CN113310937A - Method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder - Google Patents
Method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder Download PDFInfo
- Publication number
- CN113310937A CN113310937A CN202110503862.6A CN202110503862A CN113310937A CN 113310937 A CN113310937 A CN 113310937A CN 202110503862 A CN202110503862 A CN 202110503862A CN 113310937 A CN113310937 A CN 113310937A
- Authority
- CN
- China
- Prior art keywords
- milk
- samples
- model
- temperature sterilized
- spectrum
- 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
- 235000013336 milk Nutrition 0.000 title claims abstract description 105
- 239000008267 milk Substances 0.000 title claims abstract description 105
- 210000004080 milk Anatomy 0.000 title claims abstract description 105
- 238000000034 method Methods 0.000 title claims abstract description 36
- 235000020191 long-life milk Nutrition 0.000 title claims abstract description 35
- 239000000843 powder Substances 0.000 title claims abstract description 34
- 235000013365 dairy product Nutrition 0.000 title claims abstract description 19
- 235000020122 reconstituted milk Nutrition 0.000 title claims abstract description 16
- 235000020247 cow milk Nutrition 0.000 title description 4
- 241000283690 Bos taurus Species 0.000 claims abstract description 29
- 238000012360 testing method Methods 0.000 claims abstract description 26
- 238000004422 calculation algorithm Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 238000001228 spectrum Methods 0.000 claims abstract description 17
- 230000003595 spectral effect Effects 0.000 claims abstract description 12
- 238000012216 screening Methods 0.000 claims abstract description 11
- 238000012549 training Methods 0.000 claims abstract description 11
- 230000002159 abnormal effect Effects 0.000 claims abstract description 8
- 238000002329 infrared spectrum Methods 0.000 claims abstract description 8
- 238000005070 sampling Methods 0.000 claims abstract description 6
- 238000004476 mid-IR spectroscopy Methods 0.000 claims abstract description 3
- 239000000523 sample Substances 0.000 claims description 22
- 238000012706 support-vector machine Methods 0.000 claims description 17
- 235000020200 pasteurised milk Nutrition 0.000 claims description 11
- 238000007637 random forest analysis Methods 0.000 claims description 11
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 claims description 9
- 235000021243 milk fat Nutrition 0.000 claims description 8
- 238000002834 transmittance Methods 0.000 claims description 8
- 102000014171 Milk Proteins Human genes 0.000 claims description 7
- 108010011756 Milk Proteins Proteins 0.000 claims description 7
- 238000009499 grossing Methods 0.000 claims description 7
- 235000021239 milk protein Nutrition 0.000 claims description 7
- 238000002835 absorbance Methods 0.000 claims description 6
- 238000010521 absorption reaction Methods 0.000 claims description 6
- 238000001514 detection method Methods 0.000 claims description 6
- 239000007788 liquid Substances 0.000 claims description 6
- 238000012795 verification Methods 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 5
- 239000011159 matrix material Substances 0.000 claims description 4
- 230000004069 differentiation Effects 0.000 claims description 3
- 239000013307 optical fiber Substances 0.000 claims description 3
- 239000007787 solid Substances 0.000 claims description 3
- 238000000638 solvent extraction Methods 0.000 claims description 3
- 230000009466 transformation Effects 0.000 claims description 3
- 238000004364 calculation method Methods 0.000 claims description 2
- 230000017105 transposition Effects 0.000 claims description 2
- 230000000694 effects Effects 0.000 abstract description 4
- 238000004458 analytical method Methods 0.000 abstract description 3
- 230000001954 sterilising effect Effects 0.000 description 11
- 238000004659 sterilization and disinfection Methods 0.000 description 10
- 238000012545 processing Methods 0.000 description 5
- 239000004615 ingredient Substances 0.000 description 4
- 238000013145 classification model Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000010801 machine learning Methods 0.000 description 2
- 235000010469 Glycine max Nutrition 0.000 description 1
- 244000068988 Glycine max Species 0.000 description 1
- 241001465754 Metazoa Species 0.000 description 1
- 238000004497 NIR spectroscopy Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 239000003153 chemical reaction reagent Substances 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 235000016709 nutrition Nutrition 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000010183 spectrum analysis 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
- G01N21/3577—Investigating relative effect of material at wavelengths characteristic of specific elements or molecules, e.g. atomic absorption spectrometry using infrared light for analysing liquids, e.g. polluted water
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
