFJPJFONN-UHFFFAOYSA-N 0.000 description 2
- ZLMJMSJWJFRBEC-UHFFFAOYSA-N Potassium Chemical compound [K] ZLMJMSJWJFRBEC-UHFFFAOYSA-N 0.000 description 2
- 241000277263 Salmo Species 0.000 description 2
- BUGBHKTXTAQXES-UHFFFAOYSA-N Selenium Chemical compound [Se] BUGBHKTXTAQXES-UHFFFAOYSA-N 0.000 description 2
- 241001465385 Solandra grandiflora Species 0.000 description 2
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical compound [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 2
- HCHKCACWOHOZIP-UHFFFAOYSA-N Zinc Chemical compound [Zn] HCHKCACWOHOZIP-UHFFFAOYSA-N 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 238000009395 breeding Methods 0.000 description 2
- 230000001488 breeding effect Effects 0.000 description 2
- 229910052804 chromium Inorganic materials 0.000 description 2
- 239000011651 chromium Substances 0.000 description 2
- 230000002860 competitive effect Effects 0.000 description 2
- 238000001816 cooling Methods 0.000 description 2
- 229910052802 copper Inorganic materials 0.000 description 2
- 239000010949 copper Substances 0.000 description 2
- 238000012937 correction Methods 0.000 description 2
- 238000005336 cracking Methods 0.000 description 2
- 238000007865 diluting Methods 0.000 description 2
- 201000010099 disease Diseases 0.000 description 2
- 208000037265 diseases, disorders, signs and symptoms Diseases 0.000 description 2
- 239000003651 drinking water Substances 0.000 description 2
- 235000020188 drinking water Nutrition 0.000 description 2
- 238000001704 evaporation Methods 0.000 description 2
- 230000008020 evaporation Effects 0.000 description 2
- 238000010812 external standard method Methods 0.000 description 2
- 230000004720 fertilization Effects 0.000 description 2
- -1 foodstuff Substances 0.000 description 2
- 238000005194 fractionation Methods 0.000 description 2
- 125000000524 functional group Chemical group 0.000 description 2
- 239000001257 hydrogen Substances 0.000 description 2
- 230000003301 hydrolyzing effect Effects 0.000 description 2
- 230000008676 import Effects 0.000 description 2
- 230000003993 interaction Effects 0.000 description 2
- PNDPGZBMCMUPRI-UHFFFAOYSA-N iodine Chemical compound II PNDPGZBMCMUPRI-UHFFFAOYSA-N 0.000 description 2
- 150000002500 ions Chemical class 0.000 description 2
- 230000000155 isotopic effect Effects 0.000 description 2
- WPBNNNQJVZRUHP-UHFFFAOYSA-L manganese(2+);methyl n-[[2-(methoxycarbonylcarbamothioylamino)phenyl]carbamothioyl]carbamate;n-[2-(sulfidocarbothioylamino)ethyl]carbamodithioate Chemical compound [Mn+2].[S-]C(=S)NCCNC([S-])=S.COC(=O)NC(=S)NC1=CC=CC=C1NC(=S)NC(=O)OC WPBNNNQJVZRUHP-UHFFFAOYSA-L 0.000 description 2
- 238000004949 mass spectrometry Methods 0.000 description 2
- 239000012528 membrane Substances 0.000 description 2
- 230000004060 metabolic process Effects 0.000 description 2
- 230000000813 microbial effect Effects 0.000 description 2
- 238000000120 microwave digestion Methods 0.000 description 2
- 238000002156 mixing Methods 0.000 description 2
- 230000007935 neutral effect Effects 0.000 description 2
- 229910017604 nitric acid Inorganic materials 0.000 description 2
- 235000016709 nutrition Nutrition 0.000 description 2
- 230000035764 nutrition Effects 0.000 description 2
- 230000000050 nutritive effect Effects 0.000 description 2
- 239000011574 phosphorus Substances 0.000 description 2
- 239000011591 potassium Substances 0.000 description 2
- 238000003672 processing method Methods 0.000 description 2
- 238000007789 sealing Methods 0.000 description 2
- 238000004062 sedimentation Methods 0.000 description 2
- 229910052708 sodium Inorganic materials 0.000 description 2
- 239000011734 sodium Substances 0.000 description 2
- 230000000087 stabilizing effect Effects 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000004659 sterilization and disinfection Methods 0.000 description 2
- 239000011593 sulfur Substances 0.000 description 2
- 229910052717 sulfur Inorganic materials 0.000 description 2
- 230000007704 transition Effects 0.000 description 2
- 239000011701 zinc Substances 0.000 description 2
- 229910052725 zinc Inorganic materials 0.000 description 2
- 208000035473 Communicable disease Diseases 0.000 description 1
- 241000723298 Dicentrarchus labrax Species 0.000 description 1
- 241001154287 Hucho taimen Species 0.000 description 1
- 241000277269 Oncorhynchus masou Species 0.000 description 1
- 241001327684 Oncorhynchus mykiss aguabonita Species 0.000 description 1
- 241000277277 Oncorhynchus nerka Species 0.000 description 1
- BQCADISMDOOEFD-UHFFFAOYSA-N Silver Chemical compound [Ag] BQCADISMDOOEFD-UHFFFAOYSA-N 0.000 description 1
- 244000052616 bacterial pathogen Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 238000004140 cleaning Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- CYQFCXCEBYINGO-IAGOWNOFSA-N delta1-THC Chemical compound C1=C(C)CC[C@H]2C(C)(C)OC3=CC(CCCCC)=CC(O)=C3[C@@H]21 CYQFCXCEBYINGO-IAGOWNOFSA-N 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 235000005911 diet Nutrition 0.000 description 1
- 230000037213 diet Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 229940012843 omega-3 fatty acid Drugs 0.000 description 1
- 235000020660 omega-3 fatty acid Nutrition 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 229910052709 silver Inorganic materials 0.000 description 1
- 239000004332 silver Substances 0.000 description 1
- 238000003860 storage Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
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
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N1/00—Sampling; Preparing specimens for investigation
- G01N1/28—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q
- G01N1/286—Preparing specimens for investigation including physical details of (bio-)chemical methods covered elsewhere, e.g. G01N33/50, C12Q involving mechanical work, e.g. chopping, disintegrating, compacting, homogenising
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N27/00—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means
- G01N27/62—Investigating or analysing materials by the use of electric, electrochemical, or magnetic means by investigating the ionisation of gases, e.g. aerosols; by investigating electric discharges, e.g. emission of cathode
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/02—Food
- G01N33/12—Meat; fish
Landscapes
- Chemical & Material Sciences (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biochemistry (AREA)
- General Physics & Mathematics (AREA)
- Pathology (AREA)
- Analytical Chemistry (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Engineering & Computer Science (AREA)
- Food Science & Technology (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Medicinal Chemistry (AREA)
- Chemical Kinetics & Catalysis (AREA)
- Electrochemistry (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Other Investigation Or Analysis Of Materials By Electrical Means (AREA)
Abstract
The invention discloses a mixed identification method and a mixed identification system for producing areas of imported salmon, wherein the tracing method comprises the following steps: collecting salmon samples of different countries, and collecting near infrared spectrum, delta, of standard salmon sample 13 C、δ 18 O、δ 15 The method comprises the steps of training values of N, Ca, Cl, Mg, P, K, Na, Cu, Fe, Se, Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp to generate a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, sequencing the classifiers according to performance, and integrating results and sequencing positions of the four classifiers to judge the producing area of the imported salmon. The invention provides a method and a system for hybrid identification of the origin of imported salmon, aiming at the problems of long transportation time, complex transportation environment and the like of the imported salmon, improves the traceability precision of the imported salmon, and simultaneously meets the requirement of wide application range of the existing imported salmon.
Description
Technical Field
The invention relates to the field of origin tracing of producing areas, in particular to a mixed identification method and system for producing areas of imported salmon.
Background
Salmon, as many as 30 kinds of which have economic value. The most common trout at present are two kinds of trout, such as salmon and golden trout, and four kinds of trout, such as Pacific salmon, Atlantic salmon, arctic white salmon and silver salmon. The export countries of salmon in the world are mainly Norway, Sweden, America, Chile, Poland, France, British, Canada, Russia and the like, and the export quantity is the maximum in Norway. With the development of global economy and the continuous improvement of the living standard of people, the diet health care consciousness of people is increasingly enhanced, and salmon is a group with the largest trade quantity in aquatic products in China at present because the salmon is rich in omega 3 fatty acid (comprising 20-carbon 5-olefine acid EPA, 22-carbon 6-olefine acid DHA and 22-carbon 5-olefine acid DPA) beneficial to human health, is delicious in meat, is deeply loved by consumers and continuously expands the market demand. The salmon species imported in China mainly include Atlantic salmon and some Pacific salmon (hucho taimen, red salmon, and salmon), and the main imported countries are Chilean and Norway.
The globalization of the food market enables consumers to pay more attention to the production area of food, and meanwhile, salmon is used as meat with high added value, and label identification errors, label counterfeiting and common declaration of salmon food safety events caused by using geographical marks to mark the production area of salmon are also brought to the public, so that the public attention to the identification of the food origin area is increased. The stipulation of the trademark law (revision) in China proves that the trademark is protected by law in the origin, the food safety is an indispensable part of the salmon market rule, and each market participant is required to respect the law and pay attention to the food safety. Meanwhile, the importance on the food safety of the salmon is the requirement for maintaining the normal order and the fair competition of the salmon market, the requirement for maintaining the benefits of consumers and the requirement for realizing the commercial value of the salmon.
