CN110426366A - Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared - Google Patents
Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared Download PDFInfo
- Publication number
- CN110426366A CN110426366A CN201910745260.4A CN201910745260A CN110426366A CN 110426366 A CN110426366 A CN 110426366A CN 201910745260 A CN201910745260 A CN 201910745260A CN 110426366 A CN110426366 A CN 110426366A
- Authority
- CN
- China
- Prior art keywords
- meat
- visualization
- sample
- olfactory sensor
- adulterated
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 235000013372 meat Nutrition 0.000 title claims abstract description 97
- 238000012800 visualization Methods 0.000 title claims abstract description 52
- 238000001514 detection method Methods 0.000 title claims abstract description 46
- 238000012360 testing method Methods 0.000 claims abstract description 28
- 238000012549 training Methods 0.000 claims abstract description 21
- 238000000034 method Methods 0.000 claims abstract description 19
- 238000001228 spectrum Methods 0.000 claims abstract description 14
- 239000000126 substance Substances 0.000 claims description 19
- 235000015278 beef Nutrition 0.000 claims description 14
- 230000004044 response Effects 0.000 claims description 13
- CSCPPACGZOOCGX-UHFFFAOYSA-N Acetone Chemical compound CC(C)=O CSCPPACGZOOCGX-UHFFFAOYSA-N 0.000 claims description 12
- HEDRZPFGACZZDS-UHFFFAOYSA-N Chloroform Chemical compound ClC(Cl)Cl HEDRZPFGACZZDS-UHFFFAOYSA-N 0.000 claims description 12
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 11
- 239000002904 solvent Substances 0.000 claims description 9
- 210000002569 neuron Anatomy 0.000 claims description 8
- 230000008569 process Effects 0.000 claims description 8
- 230000006870 function Effects 0.000 claims description 7
- VYPSYNLAJGMNEJ-UHFFFAOYSA-N Silicium dioxide Chemical compound O=[Si]=O VYPSYNLAJGMNEJ-UHFFFAOYSA-N 0.000 claims description 6
- 235000019441 ethanol Nutrition 0.000 claims description 6
- 150000004032 porphyrins Chemical class 0.000 claims description 6
- 239000000741 silica gel Substances 0.000 claims description 6
- 229910002027 silica gel Inorganic materials 0.000 claims description 6
- 230000004927 fusion Effects 0.000 claims description 5
- 230000002209 hydrophobic effect Effects 0.000 claims description 5
- 239000007793 ph indicator Substances 0.000 claims description 5
- 239000000758 substrate Substances 0.000 claims description 5
- 230000004913 activation Effects 0.000 claims description 3
- 238000004519 manufacturing process Methods 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 229920003240 metallophthalocyanine polymer Polymers 0.000 claims description 2
- 230000035935 pregnancy Effects 0.000 claims description 2
- 235000013399 edible fruits Nutrition 0.000 claims 1
- 239000002184 metal Substances 0.000 claims 1
- 239000000203 mixture Substances 0.000 claims 1
- 239000010410 layer Substances 0.000 description 24
- 238000002329 infrared spectrum Methods 0.000 description 8
- 235000015277 pork Nutrition 0.000 description 8
- 238000005516 engineering process Methods 0.000 description 5
- 238000004458 analytical method Methods 0.000 description 3
- 238000006243 chemical reaction Methods 0.000 description 3
- 239000003795 chemical substances by application Substances 0.000 description 3
- 239000012141 concentrate Substances 0.000 description 3
- 239000000470 constituent Substances 0.000 description 3
- 235000013305 food Nutrition 0.000 description 3
- XEEYBQQBJWHFJM-UHFFFAOYSA-N Iron Chemical compound [Fe] XEEYBQQBJWHFJM-UHFFFAOYSA-N 0.000 description 2
- 230000008901 benefit Effects 0.000 description 2
- 230000007547 defect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000009826 distribution Methods 0.000 description 2
- 230000006872 improvement Effects 0.000 description 2
- 239000011229 interlayer Substances 0.000 description 2
- 229910044991 metal oxide Inorganic materials 0.000 description 2
- 150000004706 metal oxides Chemical class 0.000 description 2
- VOFUROIFQGPCGE-UHFFFAOYSA-N nile red Chemical compound C1=CC=C2C3=NC4=CC=C(N(CC)CC)C=C4OC3=CC(=O)C2=C1 VOFUROIFQGPCGE-UHFFFAOYSA-N 0.000 description 2