Landscapes
- Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Spectroscopy & Molecular Physics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Dairy Products (AREA)
- Data Mining & Analysis (AREA)
- Medical Informatics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- General Health & Medical Sciences (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
- Artificial Intelligence (AREA)
Abstract
The invention belongs to the field of milk product analysis, and particularly relates to a rapid identification method of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder. Related to mid-infrared spectroscopy. The method comprises the following steps: 1) collecting high-temperature sterilized milk, pasteurized fresh milk of dairy cows and milk powder recovered milk samples; 2) scanning the sample in the middle red spectrum range to obtain middle infrared spectrum data; 3) preprocessing the original mid-infrared spectrum to remove abnormal values; 4) dividing the preprocessed data set into a training set and a test set according to a layered sampling principle; 5) screening the spectral band of the modeling; 6) combining different spectrum preprocessing methods and modeling algorithms, establishing an identification model, evaluating the model by using accuracy and Kappa coefficients, and screening out an optimal model combining the preprocessing method and the modeling algorithm with optimal effect; 7) and verifying the optimal model and evaluating the generalization capability of the optimal model.
Description
Technical Field
The invention belongs to the technical field of milk product analysis, and particularly relates to a rapid identification method of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder.
Background
In the market, common milk types are high temperature sterilized pure milk, pasteurized fresh milk and milk powder. The processing technology adopted by the high-temperature sterilized milk comprises a high-temperature instantaneous sterilization method (UHT): the sterilization temperature is 130-150 ℃, and the sterilization time is 0.5-4 s; the holding type sterilization method: the sterilization temperature is 115-120 ℃, and the sterilization time is 15-20 min. The processing technology adopted by pasteurized fresh milk comprises a low-temperature long-time sterilization method (LTLT): sterilizing at 62-65 deg.c for 30 min; high temperature short time sterilization method (HTST): the sterilization temperature is 72-75 ℃, and the sterilization time is 15 s. The milk powder is first homogenized in homogenizer at 60 deg.c, then sterilized at 120 deg.c in short time and finally dried at 100 deg.c[1]. These different types of milk products vary in price and nutritional content, and therefore, there is a need to establish a rapid and efficient identification technique for high temperature sterilized milk, pasteurized cow fresh milk and milk powder reconstituted milk.
Mid-infrared spectral analysis is a modern technology which is rapidly developed in recent years, is free from damage and pollution and can simultaneously analyze multiple components, and is widely applied to milk quality detection and pasture management of dairy animals. The machine learning algorithm for establishing the classification model comprises a decision tree, naive Bayes, an artificial neural network, bootstrap convergence, K nearest neighbor, a random forest, a support vector machine and the like, and in practice, the random forest and the support vector machine have better performance, low misjudgment rate and high accuracy, sensitivity and specificity[5]The data output by the mid-infrared spectrometer is an n × 1060 matrix (n is a sample size), the data is huge, incomplete and inconsistent data is difficult to avoid, and the data is extremely easy to be disturbed by noise (error or abnormal value), and the low-quality data leads to a data mining result with poor effect, so some methods are needed to preprocess the output data. These methods typically include data normalization[4]Processing missing values, removing noise and abnormal values[3]And feature selection, e.g. using first order differentiation[4]Standard positiveState variable transform (SNV), Multivariate Scatter Correction (MSC), and SG convolution smoothing[2]And (5) equally mining the difference of the classified objects, and removing abnormal values by using the Mahalanobis distance[4]And the like.
Disclosure of Invention
The invention aims to determine the optimal pretreatment and modeling algorithm combination for rapidly identifying the high-temperature sterilized milk, the pasteurized fresh milk of the milk cow and the milk powder recovered milk aiming at the defects of the identification methods of the high-temperature sterilized milk, the pasteurized fresh milk of the milk cow and the milk powder recovered milk, and improve the identification speed and the identification accuracy of the three types of milk.