In addition, the safety of salmon products is seriously threatened by the occurrence of infectious diseases. When the epidemic situation outbreaks, the epidemic situation source can be quickly and accurately found, effective measures are taken to control the spread of the epidemic situation, the food safety of the salmon is favorably ensured, and the health of people is favorably ensured. The government of China is an executor of the intention of people and a defender of the interests of people, the intention is to serve people, the principle is responsible for people, and the government has great importance on the food safety problem. The salmon, which is meat with high market circulation, has food safety problems related to various aspects of society, and must pay attention to prevent food safety accidents.
At present, biotechnology such as stable isotope, near infrared, electronic tongue, mineral elements and the like is mostly utilized for tracing sources of salmon so as to find out the origin of salmon, investigate salmon possibly suffering from diseases and prevent propagation of food-borne pathogenic bacteria.
The invention patent with publication number CN108489927A discloses a method for tracing the origin of fish, which collects the spectral data of a fish meat sample by an infrared spectrometer; importing the spectral data into a trained characteristic value training model, and extracting the characteristic value of the fish production place; the characteristic value is used as the input of a BP neural network, and the BP neural network classifies the characteristic value and predicts the producing area of the fish sample; the invention also discloses an electronic device, a computer readable storage medium and a fish origin tracing device; according to the invention, the DBN algorithm is used for learning the spectral data of the fish, irrelevant and invalid spectral information is eliminated, the learned characteristic value is used as the input of the BP neural network to match with the fish identification model, the denoising capability is higher, and the problems of local optimization and the like caused by random selection of the initial value and inappropriate parameter selection of the BP neural network can be avoided; on the whole, the method for tracing the origin of the fish can further improve the accuracy of identifying the origin of the fish.
The source tracing method can only trace the source of common fishes, but cannot trace the source of the salmon based on the characteristics of the salmon. The characteristics of salmon are completely different from those of common fishes, so the existing tracing method for common fishes is not suitable for imported salmon. In addition, salmon mostly depends on import in China, the difference of transportation environments and the like is large in the import process of the salmon, and the influence of the salmon in the transportation process is not eliminated by the existing tracing method. Imported salmon covers a wide range, possibly all over the world, and has a greater influence when diseases and the like occur. The existing salmon tracing method adopts a single biotechnology to trace the source, has low tracing precision and can not effectively combine various tracing methods. Therefore, how to provide effective traceability for imported salmon is an urgent problem to be solved in the field.
Disclosure of Invention
The invention aims to provide a mixed identification method and a mixed identification system for producing areas of imported salmon, aiming at the defects of the prior art. And generating a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and judging the producing area of the imported salmon by integrating the results and the sequencing positions of the four classifiers. The invention provides a method and a system for hybrid identification of the origin of imported salmon, aiming at the problems of long transportation time, complex transportation environment and the like of the imported salmon, improves the traceability precision of the imported salmon, and simultaneously meets the requirement of wide application range of the existing imported salmon.
In order to achieve the purpose, the invention adopts the following technical scheme:
a mixed identification method for producing areas of imported salmon comprises the following steps:
s1, collecting salmon samples of different countries, crushing and drying the salmon samples, grinding the salmon samples after drying, filtering by using a sieve plate with a fixed size, and drying again to obtain standard imported salmon samples;
s2, collecting the near infrared spectrum of the standard imported salmon sample by using an infrared spectrometer, wherein the wave number range of the collected and scanned is 8000- -1 Resolution of 4cm -1 The scanning temperature is maintained at 25 ℃, the humidity is controlled to be kept stable, the spectrum of each sample is scanned for three times, and the average value of the spectrum data acquired for three times is obtained to obtain the spectrum data of each imported salmon sample; method for measuring infrared spectrum of salmon sampleSubtracting and standard deviation, and removing singular point samples to obtain final near infrared spectrum data of the imported salmon sample;
s3, detecting delta in the standard imported salmon sample by using an isotope ratio mass spectrometer 13 C、δ 18 O、δ 15 Detecting each sample by using an isotope ratio mass spectrometer for three times, and calculating the average value of isotope mass spectrum data acquired for the three times to obtain isotope mass spectrum data of each imported salmon sample; according to the variance and standard deviation of the salmon sample isotope mass spectrum data, removing singular point samples to obtain final imported salmon sample isotope mass spectrum data;
s4, detecting the content of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer, detecting each sample by using the plasma mass spectrometer three times, and averaging the mineral element data acquired by the three times to obtain the mineral element data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final imported salmon sample mineral element data;
s5, detecting the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the standard imported salmon sample by using an amino acid analyzer, detecting each sample for three times by using the amino acid analyzer, and calculating the average value of the amino acid contents collected for three times to obtain the amino acid content data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final amino acid data of imported salmon samples;
s6, establishing a support vector machine classifier, segmenting infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of the imported salmon sample, selecting 1/n sample data as a test set, taking the rest sample data as a training set, and continuously training the classifier based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data to obtain the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data;
s7, cross-validation of the performance of classifiers based on infrared spectral data, classifiers based on isotope mass spectral data, classifiers based on mineral element data and classifiers based on amino acid data;
s8, sorting the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data according to performance, and giving corresponding weight to the classifiers according to performance ranking;
s9, detecting imported salmon by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data respectively, and calculating the similarity of infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of a detection sample and salmon in each country respectively;
and S10, calculating the weighted sum of similarity results obtained by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data and corresponding classifiers, comparing the weighted sum with a set threshold value, and judging the producing area of the imported salmon.
Further, the crushing and drying of the salmon sample specifically comprises the following steps:
dicing imported salmon samples, and placing the diced salmon samples into a groove-shaped mixer to be crushed for about two hours in a dark environment; after the salmon is crushed, the salmon is put into a drying chamber to be thoroughly dried for 24 hours.
Further, the singular point elimination sample specifically includes:
calculating the average value of the detection data content of the salmon sample imported from each producing area, and removing the sample from the sample set when the variance and standard deviation of the sample exceed a set threshold value; the detection data comprises infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data.
Further, the step S7 is specifically:
randomly dividing a sample data set into K subsets, wherein one subset is used as a verification set, and the rest K-1 subsets are used as training sets; and taking the K subsets as verification sets in turn, alternately repeating the K subsets for K times to obtain K results, and taking the average value of the K results as the performance index of the classifier or the model.
Further, the corresponding weight given to the classifier according to the performance ranking specifically is:
the weight of a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data is assumed to be omega respectively 1 、ω 2 、ω 3 、ω 4 And then:
ω 1 +ω 2 +ω 3 +ω 4 =1
the better the performance of the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data is, the larger the weight is.
Further, the step S10 is specifically:
performing mixed identification by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and respectively assuming that the similarity results are r 1 、r 2 、r 3 、r 4 Then, the final detection result of the classifier is:
r=r 1 *ω 1 +r 2 *ω 2 +r 3 *ω 3 +r 4 *ω 4
and when r is larger than a set threshold value, importing the salmon to the corresponding country, otherwise not importing the salmon to the corresponding country.
The invention also provides a mixed identification system for the producing area of imported salmon, which comprises:
the pretreatment module is used for collecting salmon samples of different countries, crushing and drying the salmon samples, grinding the salmon samples after drying, filtering by using a sieve plate with a fixed size, and drying again to obtain standard imported salmon samples;
a near infrared spectrum acquisition module for acquiring the near infrared spectrum of the standard imported salmon sample by using an infrared spectrometer, wherein the wave number range of the acquired scanning is 8000-4000cm -1 Resolution of 4cm -1 The scanning temperature is maintained at 25 ℃, the humidity is controlled to be kept stable, the spectrum of each sample is scanned for three times, and the average value of the spectrum data acquired for three times is obtained to obtain the spectrum data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the near infrared spectrum of the salmon sample to obtain final near infrared spectrum data of the imported salmon sample;
an isotope collection module for detecting delta in the standard imported salmon sample using an isotope ratio mass spectrometer 13 C、δ 18 O、δ 15 Detecting each sample by using an isotope ratio mass spectrometer for three times, and calculating the average value of isotope mass spectrum data acquired for the three times to obtain isotope mass spectrum data of each imported salmon sample; according to the variance and standard deviation of the salmon sample isotope mass spectrum data, removing singular point samples to obtain final imported salmon sample isotope mass spectrum data;
the mineral element acquisition module is used for detecting the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer, detecting each sample by using the plasma mass spectrometer for three times, and calculating the average value of the mineral element data acquired for three times to obtain the mineral element data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final imported salmon sample mineral element data;
the amino acid acquisition module is used for detecting the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the standard imported salmon sample by using an amino acid analyzer, each sample is detected for three times by using the amino acid analyzer, and the amino acid content data of each imported salmon sample is obtained by averaging the amino acid contents collected for three times; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final amino acid data of imported salmon samples;
the classifier establishing module is used for establishing a support vector machine classifier, segmenting the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the imported salmon sample, selecting 1/n sample data as a test set, taking the rest sample data as a training set, continuously training the classifier based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data respectively, and obtaining the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data;
the verification evaluation module is used for cross verifying the performance of a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data;
the sorting module is used for sorting the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data according to performance and giving corresponding weight to the classifiers according to performance ranking;
the detection module is used for detecting imported salmon by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data respectively, and calculating the similarity of infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of a detection sample and salmon in each country respectively;
and the comprehensive source tracing module is used for calculating the weighted sum of similarity results obtained by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data and corresponding classifiers, comparing the weighted sum with a set threshold value and judging the producing area of the imported salmon.
