CN118470711A - Method for predicting shelf life of pork - Google Patents
Method for predicting shelf life of pork Download PDFInfo
- Publication number
- CN118470711A CN118470711A CN202410924073.3A CN202410924073A CN118470711A CN 118470711 A CN118470711 A CN 118470711A CN 202410924073 A CN202410924073 A CN 202410924073A CN 118470711 A CN118470711 A CN 118470711A
- Authority
- CN
- China
- Prior art keywords
- pork
- shelf life
- layer
- convolution
- pooling
- 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
- 235000015277 pork Nutrition 0.000 title claims abstract description 115
- 238000000034 method Methods 0.000 title claims abstract description 29
- 238000012549 training Methods 0.000 claims abstract description 13
- 238000013527 convolutional neural network Methods 0.000 claims abstract description 9
- 238000011176 pooling Methods 0.000 claims description 46
- 239000011159 matrix material Substances 0.000 claims description 27
- 235000020997 lean meat Nutrition 0.000 claims description 16
- 230000001953 sensory effect Effects 0.000 claims description 12
- 238000011156 evaluation Methods 0.000 claims description 11
- 230000003203 everyday effect Effects 0.000 claims description 8
- 238000004364 calculation method Methods 0.000 claims description 7
- 230000004913 activation Effects 0.000 claims description 4
- 230000000007 visual effect Effects 0.000 abstract description 3
- 238000003672 processing method Methods 0.000 abstract description 2
- 238000005057 refrigeration Methods 0.000 abstract description 2
- 230000006866 deterioration Effects 0.000 description 4
- 230000008014 freezing Effects 0.000 description 3
- 238000007710 freezing Methods 0.000 description 3
- 238000003307 slaughter Methods 0.000 description 3
- 238000012360 testing method Methods 0.000 description 3
- 238000001914 filtration Methods 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 239000002699 waste material Substances 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 210000000988 bone and bone Anatomy 0.000 description 1
- 238000010411 cooking Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 239000004519 grease Substances 0.000 description 1
- 235000013372 meat Nutrition 0.000 description 1
- 210000003205 muscle Anatomy 0.000 description 1
- 235000020989 red meat Nutrition 0.000 description 1
- 230000008961 swelling Effects 0.000 description 1
Classifications
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02P—CLIMATE CHANGE MITIGATION TECHNOLOGIES IN THE PRODUCTION OR PROCESSING OF GOODS
- Y02P90/00—Enabling technologies with a potential contribution to greenhouse gas [GHG] emissions mitigation
- Y02P90/30—Computing systems specially adapted for manufacturing
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to the technical field of data processing methods for prediction purposes, in particular to a quality guarantee period prediction method for pork; training a model by establishing a convolutional neural network based on a specific architecture and obtaining a pork quality guarantee period prediction model by acquiring training samples in advance, wherein the training samples comprise pork shooting image information with different refrigeration time as input and corresponding frozen quality guarantee periods as output; when a customer purchases pork, image information of the corresponding pork is acquired through the camera and is input into the prediction model, an output result matched with the probability of the corresponding shelf life can be output, so that the actual frozen shelf life of the pork can be predicted under the condition that the specific shelf life is not calculated, and the actual frozen shelf life is marked on the pork package, so that the actual frozen shelf life of the pork with different shelf lives can be reflected efficiently, and the customer obtains visual and safe shopping experience.
Description
Technical Field
The invention relates to the technical field of data processing methods for predicting purposes, in particular to a method for predicting the shelf life of pork.
Background
During the process of conveying pork from a slaughtering place to a point of sale and during the process of selling pork in shops, the shelf life is different due to the difference of ambient temperature and humidity, and after customers purchase pork, the pork can be stored by refrigerating at 4 ℃ through a refrigerator, or can be stored by freezing at-20 ℃ after being split-packaged; when the existing fresh pork is sold, the quality guarantee period is not generally marked clearly, and the actual quality guarantee period of the pork is difficult to estimate accurately because the actual quality guarantee period of the pork is different due to the environmental factors after the pork is slaughtered.