The technical scheme of the invention is as follows:
a method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder comprises the following steps:
1) selection of milk samples
Respectively collecting high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder;
2) collecting central infrared spectrum (MIR for short)
Scanning milk samples by adopting a milk component detector, and outputting light transmittance corresponding to each sample through a connected computer;
3) data pre-processing
Converting the original spectrum data from light transmittance (T) to absorbance (A), and removing abnormal values;
4) partitioning a data set
Dividing a data set into a training set and a testing set according to a layered sampling principle, wherein the training set and the testing set respectively account for 80% and 20% of the data set;
5) determining a modeled spectral band
Screening different wave bands of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder, and removing an absorption area of water;
6) model building and optimal model screening
Taking the mid-infrared spectrum of a training set sample as an input value, taking the categories of high-temperature sterilized milk, pasteurized milk cow fresh milk and milk powder recovered milk as output values, using different spectrum preprocessing methods and different modeling algorithms to combine and establish a model, using accuracy and Kappa coefficient indexes to evaluate and screen the model, and screening out an optimal model;
7) verification and application of optimal model
Taking samples of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and milk powder recovered milk, identifying the samples by using the screened optimal model, and evaluating the application performance of the samples;
wherein:
when the mid-infrared spectrum is collected in the step 2), respectively pouring milk samples into cylindrical sampling tubes with the diameter of 3.5cm and the height of 9cm to ensure that the liquid level height is more than 6cm, then putting the milk samples into a water bath kettle at 42 ℃ for water bath for 15-20min, and extending a solid optical fiber probe into the liquid for sample absorption detection;
log according to A) in step 3)10(1/T) converting the transmittance (T) to absorbance (A), removing outliers using Mahalanobis distance and the percentage of milk fat and milk protein, and retaining data for a spectrum with Mahalanobis distance ≦ 3 and percentages of milk fat and milk protein within + -3.5 standard deviations of the mean, where Mahalanobis distance is calculated as MD ═ sqrt [ (x- μ)TΣ-1(x-μ)]X is a spectral value, mu is a sample mean value, sigma is a covariance matrix, T represents transposition, and the mean value of the percentage content of milk fat milk protein is calculated by the method of M ═ x (x)1+x2+...+xn) N, i.e. the average milk fat, milk protein content of n samples, the standard deviation calculation method is SD ═ sqrt { [ (x)1-M)2+(x2-M)2+......(xn-M)2]/(n-1)}；
The method for screening the difference wave band used in the step 5) is a Pearson correlation test and a significance test of the correlation, and the preferred spectrum wave band finally selected for modeling is 972.216-1481.472cm-1、1504.62-1577.922cm-1、1770.822-2249.214cm-1And 2388.102-2966.802cm-1；
The spectrum preprocessing method used in the step 6) comprises first-order differentiation (Diff), standard normal variable transformation (SNV), multivariate scattering correction (MCS) and Savitzky-Golag convolution smoothing (SG convolution smoothing for short), and the modeling algorithm used is Random Forest (RF) and Support Vector Machine (SVM).
The optimal model selected in the step 7) is a combination of non-preprocessing and support vector machine algorithms, the accuracy of the optimal model in the training set, the testing set and the verification set is 1, and the verification process does not exceed 5 minutes, namely the optimal model selected by the invention can realize the rapid and accurate identification of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and milk powder recovered milk.
Compared with the prior art, the invention has the beneficial effects that:
(1) the invention is characterized in that differential wave bands are screened out by using Pearson correlation test and significance test of correlation, and the preferred spectral wave band for finally modeling is screened out to be 972.216-1481.472cm-1、1504.62-1577.922cm-1、1770.822-2249.214cm-1And 2388.102-2966.802cm-1And fewer wave points are used, so that the operation cost is reduced.
(2) The combination of the preprocessing and modeling algorithms of the optimal model is an unprocessed and support vector machine algorithm, and the accuracy can reach 1.