Further, the establishing a support vector machine classifier comprises: in the optimal parameter interval, initial values of a Gaussian radial basis kernel function parameter sigma and a complexity parameter C are randomly set, the initial population scale is 200, the genetic evolution algebra is 300, and a self-cognition factor C is performed 1 1.5, social cognition factor c 2 1.5, optimizing classifier parameters with a weight factor w of 0.78; in each genetic evolution, the average accuracy of 300 times of cross validation of different K values of the particles is calculated and used as the fitness of the particles, then the population optimization and the individual optimization are updated, finally the particles are sorted in a descending order according to the fitness, the first half of the particles which are more excellent directly enter the next evolution, and the second half of the particles which are worse are sequentially randomly crossed with the particles in the first half for genetic inheritance.
Further, the corresponding weight given to the classifier according to the performance ranking specifically is:
the weight of a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data is assumed to be omega respectively 1 、ω 2 、ω 3 、ω 4 And then:
ω 1 +ω 2 +ω 3 +ω 4 =1
the better the performance of the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data, the larger the weight.
Further, the comprehensive traceability module comprises:
performing mixed identification by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and respectively assuming that the similarity results are r 1 、r 2 、r 3 、r 4 Then, the final detection result of the classifier is:
r=r 1 *ω 1 +r 2 *ω 2 +r 3 *ω 3 +r 4 *ω 4
and when r is larger than a set threshold value, importing the salmon to the corresponding country, otherwise not importing the salmon to the corresponding country.
Compared with the prior art, the invention has the following effects:
(1) the characteristics of the imported salmon are deeply analyzed, and the purposefully provided method and system for identifying the origin and the place of the imported salmon are capable of detecting the imported salmon, wide in application range and extremely high in application value;
(2) because imported salmon is imported, the time spent is long, and the environmental difference is big in the transportation process, stable isotope technique, mineral elements, amino acid and the like in the existing traceability technology are greatly influenced by the test environment, the near infrared spectrum technology relies on a database, the source and the quantity of a large number of samples are needed to improve the traceability precision to a certain extent, and the like. According to the method, the origin of the imported salmon is traced by combining infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid, and the influence of the imported salmon in the transportation process is overcome and the tracing precision is improved by combining four tracing modes;
(3) according to the method, the four tracing modes are sequenced according to the performance, corresponding weights are given to different tracing modes according to the sequencing result, the influence of the tracing modes on the comprehensive tracing result can be adjusted according to the performance of the tracing model, the advantages of the tracing modes are fully exerted, and the tracing modes are not simply mixed;
(4) the method further improves the precision and efficiency of tracing by utilizing the advantages of minimum structured risk and excellent generalization capability of the support vector machine;
(5) according to the invention, the imported salmon is firstly crushed and then dried, so that the drying effect of the salmon can be improved;
(6) according to the invention, by collecting the spectral data, isotope data, mineral element data and amino acid data of each imported salmon sample for multiple times, errors in a single spectral data collection process can be avoided;
(7) the method calculates the corresponding variance and standard deviation of the acquired spectral data, isotope data, mineral element data and amino acid data of each imported salmon sample, eliminates the corresponding singular point sample, and avoids the influence of the acquisition environment and the like on the data.
Drawings
FIG. 1 is a flow chart of a mixed identification method for the origin of imported salmon according to one embodiment;
fig. 2 is a structural diagram of a hybrid identification system for the origin of imported salmon according to the second embodiment.
Detailed Description
The embodiments of the present invention are described below with reference to specific embodiments, and other advantages and effects of the present invention will be easily understood by those skilled in the art from the disclosure of the present specification. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It is to be noted that the features in the following embodiments and examples may be combined with each other without conflict.
It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention, and the components related to the present invention are only shown in the drawings rather than drawn according to the number, shape and size of the components in actual implementation, and the type, quantity and proportion of the components in actual implementation may be changed freely, and the layout of the components may be more complicated.
The invention is further described with reference to the following drawings and specific examples, which are not intended to be limiting.
Example one
As shown in fig. 1, the present embodiment provides a mixed identification method for producing origin of imported salmon, comprising:
s1, collecting salmon samples of different countries, crushing and drying the salmon samples, grinding the salmon samples after drying, filtering by using a sieve plate with a fixed size, and drying again to obtain standard imported salmon samples;
at present, salmon is imported from Norway, Sweden, America, Chilean, Poland, France, British, Canada and Russia. Therefore, for competitive breeding of the identification of the producing area, the present invention collected salmon in 9 countries of norway, sweden, usa, chile, polish, france, uk, canada, russia, 200 portions of salmon per country, 500g each.
In order to more accurately trace the source of imported salmon, pretreatment of salmon samples is required. The sample was first diced, crushed in a trough mixer, and crushed in a dark environment for about two hours. After the salmon is crushed, the salmon is dried, and the salmon can be completely dried in a drying chamber for 24 hours. According to the invention, the imported salmon is firstly crushed and then dried, so that the drying effect of the salmon can be improved.
S2, collecting the near infrared spectrum of the standard imported salmon sample by using an infrared spectrometer, wherein the wave number range of the collected and scanned is 8000- -1 Resolution of 4cm -1 The scanning temperature is maintained at 25 ℃, the humidity is controlled to be kept stable, the spectrum of each sample is scanned for three times, and the average value of the spectrum data acquired for three times is obtained to obtain the spectrum data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the near infrared spectrum of the salmon sample to obtain final near infrared spectrum data of the imported salmon sample;
the near-infrared light is a section of electromagnetic wave with a wavelength between visible light and mid-infrared light, and the wavelength range of the electromagnetic wave is 780-2526 nm. The near infrared spectrum can reflect the interaction between infrared rays and substances in imported salmon samples, in nature, the composition and the structure of each molecule are different, the absorption effects of different internal functional groups or chemical bonds such as O-H, C-H, N-H and S-H groups on red external light are different, and after the hydrogen groups absorb partial energy in the near infrared light again, the hydrogen groups are excited to generate transition, so that the positions and the absorption intensities of curves displayed on the near infrared spectrum are different, and the near infrared spectrum is generated in a near infrared spectrometer, and the characteristic near infrared absorption spectrum of each sample is obtained.
The near infrared spectrum reflects the information of the composition and content of organic matter in the sample. Imported salmon samples from different producing areas are influenced by factors such as varieties, producing area environments, processing methods and transportation modes, and also by factors such as growing environments, climates, soil and water quality, so that the structure and the content of main chemical components (such as protein, fat and water) of the food have certain difference, and the organic matter components of the food have obvious difference. In addition, the animal bodies in the respective production places differ in substance components such as protein, fat, and water due to differences in genotype, feed type, feeding method, individual metabolism, and the like. On the near infrared spectrum, these differences are reflected and hence a near infrared absorption spectrum characteristic of the sample for each origin.
The invention utilizes an infrared spectrometer to collect the near infrared spectrum of the standard salmon sample, takes 1-3 g of the standard imported salmon sample for spectrum collection, and the wave number range of the collected scanning is 8000-4000cm -1 Resolution of 4cm -1 And the scanning temperature is maintained at 25 ℃, the humidity is controlled to be kept stable, the spectrum of each sample is scanned for three times, and the average value of the three acquired spectrum data is obtained to obtain the spectrum data of each imported salmon sample. According to the invention, by collecting the spectral data of each imported salmon sample for multiple times, errors in a single spectral data collection process can be avoided.
In addition, as the imported salmon is greatly influenced by the environment, the influence of different scanning environments on the spectral data is different, and therefore, when different imported salmon samples are scanned for multiple times, the scanning environment is kept constant.
In the process of making an imported salmon sample, the problem that imported salmon sample data is inaccurate due to pollution or the fact that the near infrared spectrum is affected by factors such as equipment and environment in the collection process may exist. Therefore, before the origin tracing of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
The method adopts the variance and standard deviation of the near infrared spectrum of the salmon sample to remove singular point samples. The near infrared spectra of the imported salmon in the same producing area generally show similar characteristics, and the difference between spectra collected by different imported salmon samples is small. Therefore, the method utilizes the variances and standard deviations of the near infrared spectra of different salmon samples to compare, and when the variance and standard deviation of a certain near infrared spectrum exceed a certain threshold value, the sample is proved to have large amplitude deviating from other samples in the same producing area, and the sample is probably a singular point sample to be removed.
Therefore, the invention calculates the average value of the infrared spectrum of 200 samples of the salmon imported from each producing area, and further calculates the variance and standard deviation of each sample of the salmon imported from each producing area. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
S3, detecting delta in the standard imported salmon sample by using an isotope ratio mass spectrometer 13 C、δ 18 O、δ 15 Detecting each sample by using an isotope ratio mass spectrometer for three times, and averaging the isotope mass spectrum data acquired for three times to obtain the isotope mass spectrum data of each imported salmon sample; according to the variance and standard deviation of the salmon sample isotope mass spectrum data, removing singular point samples to obtain final imported salmon sample isotope mass spectrum data;
the principle of tracing the origin of the stable isotope technology is to identify the origin of a target sample by utilizing the natural fractionation effect of the isotope. Due to the difference of air temperature, sunlight, soil, foodstuff, air quality and the like, the isotopic abundance of a certain element in the target sample is obviously different from other samples in different producing areas, so that the producing area tracing of the animal-derived agricultural products can be accurately distinguished. Utensil for cleaning buttockIn particular, by stabilizing isotopes 13 C and 12 the ratio of C can be used for characterizing the feed types, and the ratio of C to C in the feed 3 、C 4 The proportion of the plants is closely related; in isotope of 15 N and 14 the proportion of N is influenced by a plurality of factors, mainly depends on the nutrition level, is closely related to the feed variety, can also indicate the difference in soil, climate and agricultural fertilization, and is even related to the proportion of marine and land plants in the feed; in addition to the isotopes 18 O and 16 ratio of O and 2 h and 1 the proportion of H is related to the climate, the terrain, the evaporation, the concentration and the sedimentation of water in the producing area; in isotope 34 S and 32 the proportion of S is related to microbial action and marine factors.