In particular, pork frozen in a refrigerator has a slow deterioration rate in a frozen state, but the pork still generates deterioration after being frozen for a long time for a plurality of months, so that sensory indexes are reduced; therefore, if the shelf life of the frozen pork can be accurately predicted, customers can eat the frozen pork before the pork is spoiled, and waste caused by spoilage is avoided.
Disclosure of Invention
The technical problems to be solved by the invention are as follows: the method for predicting the quality guarantee period of the pork can accurately ensure that customers can accurately eat the pork before the pork is spoiled, and avoid waste caused by spoilage.
In order to solve the technical problems, the invention adopts the following technical scheme:
the method for predicting the shelf life of pork comprises the following steps:
When selling pork, acquiring image information of lean meat parts of the pork, inputting a pre-trained shelf life prediction model, and outputting a corresponding shelf life prediction value;
The shelf life prediction model is based on a convolutional neural network, and the architecture of the convolutional neural network comprises an input layer, two calculation paths behind the input layer, a full connection layer and an output layer;
The first path comprises a first convolution layer, a first pooling layer, a second convolution layer and a second pooling layer which are distributed in sequence in the two calculation paths; the second path comprises a third convolution layer, a third pooling layer, a fourth convolution layer, a fourth pooling layer, a fifth convolution layer and a fifth pooling layer which are sequentially distributed;
The training sample data of the prediction model comprises input information and output information, wherein the input information is lean meat part image information obtained after slaughtered pork is stored for a specific time at the temperature of 4 ℃, and the output information is the actual shelf life of the lean meat stored frozen at-20 ℃ after the lean meat is placed for 20min at the temperature of 30 ℃.
In the method for predicting the shelf life of pork, the input information in the sample data is specifically that after the slaughtered pork is stored for 3 hours at the temperature of 4 ℃, m parts of pork are taken out every 0.5 hour, and corresponding lean meat part image information is obtained until 48 hours are reached, and then stopping.
In the method for predicting the shelf life of pork, the actual shelf life of the frozen pork stored at-20 ℃ is specifically from day 90 of the frozen pork, 1 part of frozen pork stored at 4 ℃ for 48 hours is taken out every day for sensory evaluation, until the sensory evaluation judges that the pork is deteriorated, the corresponding days are recorded, namely the actual shelf life of the frozen pork stored at-20 ℃, then one part of frozen pork stored at 4 ℃ for 47.5 hours is taken out every day for sensory evaluation, and the corresponding days of deterioration are recorded as the actual shelf life of the frozen pork stored at-20 ℃.
In the pork quality guarantee period prediction method, the number of convolution kernels of the first convolution layer is 128, the convolution kernels are a matrix of 3×3 pixels, the step length is 2, the first pooling layer is a matrix of 2×2 pixels, and average pooling is adopted.
In the pork quality guarantee period prediction method, the number of convolution kernels of the second convolution layer is 256, the convolution kernels are a matrix of 4 multiplied by 4 pixels, the step length is 2, the second pooling layer is a matrix of 3 multiplied by 3 pixels, and maximum pooling is adopted.
In the pork quality guarantee period prediction method, the number of convolution kernels of the third convolution layer is 512, the convolution kernels are 4×4 matrixes of pixels, the step length is 2, the third pooling layer is 3×3 matrixes of pixels, and average pooling is adopted.
In the pork quality guarantee period prediction method, the number of convolution kernels of the fourth convolution layer is 384, the convolution kernels are a matrix of 3×3 pixels, the step length is 2, the fourth pooling layer is a matrix of 3×3 pixels, and average pooling is adopted.
In the pork quality guarantee period prediction method, the number of convolution kernels of the fifth convolution layer is 128, the convolution kernels are a matrix of 4×4 pixels, the step length is 2, the fifth pooling layer is a matrix of 2×2 pixels, and average pooling is adopted.
Further, in the method for predicting the shelf life of pork, the output layer obtains an output result through a softmax activation function.