(3) The invention can realize accurate and rapid identification of the sample within 5 minutes, and realize rapid detection of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder.
Drawings
FIG. 1: the invention models a spectrogram of a waveband. Namely, the absorption value graphs of the three types of milk in the modeling wave band. Description of reference numerals: in the graph of FIG. 1, the abscissa is the spectral wavenumber, the ordinate is the absorbance, and the modeling waveband is 972.216-1481.472cm-1、1504.62-1577.922cm-1、1770.822-2249.214cm-1And 2388.102-2966.802cm-1. Panel A in FIG. 1 is 972.216-1481.472cm-1The spectrogram of wavenumber range, B in FIG. 1 is 1504.62-1577.922cm-1Spectrogram of wavenumber range, and C diagram in FIG. 1 is 1770.822-2249.214cm-1Spectrogram of wavenumber range, D in FIG. 1 is 2388.102-2966.802cm-1Spectrogram of wavenumber range.
FIG. 2: the invention tests the ROC curve of the set. Description of reference numerals: the ROC curve can measure the performance of the model in the test set. The abscissa in fig. 2 is the false positive rate, the ordinate is the true positive rate, AUC is the area enclosed by the coordinate axes under the ROC curve, the value range is between 0.5 and 1, the closer the AUC is to 1.0, the higher the authenticity of the method is, and the AUC in fig. 2 is 1, the higher the authenticity of the model of the invention is.
FIG. 3: the invention tests the classification probability map of the set. Description of reference numerals: the abscissa in fig. 3 is the predicted probability and the ordinate is the predicted category, e.g. the upper left circle in fig. 3 indicates that the sample is classified as 0.704 with a probability of being classified as 0 and as a correct classification; in FIG. 3, it is shown that the samples in the test set are all classified correctly, and the probability of classifying correctly the high-temperature sterilized milk in class 0 is 0.967-1, the probability of classifying correctly the pasteurized milk cow in class 1 is 0.929-0.999, and the probability of classifying correctly the reconstituted milk in class 2 is 0.704-1. The model of the invention can realize high-probability correct classification of the samples.
Detailed Description
The technical schemes of the invention are conventional technical schemes in the field if not particularly stated. The reagents or materials, if not specifically mentioned, are commercially available.
In the technical scheme of the invention, technical parameters such as first order differential (Diff), standard normal variable transformation (SNV), Multivariate Scattering Correction (MSC), SG convolution smoothing and the like can be routinely adjusted by a person skilled in the art according to a study object.
In the embodiment of the invention, the pretreatment of mid-infrared spectrum data, the construction and verification of the model and the like are all realized by Python 3.8.3.
Example 1: establishment of rapid identification method for high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder
Instruments and equipment: selecting MilkoScan produced by FOSS companyTM7RM milk ingredient detector (operating according to the product instruction).
The specific operation steps are as follows:
(1) collecting milk sample
643 parts of five commercial brands with large sales volume and different batches of high-temperature sterilized milk samples, 127 parts of four brands of pasteurized cow fresh milk samples and 223 parts of reconstituted milk powder samples are purchased in supermarkets respectively.
(2) Mid IR spectroscopy in assays
Respectively pouring milk samples into cylindrical sample tubes with the diameter of 3.5cm and the height of 9cm, ensuring that the liquid level height is more than 6cm, then carrying out water bath on the milk samples in a water bath kettle at 42 ℃ for 15-20min, extending a solid optical fiber probe into the liquid, carrying out sample suction detection, and obtaining the light transmittance of the samples through software.
(3) Data pre-processing
According to A ═ log10(1/T) converting the original spectrum data from light transmittance (T) to absorbance (A), calculating the Mahalanobis distance of a milk sample MIR, keeping the data that the Mahalanobis distance of the spectrum is less than or equal to 3 and the percentage contents of milk fat and milk protein are within the range of +/-3.5 standard deviations of the average value, taking the sample size variation statistics in the process as shown in the table 1, removing 17 high-temperature sterilized milk and 8 milk powder abnormal samples, and obtaining 660 effective high-temperature sterilized milk samples, 127 pasteurized milk cow fresh milk samples and 215 milk powder samples.