- FUTVBRXUIKZACV-UHFFFAOYSA-J zinc;3-[18-(2-carboxylatoethyl)-8,13-bis(ethenyl)-3,7,12,17-tetramethylporphyrin-21,24-diid-2-yl]propanoate Chemical compound [Zn+2].[N-]1C2=C(C)C(CCC([O-])=O)=C1C=C([N-]1)C(CCC([O-])=O)=C(C)C1=CC(C(C)=C1C=C)=NC1=CC(C(C)=C1C=C)=NC1=C2 FUTVBRXUIKZACV-UHFFFAOYSA-J 0.000 description 2
- FRPHFZCDPYBUAU-UHFFFAOYSA-N Bromocresolgreen Chemical compound CC1=C(Br)C(O)=C(Br)C=C1C1(C=2C(=C(Br)C(O)=C(Br)C=2)C)C2=CC=CC=C2S(=O)(=O)O1 FRPHFZCDPYBUAU-UHFFFAOYSA-N 0.000 description 1
- 239000004698 Polyethylene Substances 0.000 description 1
- 238000011529 RT qPCR Methods 0.000 description 1
- NUSORQHHEXCNQC-UHFFFAOYSA-N [Cu].N1C(C=C2N=C(C=C3NC(=C4)C=C3)C=C2)=CC=C1C=C1C=CC4=N1 Chemical compound [Cu].N1C(C=C2N=C(C=C3NC(=C4)C=C3)C=C2)=CC=C1C=C1C=CC4=N1 NUSORQHHEXCNQC-UHFFFAOYSA-N 0.000 description 1
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000002512 chemotherapy Methods 0.000 description 1
- 238000004587 chromatography analysis Methods 0.000 description 1
- 239000003086 colorant Substances 0.000 description 1
- 239000000975 dye Substances 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 235000011389 fruit/vegetable juice Nutrition 0.000 description 1
- 238000010348 incorporation Methods 0.000 description 1
- 239000004615 ingredient Substances 0.000 description 1
- 229910052742 iron Inorganic materials 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 235000013622 meat product Nutrition 0.000 description 1
- CEQFOVLGLXCDCX-WUKNDPDISA-N methyl red Chemical compound C1=CC(N(C)C)=CC=C1\N=N\C1=CC=CC=C1C(O)=O CEQFOVLGLXCDCX-WUKNDPDISA-N 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 230000035764 nutrition Effects 0.000 description 1
- 125000000538 pentafluorophenyl group Chemical group FC1=C(F)C(F)=C(*)C(F)=C1F 0.000 description 1
- -1 polyethylene Polymers 0.000 description 1
- 229920000573 polyethylene Polymers 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 238000004451 qualitative analysis Methods 0.000 description 1
- 238000004445 quantitative analysis Methods 0.000 description 1
- 230000035484 reaction time Effects 0.000 description 1
- 238000000985 reflectance spectrum Methods 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- YNHJECZULSZAQK-UHFFFAOYSA-N tetraphenylporphyrin Chemical compound C1=CC(C(=C2C=CC(N2)=C(C=2C=CC=CC=2)C=2C=CC(N=2)=C(C=2C=CC=CC=2)C2=CC=C3N2)C=2C=CC=CC=2)=NC1=C3C1=CC=CC=C1 YNHJECZULSZAQK-UHFFFAOYSA-N 0.000 description 1
- 230000009466 transformation Effects 0.000 description 1
- 238000005303 weighing Methods 0.000 description 1
Classifications
-
- 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
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
- G01N21/31—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry
- G01N21/35—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light
- G01N21/359—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light using near infrared light
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/75—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated
- G01N21/77—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator
- G01N21/78—Systems in which material is subjected to a chemical reaction, the progress or the result of the reaction being investigated by observing the effect on a chemical indicator producing a change of colour
Abstract
The invention discloses the meat adulteration ratio detection methods based on visualization olfactory sensor and near-infrared, the described method includes: 1), using visualization olfactory sensor array test meat sample to be detected, and obtain the absolute value of the color difference before and after the corresponding detection of visualization olfactory sensor array；2) infrared light diffusing reflection spectrum of the meat sample to be detected under setting condition, is obtained, wherein the setting condition includes: one of wave number, temperature or combination；3), by the absolute value of the color difference before and after the detection and the infrared light diffusing reflection spectrum be input in advance training with regard in extreme learning machine, obtain recognition result, wherein, the recognition result include: other whether adulterated meats of meat sample to be detected, in meat sample to be detected other meats adulterated ratio.Using the embodiment of the present invention, it may be convenient to carry out the detection of adulterated meat.