The salmon feed, drinking water, soil, climate and the like imported from different countries are completely different. Especially the carbon, nitrogen and hydrogen isotopes have extremely significant correlation, delta 13 C、δ 18 O、δ 15 N is used as the main index of salmon in the zone of the invention, wherein delta 13 C reflects the ratio of C3 and C4 plants in the feed, while delta 18 The O composition is related to the climate and water of the country, delta 15 N reacts with the soil conditions of the country where the imported salmon is located.
Detecting delta in the standard imported salmon sample 13 The value of C: putting 2-4 g of each standard imported salmon sample into a tin foil cup, feeding the standard imported salmon sample into an element analyzer through an automatic sampler, and combusting the imported salmon sample to convert the imported salmon sample into pure CO 2 And N 2 ,CO 2 Diluting with diluter to obtain CO 2 Sending the sample into an isotope ratio mass spectrometer for detection. Wherein the temperature of the combustion furnace is 1200 ℃, and the temperature of the reduction furnace is 600 ℃.
Detecting delta in the standard imported salmon sample 18 The value of O: 2-4 g of each standard imported salmon sample is put into a silver cup, balanced for 72 hours, put into an automatic sample injector in sequence, and then put into an element analyzer through the automatic sample injector to crack the imported salmon sample into C, H 2 、O 2 Finally, O is finally added 2 Sending the sample into an isotope ratio mass spectrometer for detection. Wherein the temperature of the cracking is 2500 ℃.
Detecting delta in the standard imported salmon sample 15 The value of N: putting 2-4 g of each standard imported salmon sample into a tin foil cup, feeding the standard imported salmon sample into an element analyzer through an automatic sampler, and combusting the imported salmon sample to convert the imported salmon sample into pure CO 2 And N 2 Finally, will N 2 Sending the sample into an isotope ratio mass spectrometer for detection. Wherein the temperature of the combustion furnace is 1200 ℃, and the temperature of the reduction furnace is 600 ℃.
Delta in salmon sample at inlet of each sample 13 C、δ 18 O、δ 15 The values of N are collected for three times, and the average value of the data collected for three times is calculated to obtain the delta in each imported salmon sample 13 C、δ 18 O、δ 15 The value of N. The invention collects the middle delta of each imported salmon sample for multiple times 13 C、δ 18 O、δ 15 And the value of N can avoid errors in a single data acquisition process. Isotope ratio mass spectrometer
As with near infrared spectral collection, delta 13 C、δ 18 O、δ 15 The value of N can also be influenced by factors such as environment, collection conditions and the like, so that the problem that the sample data of imported salmon is inaccurate is caused. Therefore, before the origin tracing of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
The invention is based on salmon sample delta 13 C、δ 18 O、δ 15 And eliminating singular point samples according to the variance and standard deviation of N. As long as delta 13 C、δ 18 O、δ 15 And when the variance and the standard deviation of any value of N exceed a certain threshold value, the sample is large in amplitude deviating from other samples in the same place of origin, and the sample is likely to be a singular point sample to be removed.
Therefore, the present invention calculates the delta of 200 samples of salmon imported from each production area 13 C、δ 18 O、δ 15 N is flatAnd (4) further calculating the variance and standard deviation of each imported salmon sample. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
S4, detecting the content of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer, detecting each sample by using the plasma mass spectrometer three times, and averaging the mineral element data acquired by the three times to obtain the mineral element data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final imported salmon sample mineral element data;
the content of each element in the salmon is closely related to conditions such as water source, climate and the like of a product producing area, and different areas have characteristic element compositions, so that the mineral element fingerprint spectrums of imported salmon with different producing areas can be established, and the more accurate tracing of the producing area of the imported salmon is realized. The mineral element fingerprint spectrum technology is characterized in that according to the measured values of major elements (calcium, phosphorus, magnesium, potassium, sodium, chlorine, sulfur and the like) and mineral elements (iron, copper, manganese, zinc, iodine, selenium, chromium and the like) in an imported salmon sample, elements with significant differences are selected through statistical analysis to establish a model, and therefore the producing area of the imported salmon can be identified more accurately.
The salmon living environment is complex and is highly influenced by the environment. Different salmon origins may have only slight differences in the content of some elements. Therefore, the content of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample is detected by using a plasma mass spectrometer so as to comprehensively analyze elements contained in the salmon. Slight differences between salmon from different origins were identified.
Detecting the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer specifically comprises the following steps: taking 2-4 g of each standard imported salmon sample, putting the sample into a digestion tube, carrying out pre-digestion for 2 hours by using concentrated nitric acid, then carrying out disinfection for 1 hour by using hydrogen peroxide, and finally putting the sample into a microwave digestion instrument for digestion. Collecting Ca, Cl, Mg, P, K, Na, Cu, Fe and Se by using an ion mass spectrometer, and finally quantifying the collected Ca, Cl, Mg, P, K, Na, Cu, Fe and Se by using an external standard method to measure the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se.
And (3) collecting the content values of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the salmon sample imported from each sample for three times, and averaging the data collected for three times to obtain the content values of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the salmon sample imported from each sample. According to the method, the content values of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in each imported salmon sample are collected for multiple times, so that errors in a single data collection process can be avoided.
Ca. The content values of Cl, Mg, P, K, Na, Cu, Fe and Se can be influenced by factors such as environment, collection conditions and the like, so that the sample data of imported salmon is inaccurate. Therefore, before the origin tracing of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
According to the method, singular point samples are removed according to the variances and standard deviations of the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se of the salmon samples. When the variance and standard deviation of any value of the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se exceed a certain threshold value, the sample is indicated to be deviated from other samples in the same place by a large amplitude, and the sample is probably a singular point sample and is removed.
Therefore, the invention calculates the average value of the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se of 200 samples of the salmon imported from each producing area, and further calculates the variance and standard deviation of each sample of the salmon imported from each producing area. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
S5, detecting the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the standard imported salmon sample by using an amino acid analyzer, detecting each sample for three times by using the amino acid analyzer, and calculating the average value of the amino acid contents collected for three times to obtain the amino acid content data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final amino acid data of imported salmon samples;
the content of the amino acid in the salmon is related to factors such as variety, sex, age, muscle part, culture environment and the like, and the content of the amino acid in the muscle is influenced by the environment obviously for the same variety and age. The origin differential analysis mainly aims to search the specific indexes for representing the salmon from different regional sources. Therefore, the invention introduces the determination of the amino acid content to distinguish imported salmon of different countries. The salmon has high nutritive value, contains abundant amino acid types, and Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids are main amino acid types in the salmon, so in order to comprehensively analyze the difference of salmon imported from various countries, the invention detects Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids.
Specifically, the amino acid determination is carried out by adopting an L-8800 amino acid analyzer. Firstly, taking 2-4 g of the standard imported salmon sample, putting the sample into a hydrolysis tube, adding 50ml of 6mol/L hydrochloric acid, vacuumizing and sealing the hydrolysis tube, hydrolyzing the sample for 24 hours in a constant-temperature environment at 110 ℃, and filtering after cooling. Adjusting the pH value of the filtrate to be neutral, fixing the volume to 125ml, mixing the filtrate with 0.02mol/L hydrochloric acid according to a ratio of 1:1, filtering the mixed solution through a microporous filter membrane, and then measuring the content of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the mixed solution by adopting an L-8800 amino acid analyzer.
The content value of the amino acid can be influenced by factors such as environment, collection conditions and the like, so that the problem that imported salmon sample data are inaccurate is caused. Therefore, before the source tracing of the origin of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
According to the method, singular point samples are removed according to the variance and standard deviation of the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in salmon samples. When the variance and standard deviation of any value of the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids exceed a certain threshold value, the sample is proved to have large amplitude deviating from other samples of the same origin, and is probably a singular point sample to be removed.
Therefore, the invention calculates the average value of the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in 200 samples of the imported salmon at each producing area, and further calculates the variance and standard deviation of each sample of the imported salmon. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
It should be noted that the sequence of steps S2, S3, S4 and S5 is not limited, and the infrared spectrum data, isotope mass spectrometry data, mineral element data and amino acid data of the imported salmon sample may be collected sequentially according to any sequence, or may be collected simultaneously.
S6, establishing a support vector machine classifier, segmenting infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of the imported salmon sample, selecting 1/n sample data as a test set, taking the rest sample data as a training set, and continuously training the classifier based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data to obtain the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data;
because imported salmon is imported in-process, the time spent is long, and the in-process environmental difference of transportation is big, current traceability technique exists stable isotope technique, mineral element, amino acid etc. and is influenced by the measuring environment greatly, near infrared spectroscopy technique relatively relies on the database, need the source and the quantity of a large amount of samples just can improve the precision scheduling problem of tracing to a certain extent, if directly apply to imported salmon with current traceability technique, the precision of tracing to a low level. Therefore, the method provided by the invention can trace the origin of the imported salmon by combining infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid, overcomes the influence of the imported salmon in the transportation process and improves the tracing precision by combining four tracing modes.
According to the method, after infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of the imported salmon sample are collected, the sample data are respectively processed, namely, the method respectively trains and obtains corresponding traceability models based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the imported salmon sample.
The classification performance of the support vector machine depends on the selection of the kernel function, and the Gaussian radial basis kernel function has smaller Hamming distance and generalization error after model correction and parameter optimization. Therefore, the present invention selects the Gaussian radial basis as the kernel function of the support vector machine classifier.