(4) Partitioning a data set
The data set is divided into a training set (n: 801: 528 high-temperature sterilized milk, 101 pasteurized milk and 172 milk powder) and a testing set (n: 201: 132 high-temperature sterilized milk, 26 pasteurized milk and 43 milk powder) according to a hierarchical sampling method.
In the modeling process, the value 0 represents high temperature sterilized milk, 1 represents pasteurized cow fresh milk, and 2 represents milk powder. Table 2 is a descriptive statistic of conventional milk ingredients of 3 types of milk, and it can be seen from table 2 that there are very significant differences (P <0.01) in conventional milk ingredients of these 3 types of products.
TABLE 1 sample size variation when rejecting outliers
Table 2 descriptive statistics of conventional milk ingredients
Note: the data in the same row are marked with different letters to indicate that the difference is significant (P <0.05), and the same letters to indicate that the difference is not significant (P > 0.05).
(5) Determining a modeled spectral band
Performing Pearson correlation test on the spectral data, performing significance analysis on the correlation, and removing the water absorption region, preferably 972.216-1481.472cm-1、1504.62-1577.922cm-1、1770.822-2249.214cm-1And 2388.102-2966.802cm-1The spectral band is modeled. FIG. 1 is a spectrum of a modeled band.
(6) Model building and optimal model screening
Spectral data were preprocessed using first order differential (Diff), standard normal variable transform (SNV), Multivariate Scatter Correction (MSC), and SG convolution smoothing, respectively, and also compared to data without preprocessing.
And establishing a classification model by using Random Forest (RF) and Support Vector Machine (SVM) algorithms and utilizing training set data, and predicting samples in the test set. The modeling results of the RF and SVM algorithms under different preconditions are shown in table 3.
TABLE 3 modeling results for RF and SVM under different preconditions
In the multi-classification discrimination model, the performance of the model is evaluated by the accuracy and the Kappa coefficient, wherein the accuracy is the probability that the correct judgment occupies all the judgments, and the closer the value is to 1, the better the value is. The Kappa coefficient is commonly used for consistency checking and may also be used to measure the accuracy of classification, with values closer to 1 being better. As can be seen from the results in Table 3, the SVM algorithm shows stronger learning ability than the RF algorithm in the classification task, and the SVM model obtains excellent results, which indicates that the 5 models can accurately identify the two types of targets of the training set and the test set. In the RF model, it can be seen that both first order differential (Diff) and SG smoothing perform better than no processing, indicating that suitable data preprocessing will improve the model accuracy. However, different preprocessing of data increases the operation difficulty and the operation time. Therefore, the model built without the combination of the process and the support vector machine is selected as the optimal model among the 5 models having the same effect.
Using the selected optimal classification model, 201 samples of the test set are predicted. The performance of the model in the test set is measured by the confusion matrix, as shown in fig. 2. As can be seen from fig. 2, the test set in this embodiment has no misclassification, which indicates that the model has a good classification effect on the test set.
Fig. 3 shows the probability of class classification in the test set, for example, the circle at the upper left of the figure indicates that the sample is classified as 0.704 and is correctly classified. As can be seen, all samples in the test set were correctly classified, and the probability that most of the samples were correctly classified is > 0.95.
Example 2: application of rapid identification method of high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder
And (3) taking 145 parts of high-temperature sterilized milk, pasteurized milk cow fresh milk and milk powder recovered milk samples (wherein 85 parts of high-temperature sterilized milk, 23 parts of pasteurized milk cow fresh milk and 37 parts of milk powder recovered milk) to verify the model, and comparing the predicted result with the real result. Wherein the 145 samples are of a type recorded in advance.
The method comprises the following specific steps: the 145 samples were measured and processed by the methods of spectrum measurement, data preprocessing, etc. of example 1, and identified using the selected optimal model (no processing + SVM).
The output results are shown in table 4.