Description
Technical field
The present invention relates to meat detection method, it is more particularly to mix based on the meat of visualization olfactory sensor and near-infrared
False ratio detection method.
Background technique
Beef is full of nutrition, unique flavor, is loved by consumers.In recent years, with the improvement of living standards, China ox
The consumption figure speedup of meat is obvious.At the same time, beef adulteration is also on the rise, wherein with the less expensive pork etc. of price
Pretend to be normal beef in meat products incorporation beef, earns juice, be the adulterated normal method of beef.
Objective, accurate identification to adulterated meat is to take precautions against the adulterated necessary condition of beef.Currently, identify for adulterated meat
Technology mainly includes that (Quantitative real time polymerase chain reaction, polymerase chain lock are anti-by PCR
Answer), chromatography, mass spectrography etc., although testing result is objective, reliable, there are at high cost, time-consuming, sample pretreatment is complicated
The defects of.Adulterated meat and the difference of normal meat volatile component can effectively be identified by electronic nose, however be based on physical absorption principle
INVENTIONConventional metal-oxide gas sensor that there are sensitivity is low, it is difficult to distinguish similar substance, and influenced by ambient humidity
Defect.
Therefore, the prior art technical problem inconvenient there are the detection of adulterated meat.
Summary of the invention
Technical problem to be solved by the present invention lies in provide the meat based on visualization olfactory sensor and near-infrared
Adulterated ratio detection method, easily to carry out the detection of adulterated meat.
The present invention is to solve above-mentioned technical problem by the following technical programs:
The embodiment of the invention provides based on visualization olfactory sensor and near-infrared meat adulteration ratio detection method,
The described method includes:
1), using visualization olfactory sensor array test meat sample to be detected, and visualization olfactory sensor array is obtained
The absolute value of color difference before and after corresponding detection；
2) infrared light diffusing reflection spectrum of the meat sample to be detected under setting condition, is obtained, wherein the setting condition packet
It includes: one of wave number, temperature or combination；
3), the absolute value of the color difference before and after the detection and the infrared light diffusing reflection spectrum are input in advance
It is trained with regard to obtaining recognition result in extreme learning machine, wherein the recognition result include: meat sample to be detected it is whether adulterated its
The adulterated ratio of other meats in his meat, meat sample to be detected.
Optionally, the step 1), comprising:
Meat sample to be detected is prepared into meat gruel；Meat gruel is divided in container bottom；Visualization olfactory sensor array is set
There is being attached on meat gruel on one side for color response substance；Container is sealed, is reacted 3-8 minutes, visualization olfactory sensor battle array is taken out
Column, wherein the color response substance includes: one of hydrophobic porphyrins, metalloporphyrin and pH indicator or combination；
Read it is described visualization olfactory sensor array in each sensor before detection after RGB difference absolute value into
And calculate the absolute value of the color difference of detection front and back.
Optionally, the visualization olfactory sensor array includes at least two visualization olfactory sensors, and is visualized
Olfactory sensor includes: substrate, and array is equipped with several blind holes on the top surface of the substrate, and the top surface is and test sample
The face of contact；
Color response substance is accommodated in the blind hole.
Optionally, the preparatory training process of the extreme learning machine includes:
Building includes the extreme learning machine of input layer, hidden layer and output layer, wherein input layer number is 33
A, output layer neuron number is 1；Hidden layer activation primitive uses hard limiting function；
According to preset ratio in meat sample other adulterated meats, and using visualization olfactory sensor array obtain it is several
The absolute value of color difference before and after the detection of a adulterated rear meat sample, and several adulterated rear meat samples are obtained under setting condition
Infrared light diffusing reflection spectrum, wherein it is described setting condition include: one of wave number, temperature or combination；Meat sample includes: ox
One of meat, pork, mutton；
Will it is adulterated after meat sample detection before and after color difference absolute value and it is corresponding it is adulterated after the infrared light of meat sample overflow
Reflectance spectrum carries out data fusion, and the combination of fused data and corresponding maternity leave ratio is used as to a sample data,
And then obtain the set of sample data；
The sample data sets are split as training set and test set；Sample data is input to initial threshold learning machine
In be trained, the extreme learning machine after being trained, reuse test set test training after extreme learning machine, predicted
As a result；
Judge whether the corresponding predicted root mean square error of the prediction result is less than preset threshold；
If so, using the extreme learning machine after the training as training in advance with regard to extreme learning machine；
If it is not, the connection weight in the extreme learning machine after the training between neuron is adjusted, by the limit after training
Learning machine returns as initial threshold learning machine and executes described be input to sample data and be trained in extreme learning machine
Step, until the corresponding predicted root mean square error of prediction result is less than preset threshold.