The invention has the beneficial effects that: training a model by establishing a convolutional neural network based on a specific architecture and obtaining a pork quality guarantee period prediction model by acquiring training samples in advance, wherein the training samples comprise pork shooting image information with different refrigeration time as input and corresponding frozen quality guarantee periods as output; when a customer purchases pork, image information of the corresponding pork is acquired through the camera and is input into the prediction model, an output result matched with the probability of the corresponding shelf life can be output, so that the actual frozen shelf life of the pork can be predicted under the condition that the specific shelf life is not calculated, and the actual frozen shelf life is marked on the pork package, so that the actual frozen shelf life of the pork with different shelf lives can be reflected efficiently, and the customer obtains visual and safe shopping experience.
Drawings
FIG. 1 is a schematic diagram of a shelf life prediction model of pork according to the present invention;
Detailed Description
In order to describe the technical contents, the achieved objects and effects of the present invention in detail, the following description will be made with reference to the embodiments in conjunction with the accompanying drawings.
The specific embodiment of the invention relates to a method for predicting the shelf life of pork, which comprises the following steps:
When selling pork, acquiring image information of lean meat parts of the pork, inputting a pre-trained shelf life prediction model, and outputting a corresponding shelf life prediction value;
Referring to fig. 1, the shelf life prediction model is based on a convolutional neural network, and the architecture of the convolutional neural network includes an input layer, two calculation paths after the input layer, a full connection layer and an output layer;
The first path comprises a first convolution layer, a first pooling layer, a second convolution layer and a second pooling layer which are distributed in sequence in the two calculation paths; the second path comprises a third convolution layer, a third pooling layer, a fourth convolution layer, a fourth pooling layer, a fifth convolution layer and a fifth pooling layer which are sequentially distributed;
The training sample data of the prediction model comprises input information and output information, wherein the input information is lean meat part image information obtained after slaughtered pork is stored for a specific time at the temperature of 4 ℃, and the output information is the actual shelf life of the lean meat stored frozen at-20 ℃ after the lean meat is placed for 20min at the temperature of 30 ℃.
In the above embodiment, the prediction model is based on a convolutional neural network, and the structure of the prediction model comprises an input layer, wherein the input layer is used for inputting sample image information, the prediction model further comprises a hidden layer, the hidden layer comprises 2 calculation paths, and each path comprises a convolutional layer and a pooling layer which are mutually independent and have different layers and are distributed, so that the purpose of extracting color and texture features of the input sample image information is achieved.
The first path sequentially comprises a first convolution layer (the number of convolution kernels is 128, the pixel point 3×3 matrix and the step length is 2), a first pooling layer (the pixel point 2×2 matrix adopts average pooling), a second convolution layer (the number of convolution kernels is 256, the pixel point 4×4 matrix and the step length is 2), and a second pooling layer (the pixel point 3×3 matrix adopts maximum pooling);
The second path is sequentially a third convolution layer (the number of convolution kernels is 512, the pixel point is 4×4 matrix, the step length is 2), a third pooling layer (the pixel point is 3×3 matrix, and average pooling is adopted), a fourth convolution layer (the number of convolution kernels is 384, the step length is 2), a fourth pooling layer (the pixel point is 3×3 matrix, and average pooling is adopted), a fifth convolution layer (the number of convolution kernels is 128, the pixel point is 4×4 matrix, and the step length is 2), and a fifth pooling layer (the pixel point is 2×2 matrix, and average pooling is adopted);
In a preferred embodiment, in the sample data, the input information is specifically that after the slaughtered pork is stored for 3 hours at the temperature of 4 ℃, m parts of pork are taken out every 0.5 hour, and the corresponding lean meat part image information is obtained until 48 hours later.
In a preferred embodiment, in the sample data, the actual shelf life of the frozen pork stored at-20 ℃ is specifically that from day 90 of the frozen pork, 1 part of frozen pork stored at 4 ℃ for 48 hours is taken out every day, sensory evaluation is performed until the sensory evaluation judges that the pork is deteriorated, the corresponding days are recorded, namely the actual shelf life of the frozen pork stored at-20 ℃, then one part of frozen pork stored at 4 ℃ for 47.5 hours is taken out every day, sensory evaluation is performed, and the corresponding days when the pork is deteriorated are recorded, namely the actual shelf life of the frozen pork stored at-20 ℃.