TABLE 4 results of model application
The identification result is completely the same as the real condition, the accuracy rate of 85 high-temperature sterilized milk samples, 23 pasteurized milk cow fresh milk samples and 37 milk powder recovered milk samples reaches 100 percent.
The spectral band used by the optimal model of the invention is 972.216-1481.472cm-1、1504.62-1577.922cm-1、1770.822-2249.214cm-1And 2388.102-2966.802cm-1Fewer wave points are used, and the operation cost is reduced; the preprocessing and modeling algorithms of the optimal model are combined into an unprocessed and support vector machine algorithm, and the accuracy can reach 1; the accurate and rapid identification of the sample can be realized within 5 minutes, and the rapid detection of high-temperature sterilized milk, pasteurized milk cow fresh milk and milk powder recovered milk is realized.
Reference to the literature
[1] Quchunli et al, talk about high temperature sterilized milk and pasteurized milk [ J ]. Chinese Dairy industry, 2006(05): 61-63;
[2] wan Liu III et al, soybean seed coat crack identification research based on near infrared spectroscopy and machine learning [ J/OL ], journal of agricultural machinery, 1-15[2021-04-27 ];
[3]C.C.Fagan,C.Everard,C.P.O’Donnell,G.Downey,E.M.Sheehan,C.M.Delahunty,D.J.O’Callaghan.Evaluating Mid-infrared Spectroscopy as a New Technique for Predicting Sensory Texture Attributes of Processed Cheese[J].Journal of Dairy Science,2007,90(3)；
[4]Soyeurt H.,Grelet C.,McParland S.,Calmels M.,Coffey M.,Tedde A.,Delhez P.,Dehareng F.,Gengler N..A comparison of 4different machine learning algorithms to predict lactoferrin content in bovine milk from mid-infrared spectra[J].Journal of Dairy Science,2020,103(12)；
[5]Xu W,Knegsel A,Vervoort J,et al.Prediction of metabolic status of dairy cows in early lactation with on-farm cow data and machine learning algorithms[J].Journal of Dairy Science,2019,102(11)。
Claims (1)
1. a method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder is characterized by comprising the following steps:
1) selection of milk samples
Respectively collecting high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder;
2) acquisition of mid-IR spectra
Scanning milk samples by adopting a milk component detector, and outputting light transmittance corresponding to each sample through a connected computer;
3) data pre-processing
Converting the original spectrum data from light transmittance to absorbance, and removing abnormal values;
4) partitioning a data set
Dividing a data set into a training set and a testing set according to a layered sampling principle, wherein the training set and the testing set respectively account for 80% and 20% of the data set;
5) determining a modeled spectral band
Screening different wave bands of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and reconstituted milk of milk powder, and removing an absorption area of water;
6) model building and optimal model screening
Taking the mid-infrared spectrum of a training set sample as an input value, taking the categories of high-temperature sterilized milk, pasteurized milk cow fresh milk and milk powder recovered milk as output values, using different spectrum preprocessing methods and different modeling algorithms to combine and establish a model, using accuracy and Kappa coefficient indexes to evaluate and screen the model, and screening out an optimal model;
7) verification and application of optimal model
Taking samples of high-temperature sterilized milk, pasteurized fresh milk of dairy cows and milk powder recovered milk, identifying the samples by using the screened optimal model, and evaluating the application performance of the samples;
wherein:
when the mid-infrared spectrum is collected in the step 2), respectively pouring milk samples into cylindrical sampling tubes with the diameter of 3.5cm and the height of 9cm to ensure that the liquid level height is more than 6cm, then putting the milk samples into a water bath kettle at 42 ℃ for water bath for 15-20min, and extending a solid optical fiber probe into the liquid for sample absorption detection;
log according to A) in step 3)10(1/T) the transmittance (T) is converted into the absorbance (A) using Mahalanobis distance and milkRemoving abnormal value from the percentage content of the lactolipoprotein, and keeping the data that the mahalanobis distance of the spectrum is less than or equal to 3 and the percentage content of the milk fat and the lactoprotein is within the range of the average value +/-3.5 standard deviations, wherein the mahalanobis distance is calculated by the method that MD is sqrt [ (x-mu)TΣ-1(x-μ)]X is a spectral value, mu is a sample mean value, sigma is a covariance matrix, T represents transposition, and the mean value of the percentage content of milk fat milk protein is calculated by the method of M ═ x (x)1+x2+...+xn) N, i.e. the average milk fat, milk protein content of n samples, the standard deviation calculation method is SD ═ sqrt { [ (x)1-M)2+(x2-M)2+......(xn-M)2]/(n-1)}；
The method for screening the difference wave band used in the step 5) is Pearson correlation test and significance test of the correlation, and the spectrum wave band finally selected for modeling is 972.216-1481.472cm-1、1504.62-1577.922cm-1、1770.822-2249.214cm-1And 2388.102-2966.802cm-1；
The spectrum preprocessing method used in the step 6) comprises first-order differentiation, standard normal variable transformation, multivariate scattering correction and SG convolution smoothing, and the modeling algorithm used is random forest RF and support vector machine SVM.