Optionally, the calculation formula of the predicted root mean square error are as follows:
Wherein,
RMSEP is predicted root mean square error；∑ is summing function；N is the number of sample data in test set；yiFor test
Concentrate the true value of i-th of sample data；For the true value of i-th of sample data in test set.
Optionally, the manufacturing process of the visualization olfactory sensor array includes:
Array of blind holes is opened up on reversed silica gel plate；
Using chloroform as solvent configure color response substance solution, wherein color response substance include: hydrophobic porphyrins,
Metalloporphyrin, metallo phthalocyanine；Hydrophobicity pH indicator solution is configured by solvent of ethyl alcohol；It is configured by solvent of acetone
Nile red solution；
Microscale sampler is by the blind hole of the solution point sample of color response substance to reversed silica gel plate, then to chloroform, second
Visualization olfactory sensor array is obtained after the completion of alcohol and acetone volatilization.
The present invention has the advantage that compared with prior art
Using the embodiment of the present invention, building visualization olfactory sensor array, and it is used for the detection of meat sample, while acquiring meat
The near infrared spectrum data of sample；Secondly the visualization olfactory sensor data and near infrared spectrum data of meat sample are led respectively
Constituent analysis, compared with the existing technology in complicated detection process, the carry out meat sample to be detected that the embodiment of the present invention can be convenient
Detection.
Detailed description of the invention
Fig. 1 is the meat adulteration ratio detection provided in an embodiment of the present invention based on visualization olfactory sensor and near-infrared
The structural schematic diagram of olfactory sensor array is visualized used in method；
Fig. 2 is the meat adulteration ratio detection provided in an embodiment of the present invention based on visualization olfactory sensor and near-infrared
The correlativity curve between the predicted value and actual value to the adulterated ratio of pork adulterated in beef that method obtains.
Specific embodiment
It elaborates below to the embodiment of the present invention, the present embodiment carries out under the premise of the technical scheme of the present invention
Implement, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to following implementation
Example.
Fig. 1 is the meat adulteration ratio detection provided in an embodiment of the present invention based on visualization olfactory sensor and near-infrared
The structural schematic diagram of olfactory sensor array is visualized used in method, as shown in Figure 1, which comprises
1), using visualization olfactory sensor array test meat sample to be detected, and visualization olfactory sensor array is obtained
The absolute value of color difference before and after corresponding detection.
Visualization olfactory sensor array should be prepared first, and manufacturing process is
Step 1: the preparation of visible sensor array substrate: concentration is respectively configured by solvent of chloroform as 2mg/mL's
Tetraphenylporphyrin, zinc protoporphyrin, ZnPc class chemical colour reaction agent solution；It take solvent configuration concentration as 2mg/mL hydrophobicity pH of ethyl alcohol
Solution, the specially indicator solution of methyl red；It is the Nile red solution of 2mg/mL by solvent configuration concentration of acetone.
Step 2: passing through capillary point sample with the chemical colour reaction agent solution that 10 μ L microscale samplers take the 5 μ L first steps to obtain
The mode reversed silica gel plate that is fixed on model C2 as shown in Figure 1 silica gel face on, then to chloroform, ethyl alcohol and acetone from
Visualization olfactory sensor array is so obtained after the completion of volatilization.
In practical applications, hydrophobic chemical color developing agent used be 7 kinds of metalloporphyrins such as, ferriporphyrin, pentafluorophenyl group iron
One of porphyrin, zinc protoporphyrin, tetraphenyl manganoporphyrin, octaethyl manganoporphyrin, copper porphyrin, Cob altporphyrin, 2 kinds of pH indicator such as first
Base is red, one of bromocresol green solution.
Step 3: meat sample is placed in household meat mincer, it is beaten 2 minutes, so that meat sample is in meat gruel shape；In practical application
In, meat sample can be rubbed to partial size 2mm.