Specifically, after slaughtering pork, cutting the pork into n parts, storing each part at 4 ℃, simulating the shelf life, taking out m parts of pork (99 m < n) every 0.5h after storing for 3 hours, photographing red meat parts (lean meat parts) to obtain sample image information, and then respectively standing at 30 ℃ for 20 minutes, and then freezing at-20 ℃ until storing at 4 ℃ for 48 hours; taking out the pork stored for 48 hours at the temperature of 4 ℃ every day from 90 days, performing sensory evaluation including smell and taste eaten after cooking, comprehensively judging whether the pork is deteriorated, and recording the corresponding days after the pork stored for 48 hours at the temperature of 4 ℃ is deteriorated, namely the actual shelf life of the pork stored for 48 hours at the temperature of 4 ℃; taking out pork stored at 4 ℃ for 47.5 hours every day, performing sensory evaluation until the pork stored at 4 ℃ for 47.5 hours is deteriorated, and recording the corresponding days, namely the actual shelf life of the pork stored at 4 ℃ for 47.5 hours; and so on until the actual shelf life of pork stored at 4 ℃ for 3 hours is recorded. In the scheme, the longer the pork is stored at 4 ℃, the shorter the actual shelf life is, so that the actual shelf life and the shelf life are in a certain linear mapping relation, and the acquisition difficulty of the training sample can be greatly reduced through the method. The above included 99x training samples, 99y test samples, (m=x+y); respectively including corresponding sample image information and corresponding actual shelf life parameters.
In the above sample information, since pork is generally refrigerated and transported at 4 ℃ after slaughtering, and is also placed in a refrigerated environment at 4 ℃ when sold on a shelf, so as to improve the shelf life of the pork, and the pork is placed at 30 ℃ for 20min, the fact that customers can return home at a higher temperature after purchasing the pork is considered, the journey time is estimated to be 20min, the temperature is set to be 30 ℃ higher than the average standard, and a certain amount of advance can exist in the actual shelf life obtained through the experiment, so that the customers can be guaranteed to eat the pork before the actual shelf life, and better quality can be guaranteed.
In the above sample information, in order to ensure pork quality, the shelf life of fresh pork at 4 ℃ is generally not more than 2 days, namely 48 hours, otherwise deterioration may occur before freezing.
As a preferred embodiment, the output layer obtains the output result by a softmax activation function.
Outputting the results output by the first path and the second path to a full-connection layer, obtaining an output result through a softmax activation function, and mapping the output result to a corresponding actual shelf life result through onehot codes; training the prediction model by taking image information corresponding to 99x training samples as input, and if the actual output of the output layer is different from the expected output, turning to error back propagation so as to adjust the weight of the convolution kernel; by reserving 99y test samples for testing the trained model, the accuracy can reach more than 86%.
In order to improve accuracy of image recognition, filtering invalid information of the image, such as grease, fat, bones and muscles, is further included before the image information is input into the prediction model, and since the images of the parts cannot effectively reflect freshness of the meat, pixel values of the parts and lean parts are greatly different, filtering, such as swelling and corrosion treatment, is easily performed on the pixel points through the prior art, and a specific method is not repeated here.
In practical application, when a customer purchases pork, image information of the corresponding pork is obtained through a camera and is input into a prediction model, an output result matched with the probability of the corresponding shelf life can be output, so that the actual frozen shelf life of the pork can be predicted under the condition that the specific shelf life is not calculated, and the actual frozen shelf life is marked on the pork package, so that the actual frozen shelf life of the pork with different shelf lives can be reflected efficiently, and the customer obtains visual and safe shopping experience.
The foregoing description is only illustrative of the present invention and is not intended to limit the scope of the invention, and all equivalent changes made by the specification and drawings of the present invention, or direct or indirect application in the relevant art, are included in the scope of the present invention.