In the optimal parameter interval, initial values of a Gaussian radial basis kernel function parameter sigma and a complexity parameter C are randomly set, the initial population scale is 200, the genetic evolution algebra is 300, and a self-cognition factor C is performed 1 A social cognition factor c of 5 2 A classifier parameter of 1.5 with a weight factor w of 0.78 was found to be optimal. In each genetic evolution, the average accuracy of 300 times of cross validation of different K values of the particles is calculated and used as the fitness of the particles, then the population optimization and the individual optimization are updated, finally the particles are sorted in a descending order according to the fitness, the first half of the particles which are more excellent directly enter the next evolution, and the second half of the particles which are worse are sequentially randomly crossed with the particles in the first half for inheritance, so that the problem of falling into the local optimization is avoided by improving the convergence speed of the model.
The invention respectively generates corresponding devices based on a support vector machine based on infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data.
S7, cross-validation of the performance of classifiers based on infrared spectral data, classifiers based on isotope mass spectral data, classifiers based on mineral element data and classifiers based on amino acid data;
in the invention, a sample data set is randomly divided into K subsets (generally, equal division), one subset is used as a verification set, and the rest K-1 groups of subsets are used as training sets; and taking the K subsets as verification sets in turn, alternately repeating the K subsets for K times to obtain K results, and taking the average value of the K results as the performance index of the classifier or the model.
That is, the invention alternately carries out cross validation on the classifier of infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data to obtain the performance of each model. The invention indicates the performance of the model through the accuracy of the tracing.
S8, sorting the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data according to performance, and giving corresponding weight to the classifiers according to performance ranking;
the method adopts the accuracy to indicate the performance of the model, so that the higher the accuracy is, the better the performance of the classifier is, and the higher the tracing precision is. According to the method, the imported salmon is comprehensively traced through the four classifiers, so that different weights are given to different classifiers, and the weights represent the influence of the classifiers on the final tracing result. The higher the weight, the greater its impact on the traceability results. Thus, the higher ranked classifiers are weighted more heavily, assuming that the classifier based on infrared spectral data, the classifier based on isotope mass spectral data, the classifier based on mineral element data, and the classifier based on amino acid data are weighted by ω, respectively 1 、ω 2 、ω 3 、ω 4 And then:
ω 1 +ω 2 +ω 3 +ω 4 =1
s9, detecting imported salmon by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data respectively, and calculating the similarity of infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of a detection sample and salmon in each country respectively;
when the origin of salmon from an unknown source is identified, measuring near-infrared characteristic spectrum data, stable isotope mass spectrum data, mineral element data and amino acid data of the salmon in an unknown country to be detected according to the steps S1, S2, S3 and S4, respectively substituting the measured data into a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and detecting the similarity between the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the salmon in the unknown country and the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the salmon in each country. When the corresponding data are completely the same, the similarity is 1, and when they are completely different, the similarity is 0. The range of the similarity s is: [0,1].
And S10, calculating the weighted sum of similarity results obtained by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data and corresponding classifiers, comparing the weighted sum with a set threshold value, and judging the producing area of the imported salmon.
The invention carries out mixed identification through a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and the respective similarity results are assumed to be r respectively 1 、r 2 、r 3 、r 4 Then, the final detection result of the classifier is:
r=r 1 *ω 1 +r 2 *ω 2 +r 3 *ω 3 +r 4 *ω 4
and comparing the final detection result with a set threshold, and if the set threshold is 0.75, when the calculated detection result is greater than the set threshold, the salmon imported from the surface is imported from the corresponding country, otherwise, the salmon imported from the surface is not imported from the corresponding country.
Example two
As shown in fig. 2, the present embodiment proposes a mixed identification system for producing imported salmon, comprising:
the pretreatment module is used for collecting salmon samples of different countries, crushing and drying the salmon samples, grinding the salmon samples after drying, filtering by using a sieve plate with a fixed size, and drying again to obtain standard imported salmon samples;
at present, salmon is imported from Norway, Sweden, America, Chilean, Poland, France, British, Canada and Russia. Therefore, for competitive breeding of the identification of the producing area, the present invention collected salmon in 9 countries of norway, sweden, usa, chile, polish, france, uk, canada, russia, 200 portions of salmon per country, 500g each.
In order to more accurately trace the source of imported salmon, pretreatment of salmon samples is required. The sample was first diced, crushed in a trough mixer, and crushed in a dark environment for about two hours. After the salmon is crushed, the salmon is dried, and the salmon can be completely dried in a drying chamber for 24 hours. According to the invention, the imported salmon is firstly crushed and then dried, so that the drying effect of the salmon can be improved.
A near infrared spectrum acquisition module for acquiring the near infrared spectrum of the standard imported salmon sample by using an infrared spectrometer, wherein the wave number range of the acquired scanning is 8000-4000cm -1 Resolution of 4cm -1 The scanning temperature is maintained at 25 ℃, the humidity is controlled to be kept stable, the spectrum of each sample is scanned for three times, and the average value of the spectrum data acquired for three times is obtained to obtain the spectrum data of each imported salmon sample; according to the variance and standard deviation of the near infrared spectrum of the salmon sample, rejecting salmonPerforming outlier sampling to obtain final near infrared spectrum data of the imported salmon sample;
the near-infrared light is a section of electromagnetic wave with a wavelength between visible light and mid-infrared light, and the wavelength range of the electromagnetic wave is 780-2526 nm. The near infrared spectrum can reflect the interaction between infrared rays and substances in imported salmon samples, in nature, the composition and the structure of each molecule are different, the absorption effects of different internal functional groups or chemical bonds such as O-H, C-H, N-H and S-H groups on red external light are different, and after the hydrogen groups absorb partial energy in the near infrared light again, the hydrogen groups are excited to generate transition, so that the positions and the absorption intensities of curves displayed on the near infrared spectrum are different, and the near infrared spectrum is generated in a near infrared spectrometer, and the characteristic near infrared absorption spectrum of each sample is obtained.
The near infrared spectrum reflects the information of the composition and content of organic matter in the sample. Imported salmon samples from different producing areas are influenced by factors such as varieties, producing area environments, processing methods and transportation modes, and also by factors such as growing environments, climates, soil and water quality, so that the structure and the content of main chemical components (such as protein, fat and water) of the food have certain difference, and the organic matter components of the food have obvious difference. In addition, the animal bodies in the respective production places differ in substance components such as protein, fat, and water due to differences in genotype, feed type, feeding method, individual metabolism, and the like. On the near infrared spectrum, these differences are reflected and hence a near infrared absorption spectrum characteristic of the sample for each origin.
The invention utilizes an infrared spectrometer to collect the near infrared spectrum of the standard salmon sample, takes 1-3 g of the standard imported salmon sample for spectrum collection, and the wave number range of the collected scanning is 8000-4000cm -1 Resolution of 4cm -1 And the scanning temperature is maintained at 25 ℃, the humidity is controlled to be kept stable, the spectrum of each sample is scanned for three times, and the average value of the three acquired spectrum data is obtained to obtain the spectrum data of each imported salmon sample. The invention can avoid the single spectrum number by collecting the spectrum data of each imported salmon sample for multiple timesAccording to the error in the acquisition process.
In addition, as the imported salmon is greatly influenced by the environment, the influence of different scanning environments on the spectral data is different, and therefore, when different imported salmon samples are scanned for multiple times, the scanning environment is kept constant.
In the process of making an imported salmon sample, the problem that imported salmon sample data is inaccurate due to pollution or the influence of factors such as equipment and environment on the near infrared spectrum in the collection process may exist. Therefore, before the source tracing of the origin of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
The method adopts the variance and standard deviation of the near infrared spectrum of the salmon sample to remove singular point samples. Near infrared spectra of imported salmon in the same producing area generally show similar characteristics, and the difference between spectra acquired by different imported salmon samples is small. Therefore, the method utilizes the variances and standard deviations of the near infrared spectra of different salmon samples to compare, and when the variance and standard deviation of a certain near infrared spectrum exceed a certain threshold value, the sample is proved to have large amplitude deviating from other samples in the same producing area, and the sample is probably a singular point sample to be removed.
Therefore, the invention calculates the average value of the infrared spectrum of 200 samples of the salmon imported from each producing area, and further calculates the variance and standard deviation of each sample of the salmon imported from each producing area. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
An isotope collection module for detecting delta in the standard imported salmon sample using an isotope ratio mass spectrometer 13 C、δ 18 O、δ 15 Detecting each sample by using an isotope ratio mass spectrometer for three times, and calculating the average value of isotope mass spectrum data acquired for the three times to obtain isotope mass spectrum data of each imported salmon sample; according to the variance and standard deviation of the isotope mass spectrum data of the salmon sample, singular point samples are removed to obtain the final imported threeIsotope mass spectrometry data of the salmon sample;
the principle of tracing the origin of the stable isotope technology is to identify the origin of a target sample by utilizing the natural fractionation effect of the isotope. Due to the difference of air temperature, sunlight, soil, foodstuff, air quality and the like, the isotopic abundance of a certain element in the target sample is obviously different from other samples in different producing areas, so that the producing area tracing of the animal-derived agricultural products can be accurately distinguished. In particular by stabilizing isotopes 13 C and 12 the ratio of C can be used for characterizing the feed types, and the ratio of C to C in the feed 3 、C 4 The proportion of the plants is closely related; in isotope of 15 N and 14 the proportion of N is influenced by a plurality of factors, mainly depends on the nutrition level, is closely related to the feed variety, can also indicate the difference in soil, climate and agricultural fertilization, and is even related to the proportion of marine and land plants in the feed; in addition to the isotopes 18 O and 16 ratio of O and 2 h and 1 the proportion of H is related to the climate, the terrain, the evaporation, the concentration and the sedimentation of water in the producing area; in isotope 34 S and 32 the proportion of S is related to microbial action and marine factors.