Step 4: weighing the meat sample 40g to be detected that third step obtains, it is placed in 250mL beaker, and meat sample to be detected is put down
It is laid on and is covered in beaker bottom, so that beaker bottom is completely covered after meat sample to be detected expansion.
Step 5: the visualization olfactory sensor array that will be prepared, color response substance are attached to meat sample to be detected downward
On, and with polyethylene film sealed beaker, the reaction time 5 minutes.
2) infrared light diffusing reflection spectrum of the meat sample to be detected under setting condition, is obtained, wherein the setting condition packet
It includes: one of wave number, temperature or combination.
The diffusing reflection spectrum of meat sample to be detected can be acquired under 3300~10000 wave numbers.
Meat sample diffusing reflection spectrum is acquired using Fourier transform near infrared spectrometer.As follows, data area is arranged in instrument parameter:
3300~10000 wave numbers, scanning step: 0.316495746WN, sampling resolution: 4WN, scanning times: 32 times.It, will when test
Sample is placed directly in sample room objective table and carries out diffusing reflection spectrum information collection, after deducting background, exports as initial data.
3), the absolute value of the color difference before and after the detection and the infrared light diffusing reflection spectrum are input in advance
It is trained with regard to obtaining recognition result in extreme learning machine, wherein the recognition result include: meat sample to be detected it is whether adulterated its
The adulterated ratio of other meats in his meat, meat sample to be detected.
In embodiments of the present invention, the training process of extreme learning machine can be with are as follows:
Fresh finger meat meat, pig brisket are respectively placed in meat grinder, 2min is beaten, it is spare.It is according to adulterated ratio
20%, 40%, 60%, 80% ratio obtains configured sample into beef for pork is adulterated.To under every kind of adulterated ratio
Specimen sample 14 times, obtain the sample that 56 weight are 40.0g.
Utilize the visualization olfactory sensing of visualization 56 samples of olfactory sensor array acquisition identical with step 1)
Device data, and diffuse modal data using with acquisition mode identical in step 1) acquisition near-infrared.
Extract the minimum number of meat sample visible sensor data and near infrared spectrum data accumulation contribution rate greater than 0.90
Principal component merges into fusion variable, that is, chooses 7 principal components before visualization olfactory sensor, 24 masters before near infrared spectrum data
Ingredient carries out information fusion.Assuming that before the corresponding visualization olfactory sensor of i-th of sample 7 it is main at be scored at Ui=(u1,
U2, u3 ..., u7), 24 principal component scores are Vi=(v1, v2, v3 ..., v24) before corresponding near infrared spectrum, then merge it
Data afterwards are Zi=(u1, u2, u3 ..., u7, v1, v2, v3 ..., v24).
It is understood that principal component analysis is that there may be the variables of correlation to be converted to by one group by orthogonal transformation
One group of linear incoherent variable, this group of variable after conversion is principal component.
Then, the corresponding fused data of meat sample after will be adulterated are divided into test set and training set, and test set and instruction
Practice and concentrates no identical data.Then using training set as being input to the extreme learning machine model constructed in advance.Limit study
Machine network model is 3 layers, including input layer, hidden layer and output layer, and input layer number is 33, output layer neuron
Number is 1.Hidden layer activation primitive uses hardlim function, i.e. hard limiting function, expression formula is as follows:
Wherein, n is input data.
For example, test the extreme learning machine after training after the 1st iteration using test set, obtain prediction result,
And formula is utilized,The corresponding predicted root mean square error of prediction result, wherein
RMSEP is predicted root mean square error；∑ is summing function；N is the number of sample data in test set；yiFor test
Concentrate the true value of i-th of sample data；For the true value of i-th of sample data in test set.
In the corresponding RMSEP of prediction result, (Root-Mean-Square Error of Prediction predicts root mean square
Error) be greater than or equal to 2% when, it is believed that extreme learning machine is not trained successfully；Neuron in hidden layer in adjustment extreme learning machine
One of connection weight, input layer between number, hidden layer and output layer and implicit interlayer connection weight combine；Then
Iteration again is carried out, until the corresponding predicted root mean square error of prediction result is less than 2%.
Hidden layer neuron number is 438 in embodiments of the present invention, and hidden layer neuron threshold value is
0.208431131079598, connection weight between hidden layer and output layer is 0.036233771993156, input layer with it is hidden
Connection weight containing interlayer is as shown in table 1, and table 1 is input layer and hidden layer connection weight.