Claims (9)
1. The method for predicting the shelf life of pork is characterized by comprising the following steps of:
When selling pork, acquiring image information of lean meat parts of the pork, inputting a pre-trained shelf life prediction model, and outputting a corresponding shelf life prediction value;
The shelf life prediction model is based on a convolutional neural network, and the architecture of the convolutional neural network comprises an input layer, two calculation paths behind the input layer, a full connection layer and an output layer;
The first path comprises a first convolution layer, a first pooling layer, a second convolution layer and a second pooling layer which are distributed in sequence in the two calculation paths; the second path comprises a third convolution layer, a third pooling layer, a fourth convolution layer, a fourth pooling layer, a fifth convolution layer and a fifth pooling layer which are sequentially distributed;
The training sample data of the prediction model comprises input information and output information, wherein the input information is lean meat part image information obtained after slaughtered pork is stored for a specific time at the temperature of 4 ℃, and the output information is the actual shelf life of the lean meat stored frozen at-20 ℃ after the lean meat is placed for 20min at the temperature of 30 ℃.
2. The method for predicting the shelf life of pork according to claim 1, wherein in the sample data, the input information is specifically that after the slaughtered pork is stored for 3 hours at 4 ℃, m parts of pork are taken out every 0.5 hour, and the corresponding lean meat part image information is obtained until 48 hours are reached, and then the method is stopped.
3. The method for predicting the shelf life of pork according to claim 2, wherein in the sample data, the actual shelf life of the frozen pork stored at-20 ℃ is specifically that from day 90 of the frozen pork, 1 part of the frozen pork stored at 4 ℃ for 48 hours is taken out every day, sensory evaluation is performed until the sensory evaluation judges that the pork is deteriorated, the corresponding days are recorded, namely the actual shelf life of the frozen pork stored at-20 ℃, then one part of the frozen pork stored at 4 ℃ for 47.5 hours is taken out every day, sensory evaluation is performed, and the corresponding days when the pork is deteriorated are recorded, namely the actual shelf life of the frozen pork stored at-20 ℃.
4. The method for predicting the shelf life of pork as claimed in claim 1, wherein the number of convolution kernels of the first convolution layer is 128, the convolution kernels are 3 x 3 matrix of pixels, the step length is 2, the first pooling layer is 2 x 2 matrix of pixels, and the average pooling is adopted.
5. The method for predicting the shelf life of pork as claimed in claim 1, wherein the number of convolution kernels of the second convolution layer is 256, the convolution kernels are 4 x 4 matrix of pixels, the step size is 2, the second pooling layer is 3 x 3 matrix of pixels, and the maximum pooling is adopted.
6. The method for predicting the shelf life of pork as claimed in claim 1, wherein the number of convolution kernels of the third convolution layer is 512, the number of convolution kernels is a 4×4 matrix of pixels, the step size is 2, the third pooling layer is a 3×3 matrix of pixels, and the average pooling is adopted.
7. The method for predicting the shelf life of pork as claimed in claim 1, wherein the number of convolution kernels of the fourth convolution layer is 384, the number of convolution kernels is a 3 x 3 matrix of pixels, the step size is 2, the fourth pooling layer is a 3 x 3 matrix of pixels, and the average pooling is adopted.
8. The method for predicting the shelf life of pork as claimed in claim 1, wherein the number of convolution kernels of the fifth convolution layer is 128, the convolution kernels are 4 x 4 matrix of pixels, the step size is 2, the fifth pooling layer is 2 x 2 matrix of pixels, and the average pooling is adopted.