The verification of the optimal model in the step 7) and the application of the optimal model are combined by a non-preprocessing and support vector machine algorithm.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110503862.6A CN113310937A (en) | 2021-05-10 | 2021-05-10 | Method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110503862.6A CN113310937A (en) | 2021-05-10 | 2021-05-10 | Method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113310937A true CN113310937A (en) | 2021-08-27 |
Family
ID=77371780
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110503862.6A Pending CN113310937A (en) | 2021-05-10 | 2021-05-10 | Method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113310937A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114184572A (en) * | 2021-11-01 | 2022-03-15 | 华中农业大学 | Intermediate infrared rapid batch detection method for alpha-lactalbumin in milk |
| CN114184573A (en) * | 2021-11-01 | 2022-03-15 | 华中农业大学 | Intermediate infrared rapid batch detection method for kappa-casein in milk |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446599A (en) * | 2018-02-27 | 2018-08-24 | 首都师范大学 | A kind of high spectrum image wave band fast selecting method of p value statistic modeling independence |
| CN108844917A (en) * | 2018-09-29 | 2018-11-20 | 山东大学 | A kind of Near Infrared Spectroscopy Data Analysis based on significance tests and Partial Least Squares |
| CN111579500A (en) * | 2020-05-20 | 2020-08-25 | 湖南城市学院 | Heavy metal content support vector machine regression method combining wave bands and ratios of indoor and outdoor spectrums |
| CN112525850A (en) * | 2020-10-01 | 2021-03-19 | 华中农业大学 | Spectral fingerprint identification method for milk, mare, camel, goat and buffalo milk |
| CN112666112A (en) * | 2020-10-01 | 2021-04-16 | 华中农业大学 | Batch discrimination model and method for camel milk and mare milk |
| CN112666111A (en) * | 2020-10-01 | 2021-04-16 | 华中农业大学 | Method for quickly identifying milk and mare milk |
-
2021
- 2021-05-10 CN CN202110503862.6A patent/CN113310937A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108446599A (en) * | 2018-02-27 | 2018-08-24 | 首都师范大学 | A kind of high spectrum image wave band fast selecting method of p value statistic modeling independence |
| CN108844917A (en) * | 2018-09-29 | 2018-11-20 | 山东大学 | A kind of Near Infrared Spectroscopy Data Analysis based on significance tests and Partial Least Squares |
| CN111579500A (en) * | 2020-05-20 | 2020-08-25 | 湖南城市学院 | Heavy metal content support vector machine regression method combining wave bands and ratios of indoor and outdoor spectrums |
| CN112525850A (en) * | 2020-10-01 | 2021-03-19 | 华中农业大学 | Spectral fingerprint identification method for milk, mare, camel, goat and buffalo milk |
| CN112666112A (en) * | 2020-10-01 | 2021-04-16 | 华中农业大学 | Batch discrimination model and method for camel milk and mare milk |
| CN112666111A (en) * | 2020-10-01 | 2021-04-16 | 华中农业大学 | Method for quickly identifying milk and mare milk |
Non-Patent Citations (2)
| Title |
|---|
| CHAO DU 等: ""Genetic Analysis of Milk Production Traits and Mid-Infrared Spectra in Chinese Holstein Population"", 《ANIMALS》 * |
| 张爱武 等: ""p值统计量建模独立性的高光谱波段选择方法"", 《红外与激光工程》 * |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114184572A (en) * | 2021-11-01 | 2022-03-15 | 华中农业大学 | Intermediate infrared rapid batch detection method for alpha-lactalbumin in milk |
| CN114184573A (en) * | 2021-11-01 | 2022-03-15 | 华中农业大学 | Intermediate infrared rapid batch detection method for kappa-casein in milk |