The salmon feed, drinking water, soil, climate and the like imported from different countries are completely different. Especially the carbon, nitrogen and hydrogen isotopes have extremely significant correlation, delta 13 C、δ 18 O、δ 15 N is used as the main index of the salmon in the zone of the invention, wherein delta 13 C reflects the ratio of C3 and C4 plants in the feed, while delta 18 The O composition is related to the climate and water of the country, delta 15 N reacts with the soil conditions of the country where the imported salmon is located.
Detecting delta in the standard imported salmon sample 13 The value of C: putting 2-4 g of each standard imported salmon sample into a tin foil cup, feeding the standard imported salmon sample into an element analyzer through an automatic sampler, and combusting the imported salmon sample to convert the imported salmon sample into pure CO 2 And N 2 ,CO 2 Diluting with diluter to obtain CO 2 Sending the sample into an isotope ratio mass spectrometer for detection. Wherein the temperature of the combustion furnace is 1200 ℃, and the temperature of the reduction furnace is 600 ℃.
Detecting delta in the standard imported salmon sample 18 The value of O: 2-4 g of each standard imported salmon sample is put into a silver cup, balanced for 72 hours, put into an automatic sample injector in sequence, and then put into an element analyzer through the automatic sample injector to crack the imported salmon sample into C, H 2 、O 2 Finally, will be O 2 Sending the sample into an isotope ratio mass spectrometer for detection. Wherein the temperature of the cracking is 2500 ℃.
Detecting delta in the standard imported salmon sample 15 The value of N: putting 2-4 g of each standard imported salmon sample into a tin foil cup, feeding the standard imported salmon sample into an element analyzer through an automatic sampler, and combusting the imported salmon sample to convert the imported salmon sample into pure CO 2 And N 2 Finally, will N 2 Sending the sample into an isotope ratio mass spectrometer for detection. Wherein the temperature of the combustion furnace is 1200 ℃, and the temperature of the reduction furnace is 600 ℃.
Delta in salmon sample at inlet of each sample 13 C、δ 18 O、δ 15 The values of N are collected for three times, and the average value of the data collected for three times is obtained to obtain the delta in each imported salmon sample 13 C、δ 18 O、δ 15 The value of N. The invention collects the middle delta of each imported salmon sample for multiple times 13 C、δ 18 O、δ 15 And the value of N can avoid errors in a single data acquisition process. Isotope ratio mass spectrometer
As with near infrared spectral collection, delta 13 C、δ 18 O、δ 15 The value of N can also be influenced by factors such as environment, collection conditions and the like, so that the problem that the sample data of imported salmon is inaccurate is caused. Therefore, before the origin tracing of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
The invention is based on salmon sample delta 13 C、δ 18 O、δ 15 Of NAnd eliminating singular point samples according to the variance and the standard deviation. As long as delta 13 C、δ 18 O、δ 15 And when the variance and the standard deviation of any value of N exceed a certain threshold value, the sample is large in amplitude deviating from other samples in the same place of origin, and the sample is likely to be a singular point sample to be removed.
Therefore, the present invention calculates the delta of 200 samples of salmon imported from each production area 13 C、δ 18 O、δ 15 And N, further calculating the variance and standard deviation of each imported salmon sample. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
The mineral element acquisition module is used for detecting the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer, detecting each sample by using the plasma mass spectrometer for three times, and calculating the average value of the mineral element data acquired for three times to obtain the mineral element data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final imported salmon sample mineral element data;
the content of each element in the salmon is closely related to conditions such as water source, climate and the like of a product producing area, and different areas have characteristic element compositions, so that the mineral element fingerprint spectrums of imported salmon with different producing areas can be established, and the more accurate tracing of the producing area of the imported salmon is realized. The mineral element fingerprint spectrum technology is characterized in that according to the measured values of macroelements (calcium, phosphorus, magnesium, potassium, sodium, chlorine, sulfur and the like) and mineral elements (iron, copper, manganese, zinc, iodine, selenium, chromium and the like) in an imported salmon sample, elements with obvious differences are selected through statistical analysis to establish a model, and therefore the producing area of the imported salmon can be identified more accurately.
The salmon living environment is complex and is highly influenced by the environment. Different salmon origins may have only slight differences in the content of some elements. Therefore, the content of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample is detected by using a plasma mass spectrometer so as to comprehensively analyze elements contained in the salmon. Slight differences between salmon from different origins were identified.
Detecting the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer specifically comprises the following steps: taking 2-4 g of each standard imported salmon sample, putting the sample into a digestion tube, carrying out pre-digestion for 2 hours by using concentrated nitric acid, then carrying out disinfection for 1 hour by using hydrogen peroxide, and finally putting the sample into a microwave digestion instrument for digestion. Collecting Ca, Cl, Mg, P, K, Na, Cu, Fe and Se by using an ion mass spectrometer, and finally quantifying the collected Ca, Cl, Mg, P, K, Na, Cu, Fe and Se by using an external standard method to measure the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se.
And (3) collecting the content values of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the salmon sample imported from each sample for three times, and averaging the data collected for three times to obtain the content values of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the salmon sample imported from each sample. According to the method, the content values of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in each imported salmon sample are collected for multiple times, so that errors in a single data collection process can be avoided.
Ca. The content values of Cl, Mg, P, K, Na, Cu, Fe and Se can be influenced by factors such as environment, collection conditions and the like, so that the sample data of imported salmon is inaccurate. Therefore, before the origin tracing of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
According to the method, singular point samples are removed according to the variances and standard deviations of the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se of the salmon samples. When the variance and standard deviation of any value of the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se exceed a certain threshold value, the sample is indicated to be deviated from other samples in the same place by a large amplitude, and the sample is probably a singular point sample and is removed.
Therefore, the invention calculates the average value of the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se of 200 samples of the salmon imported from each producing area, and further calculates the variance and standard deviation of each sample of the salmon imported from each producing area. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
The amino acid acquisition module is used for detecting the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the standard imported salmon sample by using an amino acid analyzer, each sample is detected for three times by using the amino acid analyzer, and the amino acid content data of each imported salmon sample is obtained by averaging the amino acid contents collected for three times; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final amino acid data of imported salmon samples;
the content of the amino acid in the salmon is related to factors such as variety, sex, age, muscle part, culture environment and the like, and the content of the amino acid in the muscle is influenced by the environment obviously for the same variety and age. The origin differential analysis mainly aims to search the specific indexes for representing the salmon from different regional sources. Therefore, the invention introduces the determination of the amino acid content to distinguish imported salmon of different countries. The salmon has high nutritive value, contains abundant amino acid types, and Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids are main amino acid types in the salmon, so in order to comprehensively analyze the difference of salmon imported from various countries, the invention detects Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids.
Specifically, the amino acid determination is carried out by adopting an L-8800 amino acid analyzer. Firstly, taking 2-4 g of the standard imported salmon sample, putting the sample into a hydrolysis tube, adding 50ml of 6mol/L hydrochloric acid, vacuumizing and sealing the hydrolysis tube, hydrolyzing the sample for 24 hours in a constant-temperature environment at 110 ℃, and filtering after cooling. Adjusting the pH value of the filtrate to be neutral, fixing the volume to 125ml, mixing the filtrate with 0.02mol/L hydrochloric acid according to a ratio of 1:1, filtering the mixed solution through a microporous filter membrane, and then measuring the content of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the mixed solution by adopting an L-8800 amino acid analyzer.
The content value of amino acid may be influenced by factors such as environment and collection conditions, so that the sample data of imported salmon is inaccurate. Therefore, before the origin tracing of the imported salmon is carried out by using sample data, singular point samples appearing in the sample process are removed, and the influence of the singular point samples on the source tracing result is avoided.
According to the method, singular point samples are removed according to the variance and standard deviation of the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in salmon samples. When the variance and standard deviation of any value of the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids exceed a certain threshold value, the sample is proved to have large amplitude deviating from other samples of the same origin, and is probably a singular point sample to be removed.
Therefore, the invention calculates the average value of the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in 200 samples of the imported salmon at each producing area, and further calculates the variance and standard deviation of each sample of the imported salmon. And when the variance and the standard deviation of the sample exceed set thresholds, removing the sample from the sample set.
The classifier establishing module is used for establishing a support vector machine classifier, segmenting the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the imported salmon sample, selecting 1/n sample data as a test set, taking the rest sample data as a training set, continuously training the classifier based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data respectively, and obtaining the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data;
because imported salmon is imported in-process, the time spent is long, and the in-process environmental difference of transportation is big, current traceability technique exists stable isotope technique, mineral element, amino acid etc. and is influenced by the measuring environment greatly, near infrared spectroscopy technique relatively relies on the database, need the source and the quantity of a large amount of samples just can improve the precision scheduling problem of tracing to a certain extent, if directly apply to imported salmon with current traceability technique, the precision of tracing to a low level. Therefore, the method provided by the invention can trace the origin of the imported salmon by combining infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid, overcomes the influence of the imported salmon in the transportation process and improves the tracing precision by combining four tracing modes.
According to the method, after infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of the imported salmon sample are collected, the sample data are respectively processed, namely, the method respectively trains and obtains corresponding traceability models based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the imported salmon sample.
The classification performance of the support vector machine depends on the selection of the kernel function, and the Gaussian radial basis kernel function has smaller Hamming distance and generalization error after model correction and parameter optimization. Therefore, the present invention selects the Gaussian radial basis as the kernel function of the support vector machine classifier.