9. The method of claim 1, wherein the output layer obtains the output by a softmax activation function.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410924073.3A CN118470711A (en) | 2024-07-11 | 2024-07-11 | Method for predicting shelf life of pork |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202410924073.3A CN118470711A (en) | 2024-07-11 | 2024-07-11 | Method for predicting shelf life of pork |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN118470711A true CN118470711A (en) | 2024-08-09 |
Family
ID=92164162
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202410924073.3A Pending CN118470711A (en) | 2024-07-11 | 2024-07-11 | Method for predicting shelf life of pork |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN118470711A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109961030A (en) * | 2019-03-18 | 2019-07-02 | 北京邮电大学 | Pavement patching information detecting method, device, equipment and storage medium |
| CN110663971A (en) * | 2018-07-02 | 2020-01-10 | 天津工业大学 | Red date quality classification method based on double-branch deep fusion convolutional neural network |
| CN110889448A (en) * | 2019-11-26 | 2020-03-17 | 北京华医共享医疗科技有限公司 | Electrocardiogram classification method based on convolutional neural network |
| US20220147755A1 (en) * | 2020-11-06 | 2022-05-12 | Tata Consultancy Services Limited | Method and system for real-time shelf-life prediction of food items |
-
2024
- 2024-07-11 CN CN202410924073.3A patent/CN118470711A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110663971A (en) * | 2018-07-02 | 2020-01-10 | 天津工业大学 | Red date quality classification method based on double-branch deep fusion convolutional neural network |
| CN109961030A (en) * | 2019-03-18 | 2019-07-02 | 北京邮电大学 | Pavement patching information detecting method, device, equipment and storage medium |
| CN110889448A (en) * | 2019-11-26 | 2020-03-17 | 北京华医共享医疗科技有限公司 | Electrocardiogram classification method based on convolutional neural network |
| US20220147755A1 (en) * | 2020-11-06 | 2022-05-12 | Tata Consultancy Services Limited | Method and system for real-time shelf-life prediction of food items |
Non-Patent Citations (1)
| Title |
|---|
| 房永智，刘建吉，刘军: "《无人化工程机械现状及发展对策研究》", 28 February 2021, 北京工业大学出版社, pages: 1 * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| KR102236974B1 (en) | Method, device, and system ofquality classifying and selling packed meat based on image | |
| Ndraha et al. | Evaluation of the cold chain management options to preserve the shelf life of frozen shrimps: A case study in the home delivery services in Taiwan | |
| Giménez et al. | Sensory shelf-life estimation: A review of current methodological approaches | |
| Umberger et al. | COUNTRY-OF-ORIGIN LABELING OF BEEF PRODUCTS: US CONSUMERS'PERCEPTIONS | |
| CN110210680A (en) | A kind of fish body Noninvasive Measuring Method of Freshness and device based on temperature change | |
| CN113791055B (en) | Fish freshness detection method and system | |
| Manzocco | The acceptability limit in food shelf life studies | |
| Østli et al. | How fresh is fresh? Perceptions and experience when buying and consuming fresh cod fillets | |
| Bowker et al. | Measurement of muscle exudate protein composition as an indicator of beef tenderness | |
| Nielsen et al. | Substitution of unprocessed and processed red meat with poultry or fish and total and cause-specific mortality | |
| CN111724350A (en) | Nondestructive testing method and device for freshness of fish body | |
| CN114965910A (en) | Meat quality sensing method and device | |
| de la Cruz Quiroz et al. | Residential refrigerator performance based on microbial indicators of ground beef preservation assessed using predictive microbiology tools | |
| Kim et al. | Estimation of real-time remaining shelf life using mean kinetic temperature | |
| CN118470711A (en) | Method for predicting shelf life of pork | |
| CN111248716B (en) | Food cooking control method, image processing method and device and cooking equipment | |
| Mai et al. | Kinetics of quality changes of Pangasius fillets at stable and dynamic temperatures, simulating downstream cold chain conditions | |
| CN117710530A (en) | Image generation method, device, equipment and storage medium | |
| JP2021136026A (en) | Perishable food current state information record update device, perishable food current state information record update system, method for updating perishable food current state information record, and perishable food current state information record update program | |
| CN116205688A (en) | Fresh product information processing method and device, computer equipment and storage medium | |
| Chengappa et al. | Changing demand for livestock food products: An evidence from Indian households | |
| Stathas et al. | Quantitative microbial risk assessment of Salmonella in fresh chicken patties | |
| CN118261492B (en) | Nondestructive testing method and system for comprehensive quality of fresh pork | |
| Price et al. | Differences in carcass chilling rate underlie differences in sensory traits of pork chops from pigs with heavier carcass weights | |
| Carrasco et al. | Food safety risk management |
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 |