Table 1
Fig. 2 is the meat adulteration ratio detection provided in an embodiment of the present invention based on visualization olfactory sensor and near-infrared
The correlativity curve between the predicted value and actual value to the adulterated ratio of pork adulterated in beef that method obtains, such as Fig. 2 institute
Show, it is adulterated be 20% when, a little higher than actual value of predicted value, it is adulterated be 40% when, distribution of forecasting value is in oblique line two sides；It is mixing
When vacation is 60%, distribution of forecasting value is in oblique line two sides close to actual value, and at adulterated 80%, predicted value is slightly below actual value,
General description, constructed extreme learning machine model is to the adulterated adulterated ratio of beef in the prediction result of independent sample and practical pork
RMSEP between example is 1.1%, coefficient R 0.85, show it is of the present invention it is a kind of based on visualization smell technology and
The adulterated adulterated scale prediction method of pork is effective in the beef of near-infrared fusion
Using the embodiment of the present invention, building visualization olfactory sensor array, and it is used for the detection of meat sample, while acquiring meat
The near infrared spectrum data of sample；Secondly the visualization olfactory sensor data and near infrared spectrum data of meat sample are led respectively
Constituent analysis, compared with the existing technology in complicated detection process, the carry out meat sample to be detected that the embodiment of the present invention can be convenient
Detection.
Moreover, the embodiment of the present invention it be to be reacted with microscratch amount chemical component in sample to be tested gas phase using chemo-responsive dyes
Front and back, sensor colors change this property realize sample quality qualitative and quantitative analysis.Visualizing smell technology can be with
Avoid influence of the ambient humidity to testing result, have the advantages that compared with the traditional electronic nose based on metal oxide electrode it is significant,
There are very big potentiality in the quick detection of food quality.
Furthermore near infrared spectrum is that the frequency multiplication of chemical constituent hydric group fundamental vibration and sum of fundamental frequencies absorb in sample, analysis
Process is quickly and without complicated sample pretreatment, in the quality grading of raw-food material, food processing process monitoring, finished product food
Product quality identification and equal fields application of tracing to the source are rather extensive, are very suitable to develop the rapid detection method of adulterated beef.
Finally, in the achievable beef that the embodiment of the present invention can be convenient the adulterated adulterated ratio of pork effective detection, and
Detection time is short, high-efficient.
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the invention, all in essence of the invention
Made any modifications, equivalent replacements, and improvements etc., should all be included in the protection scope of the present invention within mind and principle.
Claims (6)
1. the meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared, which is characterized in that the method
Include:
1), using visualization olfactory sensor array test meat sample to be detected, and it is corresponding to obtain visualization olfactory sensor array
Detection before and after color difference absolute value；
2) infrared light diffusing reflection spectrum of the meat sample to be detected under setting condition, is obtained, wherein the setting condition includes: wave
One of number, temperature or combination；
3) absolute value of the color difference before and after the detection and the infrared light diffusing reflection spectrum, are input to preparatory training
With regard to obtaining recognition result in extreme learning machine, wherein the recognition result includes: other whether adulterated meat of meat sample to be detected
The adulterated ratio of other meats in class, meat sample to be detected.
2. the meat adulteration ratio detection method according to claim 1 based on visualization olfactory sensor and near-infrared,
It is characterized in that, the step 1), comprising:
Meat sample to be detected is prepared into meat gruel；Meat gruel is divided in container bottom；Visualization olfactory sensor array is equipped with face
Colour response substance is attached on meat gruel on one side；Container is sealed, is reacted 3-8 minutes, visualization olfactory sensor array is taken out,
In, the color response substance includes: one of hydrophobic porphyrins, metalloporphyrin and pH indicator or combination；
Read it is described visualization olfactory sensor array in each sensor before detection after RGB difference absolute value so that count
Calculate the absolute value of the color difference of detection front and back.
3. the meat adulteration ratio detection method according to claim 2 based on visualization olfactory sensor and near-infrared,
It is characterized in that, the visualization olfactory sensor array includes at least two visualization olfactory sensors, and visualize smell
Sensor includes: substrate, and array is equipped with several blind holes on the top surface of the substrate, and the top surface is to contact with test sample
Face；
Color response substance is accommodated in the blind hole.