In the optimal parameter interval, the initial values of the Gaussian radial basis kernel function parameter sigma and the complexity parameter C are randomly set, the initial population scale is 200, the genetic evolution algebra is 300, and the self-cognition factor C is carried out 1 Social cognition factor c of 5 2 A classifier parameter of 1.5 with a weight factor w of 0.78 was found to be optimal. In each genetic evolution, the average accuracy of 300 times of cross validation of different K values of the particles is calculated and used as the fitness of the particles, then the population optimization and the individual optimization are updated, finally the particles are sorted in a descending order according to the fitness, the first half of the particles with the superiority directly enter the next evolution, and the second half of the particles with the poorer fitness directly enter the next evolutionThe seeds are sequentially randomly crossed and inherited with the particles in the first half, so that the speed of model convergence is improved, and the problem of falling into local optimum is avoided.
The invention respectively generates corresponding devices based on a support vector machine based on infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data.
The verification evaluation module is used for cross verifying the performance of a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data;
in the invention, a sample data set is randomly divided into K subsets (generally, equal division), one subset is used as a verification set, and the rest K-1 groups of subsets are used as training sets; and taking the K subsets as verification sets in turn, alternately repeating the K subsets for K times to obtain K results, and taking the average value of the K results as the performance index of the classifier or the model.
That is, the invention alternately carries out cross validation on the classifier of infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data to obtain the performance of each model. The invention indicates the performance of the model through the accuracy of the tracing.
The sorting module is used for sorting the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data according to performance and giving corresponding weight to the classifiers according to performance ranking;
the method adopts the accuracy to indicate the performance of the model, so that the higher the accuracy is, the better the performance of the classifier is, and the higher the tracing precision is. According to the method, the imported salmon is comprehensively traced through the four classifiers, so that different weights are given to different classifiers, and the weights represent the influence of the classifiers on the final tracing result. The higher the weight, the greater its impact on the traceability results. Thus, the higher ranked classifiers are weighted more heavily, assuming classifiers based on infrared spectral data, classifiers based on isotope mass spectral data, mineral-basedThe weight of the element data classifier and the amino acid data-based classifier is omega 1 、ω 2 、ω 3 、ω 4 And then:
ω 1 +ω 2 +ω 3 +ω 4 =1
the detection module is used for detecting imported salmon by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data respectively, and calculating the similarity of infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of a detection sample and salmon in each country respectively;
when the origin of salmon from an unknown source is identified, measuring near-infrared characteristic spectrum data, stable isotope mass spectrum data, mineral element data and amino acid data of the salmon in an unknown country to be detected according to the steps S1, S2, S3 and S4, respectively substituting the measured data into a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and detecting the similarity between the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the salmon in the unknown country and the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the salmon in each country. When the corresponding data are completely the same, the similarity is 1, and when they are completely different, the similarity is 0. The range of the similarity s is: [0,1].
And the comprehensive source tracing module is used for calculating the weighted sum of similarity results obtained by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data and corresponding classifiers, comparing the weighted sum with a set threshold value and judging the producing area of the imported salmon.
The invention performs mixed identification through a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and supposing thatThe respective similarity results are r 1 、r 2 、r 3 、r 4 Then, the final detection result of the classifier is:
r=r 1 *ω 1 +r 2 *ω 2 +r 3 *ω 3 +r 4 *ω 4
and comparing the final detection result with a set threshold, and if the set threshold is 0.75, when the calculated detection result is greater than the set threshold, the salmon imported from the surface is imported from the corresponding country, otherwise, the salmon imported from the surface is not imported from the corresponding country.
Therefore, the mixed identification method and system for the producing areas of the imported salmon can detect the imported salmon, and have the advantages of wide application range and high application value. By combining the four tracing modes, the influence of imported salmon in the transportation process is overcome, and the tracing precision is improved; meanwhile, the four tracing modes are sequenced according to the performance, corresponding weights are given to different tracing modes according to the sequencing result, the influence of the tracing modes on the comprehensive tracing result can be adjusted according to the performance of the tracing model, the advantages of the tracing modes are fully exerted, and the tracing modes are not simply mixed. The method further improves the precision and efficiency of tracing by utilizing the advantages of minimum structured risk and excellent generalization capability of the support vector machine. In addition, the imported salmon is firstly crushed and then dried, so that the drying effect of the salmon can be improved. The invention can avoid the error in the single spectral data acquisition process by acquiring the spectral data, the isotope data, the mineral element data and the amino acid data of each imported salmon sample for multiple times. The method calculates the corresponding variance and standard deviation of the acquired spectral data, isotope data, mineral element data and amino acid data of each imported salmon sample, eliminates the corresponding singular point sample, and avoids the influence of the acquisition environment and the like on the data.
It is to be noted that the foregoing is only illustrative of the preferred embodiments of the present invention and the technical principles employed. It will be understood by those skilled in the art that the present invention is not limited to the particular embodiments described herein, but is capable of various obvious changes, rearrangements and substitutions as will now become apparent to those skilled in the art without departing from the scope of the invention. Therefore, although the present invention has been described in greater detail by the above embodiments, the present invention is not limited to the above embodiments, and may include other equivalent embodiments without departing from the spirit of the present invention, and the scope of the present invention is determined by the scope of the appended claims.
Claims (5)
1. A mixed identification method for producing areas of imported salmon is characterized by comprising the following steps:
s1, collecting salmon samples of different countries, crushing and drying the salmon samples, grinding the salmon samples after drying, filtering by using a sieve plate with a fixed size, and drying again to obtain standard imported salmon samples;
s2, collecting the near infrared spectrum of the standard imported salmon sample by using an infrared spectrometer, wherein the wave number range of the collected scanning is 8000-4000cm < -1 >, the resolution is 4cm < -1 >, the scanning temperature is maintained at 25 ℃, the humidity is controlled to be stable, the spectrum of each sample is scanned three times, and the average value of the collected spectrum data of the three times is obtained to obtain the spectrum data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the near infrared spectrum of the salmon sample to obtain final near infrared spectrum data of the imported salmon sample;
s3, detecting the values of delta 13C, delta 18O and delta 15N in the standard imported salmon sample by using an isotope ratio mass spectrometer, detecting each sample three times by using the isotope ratio mass spectrometer, and averaging the isotope mass spectrum data acquired three times to obtain the isotope mass spectrum data of each imported salmon sample; according to the variance and standard deviation of the salmon sample isotope mass spectrum data, removing singular point samples to obtain final imported salmon sample isotope mass spectrum data;
s4, detecting the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer, detecting each sample by using the plasma mass spectrometer three times, and averaging the mineral element data acquired three times to obtain the mineral element data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final imported salmon sample mineral element data;
s5, detecting the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the standard imported salmon sample by using an amino acid analyzer, detecting each sample for three times by using the amino acid analyzer, and calculating the average value of the amino acid contents collected for three times to obtain the amino acid content data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final amino acid data of imported salmon samples;
s6, establishing a support vector machine classifier, segmenting infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of the imported salmon sample, selecting sample data of a test set, taking the rest sample data as a training set, and continuously training the classifier based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data to obtain the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data;
s7, cross-verifying the performance of the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data;
s8, sorting the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data according to performance, and giving corresponding weight to the classifiers according to performance ranking;
s9, detecting imported salmon by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data respectively, and calculating the similarity of infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of a detection sample and salmon in each country respectively;
s10, calculating the weighted sum of similarity results obtained by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data and corresponding classifiers, comparing the weighted sum with a set threshold value, and judging the producing area of the imported salmon;
the method for crushing and drying the salmon sample specifically comprises the following steps:
dicing imported salmon samples, and putting the diced salmon samples into a groove-shaped mixer to be crushed for two hours in a dark environment; after the salmon is crushed, putting the salmon into a drying chamber for completely drying for 24 hours;
the singular point eliminating sample specifically comprises the following steps:
calculating the average value of the detection data content of the salmon sample imported from each producing area, and removing the sample from the sample set when the variance and standard deviation of the sample exceed a set threshold value; the detection data comprises infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data;
the step S7 specifically includes:
randomly dividing a sample data set into K subsets, wherein one subset is used as a verification set, and the rest K-1 subsets are used as training sets; taking K subsets as verification sets in turn, repeating the verification sets for K times in a crossed manner to obtain K results, and taking the average value of the K results as the performance index of the classifier;
the corresponding weight given to the classifier according to the performance ranking is specifically as follows:
assuming that the weights of the classifier based on infrared spectral data, the classifier based on isotope mass spectral data, the classifier based on mineral element data, and the classifier based on amino acid data are ω 1, ω 2, ω 3, and ω 4, respectively:
ω 1 +ω 2 +ω 3 +ω 4 =1
the better the performance of the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data is, the larger the weight is;
the step S10 specifically includes:
performing mixed identification by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and assuming that similarity results are r1, r2, r3 and r4 respectively, the final detection result of the classifier is as follows:
r=r 1 *ω 1 +r 2 *ω 2 +r 3 *ω 3 +r 4 *ω 4
and when r is larger than a set threshold value, importing the salmon to the corresponding country, otherwise not importing the salmon to the corresponding country.