| CN114184572B (en) * | 2021-11-01 | 2024-02-20 | 华中农业大学 | Mid-infrared rapid batch detection method for alpha-lactalbumin in milk |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Huang et al. | Review of seed quality and safety tests using optical sensing technologies | |
| Dong et al. | Nondestructive determination of apple internal qualities using near-infrared hyperspectral reflectance imaging | |
| JP6339244B2 (en) | Method for predicting sugar content and acidity of fruit using multivariate statistical analysis of FT-IR spectrum data | |
| CN113310936A (en) | Rapid identification method for four high-temperature sterilized commercial milks | |
| Zhang et al. | Identification of corn seeds with different freezing damage degree based on hyperspectral reflectance imaging and deep learning method | |
| Cubero et al. | A new method for assessment of bunch compactness using automated image analysis | |
| Shao et al. | Determination of the bruise degree for cherry using Vis-NIR reflection spectroscopy coupled with multivariate analysis | |
| CN113310937A (en) | Method for rapidly identifying high-temperature sterilized milk, pasteurized fresh milk of dairy cow and reconstituted milk of milk powder | |
| CN113310930A (en) | Spectral identification method of high-temperature sterilized milk, pasteurized milk and pasteurized milk mixed with high-temperature sterilized milk | |
| Sharma et al. | Rapid ripening stage classification and dry matter prediction of durian pulp using a pushbroom near infrared hyperspectral imaging system | |
| Chen et al. | New approach of simultaneous, multi‐perspective imaging for quantitative assessment of the compactness of grape bunches | |
| Rafiq et al. | Application of computer vision system in food processing | |
| Yin et al. | Non-destructive detection of foreign contaminants in toast bread with near infrared spectroscopy and computer vision techniques | |
| CN113310934A (en) | Method for quickly identifying milk cow milk mixed in camel milk and mixing proportion thereof | |
| CN113324943A (en) | Yak milk and rapid identification model of milk mixed with yak milk | |
| Sun et al. | Non-destructive detection of blackheart and soluble solids content of intact pear by online NIR spectroscopy | |
| Zhang et al. | Detection of pears with moldy core using online full-transmittance spectroscopy combined with supervised classifier comparison and variable optimization | |
| CN113310929A (en) | Soybean powder doped in high-temperature sterilized milk and spectral identification method of doping proportion thereof | |
| CN112666114A (en) | Method for identifying buffalo milk and mare milk by using spectrum | |
| CN113310938A (en) | Method for rapidly identifying pasteurized fresh buffalo milk and fresh dairy cow milk | |
| US20230089466A1 (en) | Establishment of Identification and Screening Method of Cows with A2 Beta-Casein Genotype of Producing A2 Milk and Applications Thereof | |
| CN113310933A (en) | Spectrum identification method for number of days for storing raw buffalo milk | |
| Fu et al. | Discrimination of pear varieties using three classification methods based on near-infrared spectroscopy | |
| Kavdır et al. | Classification of olives using FT-NIR spectroscopy, neural networks and statistical classifiers | |
| CN113324942A (en) | Rapid identification model for raw milk, high-temperature sterilized milk and raw milk mixed with high-temperature sterilized milk |
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 |
Application publication date: 20210827 |
|
| RJ01 | Rejection of invention patent application after publication |