4. the meat adulteration ratio detection method according to claim 1 based on visualization olfactory sensor and near-infrared,
It is characterized in that, the preparatory training process of the extreme learning machine includes:
Building includes the extreme learning machine of input layer, hidden layer and output layer, wherein input layer number is 33, defeated
Layer neuron number is 1 out；Hidden layer activation primitive uses hard limiting function；
According to preset ratio in meat sample other adulterated meats, and obtain several using visualization olfactory sensor array and mix
The absolute value of color difference after vacation before and after the detection of meat sample, and obtain several it is adulterated after meat samples it is red under setting condition
Outer light diffusing reflection spectrum, wherein the setting condition includes: one of wave number, temperature or combination；Meat sample includes: beef, pig
One of meat, mutton；
Will it is adulterated after meat sample detection before and after color difference absolute value and it is corresponding it is adulterated after meat sample infrared light diffusing reflection
Spectrum carries out data fusion, and the combination of fused data and corresponding maternity leave ratio is used as to a sample data, in turn
Obtain the set of sample data；
The sample data sets are split as training set and test set；By sample data be input in initial threshold learning machine into
Row training, the extreme learning machine after being trained, the extreme learning machine after reusing test set test training obtain prediction knot
Fruit；
Judge whether the corresponding predicted root mean square error of the prediction result is less than preset threshold；
If so, using the extreme learning machine after the training as training in advance with regard to extreme learning machine；
If it is not, adjusting the connection weight in the extreme learning machine after the training between neuron, the limit after training is learnt
Machine returns to execute and described sample data is input to the step being trained in extreme learning machine as initial threshold learning machine
Suddenly, until the corresponding predicted root mean square error of prediction result is less than preset threshold.
5. the meat adulteration ratio detection method according to claim 4 based on visualization olfactory sensor and near-infrared,
It is characterized in that, the calculation formula of the predicted root mean square error are as follows:
Wherein,
RMSEP is predicted root mean square error；∑ is summing function；N is the number of sample data in test set；yiFor in test set
The true value of i-th of sample data；For the true value of i-th of sample data in test set.
6. the meat adulteration ratio detection method according to claim 4 based on visualization olfactory sensor and near-infrared,
It is characterized in that, the manufacturing process of the visualization olfactory sensor array includes:
Array of blind holes is opened up on reversed silica gel plate；
The solution of color response substance is configured using chloroform as solvent, wherein color response substance includes: hydrophobic porphyrins, metal
Porphyrin, metallo phthalocyanine；Hydrophobicity pH indicator solution is configured by solvent of ethyl alcohol；Buddhist nun sieve is configured by solvent of acetone
Red solution；
Microscale sampler by the blind hole of the solution point sample of color response substance to reversed silica gel plate, then to chloroform, ethyl alcohol and
Visualization olfactory sensor array is obtained after the completion of acetone volatilization.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745260.4A CN110426366A (en) | 2019-08-13 | 2019-08-13 | Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910745260.4A CN110426366A (en) | 2019-08-13 | 2019-08-13 | Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110426366A true CN110426366A (en) | 2019-11-08 |
Family
ID=68414413
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910745260.4A Pending CN110426366A (en) | 2019-08-13 | 2019-08-13 | Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110426366A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563558A (en) * | 2020-05-13 | 2020-08-21 | 宿州学院 | Rapid identification method for producing area and brand of wine |
| CN114047156A (en) * | 2021-10-09 | 2022-02-15 | 中南民族大学 | Identification method for dendrobium huoshanense cultivation mode and age limit |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101936912A (en) * | 2010-08-25 | 2011-01-05 | 江苏大学 | Method and device for detecting freshness of fish based on olfaction visualization |
| CN103278609A (en) * | 2013-06-27 | 2013-09-04 | 山东商业职业技术学院 | Meat product freshness detection method based on multisource perceptual information fusion |
| CN204989009U (en) * | 2015-06-09 | 2016-01-20 | 宁夏大学 | Online quick nondestructive test production line of mutton safety quality based on map fusion technique |
| CN109406500A (en) * | 2018-09-30 | 2019-03-01 | 江苏大学 | A kind of sausage rapid classification method based on olfaction visualization array |
-
2019
- 2019-08-13 CN CN201910745260.4A patent/CN110426366A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101936912A (en) * | 2010-08-25 | 2011-01-05 | 江苏大学 | Method and device for detecting freshness of fish based on olfaction visualization |
| CN103278609A (en) * | 2013-06-27 | 2013-09-04 | 山东商业职业技术学院 | Meat product freshness detection method based on multisource perceptual information fusion |
| CN204989009U (en) * | 2015-06-09 | 2016-01-20 | 宁夏大学 | Online quick nondestructive test production line of mutton safety quality based on map fusion technique |
| CN109406500A (en) * | 2018-09-30 | 2019-03-01 | 江苏大学 | A kind of sausage rapid classification method based on olfaction visualization array |
Non-Patent Citations (5)
| Title |
|---|
| 张娟等: "电子鼻结合统计学分析对牛肉中猪肉掺假的识别", 《食品科学》 * |
| 王名星: "基于嗅觉可视化和近红外光谱技术的鸡肉中假单胞菌快速识别研究", 《中国优秀硕士学位论文全文数据库》 * |
| 邹小波等: "嗅觉可视化传感器阵列", 《农产品无损检测技术与数据分析方法》 * |
| 韩方凯等: "近红外结合极限学习机快速识别牛肉中掺假猪肉", 《安徽农业科学》 * |
| 黄星奕等: "基于嗅觉可视化和近红外光谱融合技术的海鲈鱼新鲜度评价", 《 农业工程学报》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111563558A (en) * | 2020-05-13 | 2020-08-21 | 宿州学院 | Rapid identification method for producing area and brand of wine |
| CN114047156A (en) * | 2021-10-09 | 2022-02-15 | 中南民族大学 | Identification method for dendrobium huoshanense cultivation mode and age limit |
| CN114047156B (en) * | 2021-10-09 | 2022-10-18 | 中南民族大学 | Identification method for dendrobium huoshanense cultivation mode and age limit |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
| Meza-Márquez et al. | Application of mid-infrared spectroscopy with multivariate analysis and soft independent modeling of class analogies (SIMCA) for the detection of adulterants in minced beef | |
| Sharma et al. | Trends of chemometrics in bloodstain investigations | |
| Alamprese et al. | Detection of minced beef adulteration with turkey meat by UV–vis, NIR and MIR spectroscopy | |
| Di Natale et al. | Outer product analysis of electronic nose and visible spectra: application to the measurement of peach fruit characteristics | |
| CN103134767B (en) | Method for liquor quality identification through infrared spectrum revision | |
| Li et al. | Pears characteristics (soluble solids content and firmness prediction, varieties) testing methods based on visible-near infrared hyperspectral imaging | |
| CN105181912B (en) | A kind of Noninvasive Measuring Method of Freshness in rice storage | |
| CN101936912A (en) | Method and device for detecting freshness of fish based on olfaction visualization | |
| Weng et al. | A comprehensive method for assessing meat freshness using fusing electronic nose, computer vision, and artificial tactile technologies | |
| CN101493431A (en) | Method for detecting fresh degree of chicken meat by electronic nose | |
| CN109669023A (en) | A kind of soil attribute prediction technique based on Multi-sensor Fusion | |
| CN106841083A (en) | Sesame oil quality detecting method based on near-infrared spectrum technique | |
| CN103900972B (en) | Multi-feature fusion-based meat freshness hyperspectral image visual detection | |
| Wang | Near-infrared spectroscopy for food quality evaluation | |
| CN105548062B (en) | The quick nondestructive synchronization detecting method of fresh beef appetizer multi objective | |
| Huang et al. | Non-destructive evaluation of total volatile basic nitrogen (TVB-N) and K-values in fish using colorimetric sensor array | |
| CN106872370A (en) | Anthocyanin content method for measuring in a kind of red bayberry based on EO-1 hyperion | |
| CN110426366A (en) | Meat adulteration ratio detection method based on visualization olfactory sensor and near-infrared | |
| CN107478595A (en) | The method that a kind of the quick discriminating pearl powder true and false and quantitative forecast mix pseudo- shell powder content | |
| CN106950192A (en) | A kind of method of Contents of Main Components quick detection in vegetable protein beverage based on near-infrared spectral analysis technology | |
| Han et al. | Fusion of a low-cost electronic nose and Fourier transform near-infrared spectroscopy for qualitative and quantitative detection of beef adulterated with duck | |
| Guo et al. | Method and system for nondestructive detection of freshness in Penaeus vannamei based on hyperspectral technology | |
| CN106706555A (en) | Milk powder determination method and system based on near infrared spectroscopy technology | |
| Ning et al. | Study on apple damage detecting method based on relaxation single-wavelength laser and convolutional neural network |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20191108 |