2. An imported salmon origin mixed identification system, comprising:
the pretreatment module is used for collecting salmon samples of different countries, crushing and drying the salmon samples, grinding the salmon samples after drying, filtering by using a sieve plate with a fixed size, and drying again to obtain standard imported salmon samples;
the near infrared spectrum acquisition module is used for acquiring the near infrared spectrum of the standard imported salmon sample by using an infrared spectrometer, the wave number range of the acquired scanning is 8000-4000cm < -1 >, the resolution is 4cm < -1 >, the scanning temperature is maintained at 25 ℃, the humidity is controlled to be stable, the spectrum of each sample is scanned for three times, and the average value of the acquired spectrum data of the three times is obtained to obtain the spectrum data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the near infrared spectrum of the salmon sample to obtain final near infrared spectrum data of the imported salmon sample;
the isotope collection module is used for detecting the values of delta 13C, delta 18O and delta 15N in the standard imported salmon sample by using an isotope ratio mass spectrometer, detecting each sample by using the isotope ratio mass spectrometer for three times, and calculating the average value of isotope mass spectrum data acquired for the three times to obtain the isotope mass spectrum data of each imported salmon sample; according to the variance and standard deviation of the salmon sample isotope mass spectrum data, removing singular point samples to obtain final imported salmon sample isotope mass spectrum data;
the mineral element acquisition module is used for detecting the contents of Ca, Cl, Mg, P, K, Na, Cu, Fe and Se in the standard imported salmon sample by using a plasma mass spectrometer, detecting each sample by using the plasma mass spectrometer for three times, and calculating the average value of the mineral element data acquired for three times to obtain the mineral element data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final imported salmon sample mineral element data;
the amino acid acquisition module is used for detecting the contents of Asp, Thr, Ser, Glu, Gly, Ala, Cys, Val, Met, Ile, Leu, Tyr, Phe, Lys, His, Arg, Pro and Trp18 amino acids in the standard imported salmon sample by using an amino acid analyzer, each sample is detected three times by using the amino acid analyzer, and the average value of the contents of the amino acids collected three times is obtained to obtain the amino acid content data of each imported salmon sample; removing singular point samples according to the variance and standard deviation of the salmon sample and mineral element data to obtain final amino acid data of imported salmon samples;
the classifier establishing module is used for establishing a support vector machine classifier, segmenting the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data of the imported salmon sample, selecting the sample data of a test set, taking the rest sample data as a training set, and continuously training the classifier based on the infrared spectrum data, the isotope mass spectrum data, the mineral element data and the amino acid data to obtain the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data;
the verification evaluation module is used for cross verifying the performance of a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data; the sorting module is used for sorting the classifier based on the infrared spectrum data, the classifier based on the isotope mass spectrum data, the classifier based on the mineral element data and the classifier based on the amino acid data according to performance and giving corresponding weight to the classifiers according to performance ranking;
the detection module is used for detecting imported salmon by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data respectively, and calculating the similarity of infrared spectrum data, isotope mass spectrum data, mineral element data and amino acid data of a detection sample and salmon in each country respectively;
and the comprehensive source tracing module is used for calculating the weighted sum of similarity results obtained by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data and corresponding classifiers, comparing the weighted sum with a set threshold value and judging the producing area of the imported salmon.
3. The hybrid salmon origin discrimination system of claim 2, wherein said establishing a support vector machine classifier comprises: in the optimal parameter interval, randomly setting initial values of a Gaussian radial basis kernel function parameter sigma and a complexity parameter C, and optimizing classifier parameters with the initial population scale of 200, the genetic evolution algebra of 300, the self-cognition factor C1 of 1.5, the social cognition factor C2 of 1.5 and the weight factor w of 0.78; in each genetic evolution, the average accuracy of 300 times of cross validation of different K values of the particles is calculated and used as the fitness of the particles, then the population optimization and the individual optimization are updated, finally the particles are sorted in a descending order according to the fitness, the first half of the particles which are more excellent directly enter the next evolution, and the second half of the particles which are worse are sequentially randomly crossed with the particles in the first half for genetic inheritance.
4. The salmon habitat hybrid identification system of claim 2, wherein the corresponding weights given to the classifiers according to the performance ranking are specifically: assuming that the weights of the classifier based on infrared spectral data, the classifier based on isotope mass spectral data, the classifier based on mineral element data, and the classifier based on amino acid data are ω 1, ω 2, ω 3, and ω 4, respectively:
ω1+ω2+ω3+ω4=1
the better the performance of the classifier based on infrared spectrum data, the classifier based on isotope mass spectrum data, the classifier based on mineral element data and the classifier based on amino acid data is, the larger the weight is.
5. The salmon origin hybrid identification system of claim 4, wherein the comprehensive traceability module comprises:
performing mixed identification by using a classifier based on infrared spectrum data, a classifier based on isotope mass spectrum data, a classifier based on mineral element data and a classifier based on amino acid data, and assuming that similarity results are r1, r2, r3 and r4 respectively, the final detection result of the classifier is as follows:
r=r1*ω1+r2*ω2+r3*ω3+r4*ω4
and when r is larger than a set threshold value, importing the salmon to the corresponding country, otherwise not importing the salmon to the corresponding country.
Priority Applications (2)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911141295.3A CN110954499B (en) | 2019-11-20 | 2019-11-20 | Mixed identification method and system for producing areas of imported salmon |
JP2020007330A JP6712691B1 (en) | 2019-11-20 | 2020-01-21 | Method and system for distinguishing mixed salmon production areas |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201911141295.3A CN110954499B (en) | 2019-11-20 | 2019-11-20 | Mixed identification method and system for producing areas of imported salmon |
Publications (2)
Publication Number | Publication Date |
---|---|
CN110954499A CN110954499A (en) | 2020-04-03 |
CN110954499B true CN110954499B (en) | 2022-08-02 |
Family
ID=69977949
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201911141295.3A Active CN110954499B (en) | 2019-11-20 | 2019-11-20 | Mixed identification method and system for producing areas of imported salmon |
Country Status (2)
Country | Link |
---|---|
JP (1) | JP6712691B1 (en) |
CN (1) | CN110954499B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111678973A (en) * | 2020-07-18 | 2020-09-18 | 上海海洋大学 | Method for rapidly identifying Atlantic salmon and rainbow trout based on mass spectrometry technology |
CN112485217B (en) * | 2020-12-02 | 2023-04-25 | 仲恺农业工程学院 | Construction method and device of meat identification model applied to origin tracing |
CN114414551B (en) * | 2022-01-21 | 2023-09-01 | 中国海洋大学 | Fish identification method based on LIBS-RAMAN spectrum technology |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103425996A (en) * | 2013-08-01 | 2013-12-04 | 华南理工大学 | Parallel distribution type large-scale image recognition method |
CN106560692A (en) * | 2016-10-20 | 2017-04-12 | 中国计量大学 | Wuyi rock tea production place identification method through combination of four detection technologies |
-
2019
- 2019-11-20 CN CN201911141295.3A patent/CN110954499B/en active Active
-
2020
- 2020-01-21 JP JP2020007330A patent/JP6712691B1/en not_active Expired - Fee Related
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103425996A (en) * | 2013-08-01 | 2013-12-04 | 华南理工大学 | Parallel distribution type large-scale image recognition method |
CN106560692A (en) * | 2016-10-20 | 2017-04-12 | 中国计量大学 | Wuyi rock tea production place identification method through combination of four detection technologies |
Non-Patent Citations (1)
Title |
---|
基于全局和局部特征集成的人脸识别;苏煜 等;《软件学报》;20100831;第21卷(第8期);第1851页第2段,第1853页第2.1节 * |
Also Published As
Publication number | Publication date |
---|---|
JP2021081406A (en) | 2021-05-27 |
CN110954499A (en) | 2020-04-03 |
JP6712691B1 (en) | 2020-06-24 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110954500B (en) | Mixed tracing method and system for producing area of imported beef | |
CN110954499B (en) | Mixed identification method and system for producing areas of imported salmon | |
Hassoun et al. | Fraud in animal origin food products: Advances in emerging spectroscopic detection methods over the past five years | |
Li et al. | Authentication of fishery and aquaculture products by multi-element and stable isotope analysis | |
CN108982692B (en) | Method for distinguishing milk powder producing area by element analysis-stable isotope mass spectrum | |
Makarewicz et al. | Dietary reconstruction, mobility, and the analysis of ancient skeletal tissues: Expanding the prospects of stable isotope research in archaeology | |
Aceto | The use of ICP-MS in food traceability | |
Chesson et al. | Applying the principles of isotope analysis in plant and animal ecology to forensic science in the Americas | |
CN107228924B (en) | A kind of adequate proteins processing peanut raw material quality determination and its evaluation method | |
Ye et al. | A comprehensive overview of emerging techniques and chemometrics for authenticity and traceability of animal-derived food | |
Pepi et al. | Relationship among geochemical elements in soil and grapes as terroir fingerprintings in Vitis vinifera L. cv.“Glera” | |
Monavar et al. | Determining quality of caviar from Caspian Sea based on Raman spectroscopy and using artificial neural networks | |
Wei et al. | Identification techniques and detection methods of edible fungi species | |
Li et al. | Assessment of elemental profiling for distinguishing geographic origin of aquacultured shrimp from India, Thailand and Vietnam | |
Danezis et al. | Elemental metabolomics: Food elemental assessment could reveal geographical origin | |
Aceto | Food forensics | |
Kong et al. | Hyperspectral imaging coupled with CNN: A powerful approach for quantitative identification of feather meal and fish by-product meal adulterated in marine fishmeal | |
CN111024802B (en) | Stichopus japonicus origin tracing model construction and identification method based on lead-Pb stable isotope | |
Magdas et al. | REEs–a possible tool for geographical origin assessment? | |
Boughattas et al. | Mid infrared spectroscopy combined with chemometric tools for the identification of canned tuna species in brine | |
Liu et al. | Application of stable isotopic and elemental composition combined with random forest algorithm for the botanical classification of Chinese honey | |
Nawi et al. | Application of artificial neural network classification to determine nutrient content in oil palm leaves | |
Santos et al. | Current trends in the traceability of geographic origin and detection of species-mislabeling in marine bivalves | |
CN108982570A (en) | A kind of edible oil quality discrimination method based on nuclear magnetic resonance technique | |
Baroccio et al. | Classification of biostimulants origin using amino acids composition of hydrolyzed proteins |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant |