CN115372569A - Red wine quality evaluation method and system based on long-term and short-term memory neural network - Google Patents
Red wine quality evaluation method and system based on long-term and short-term memory neural network Download PDFInfo
- Publication number
- CN115372569A CN115372569A CN202210998982.2A CN202210998982A CN115372569A CN 115372569 A CN115372569 A CN 115372569A CN 202210998982 A CN202210998982 A CN 202210998982A CN 115372569 A CN115372569 A CN 115372569A
- Authority
- CN
- China
- Prior art keywords
- red wine
- quality evaluation
- wine quality
- training
- model
- 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
- 235000020095 red wine Nutrition 0.000 title claims abstract description 85
- 238000013441 quality evaluation Methods 0.000 title claims abstract description 43
- 238000000034 method Methods 0.000 title claims abstract description 42
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 18
- 230000007787 long-term memory Effects 0.000 title claims abstract description 10
- 230000006403 short-term memory Effects 0.000 title claims abstract description 9
- 238000012549 training Methods 0.000 claims abstract description 62
- 238000012360 testing method Methods 0.000 claims abstract description 25
- 238000011156 evaluation Methods 0.000 claims abstract description 22
- 238000013210 evaluation model Methods 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 17
- 238000012795 verification Methods 0.000 claims abstract description 8
- KRKNYBCHXYNGOX-UHFFFAOYSA-N citric acid Chemical compound OC(=O)CC(O)(C(O)=O)CC(O)=O KRKNYBCHXYNGOX-UHFFFAOYSA-N 0.000 claims description 30
- 238000004458 analytical method Methods 0.000 claims description 12
- 239000002253 acid Substances 0.000 claims description 10
- 230000015654 memory Effects 0.000 claims description 10
- LFQSCWFLJHTTHZ-UHFFFAOYSA-N Ethanol Chemical compound CCO LFQSCWFLJHTTHZ-UHFFFAOYSA-N 0.000 claims description 9
- 238000010606 normalization Methods 0.000 claims description 9
- 238000012545 processing Methods 0.000 claims description 8
- 230000002159 abnormal effect Effects 0.000 claims description 6
- 238000006467 substitution reaction Methods 0.000 claims description 5
- 230000000694 effects Effects 0.000 abstract description 5
- 238000005065 mining Methods 0.000 abstract description 3
- 238000013135 deep learning Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 7
- 230000008569 process Effects 0.000 description 6
- 230000004913 activation Effects 0.000 description 3
- 238000005259 measurement Methods 0.000 description 3
- 238000002203 pretreatment Methods 0.000 description 3
- 239000000126 substance Substances 0.000 description 3
- 235000014101 wine Nutrition 0.000 description 3
- 230000001476 alcoholic effect Effects 0.000 description 2
- 238000004364 calculation method Methods 0.000 description 2
- 238000013480 data collection Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004519 manufacturing process Methods 0.000 description 2
- 238000003908 quality control method Methods 0.000 description 2
- 238000010561 standard procedure Methods 0.000 description 2
- FEWJPZIEWOKRBE-UHFFFAOYSA-N Tartaric acid Natural products [H+].[H+].[O-]C(=O)C(O)C(O)C([O-])=O FEWJPZIEWOKRBE-UHFFFAOYSA-N 0.000 description 1
- 235000003095 Vaccinium corymbosum Nutrition 0.000 description 1
- 240000000851 Vaccinium corymbosum Species 0.000 description 1
- 235000017537 Vaccinium myrtillus Nutrition 0.000 description 1
- 241000219094 Vitaceae Species 0.000 description 1
- 235000009754 Vitis X bourquina Nutrition 0.000 description 1
- 235000012333 Vitis X labruscana Nutrition 0.000 description 1
- 240000006365 Vitis vinifera Species 0.000 description 1
- 235000014787 Vitis vinifera Nutrition 0.000 description 1
- 150000007513 acids Chemical class 0.000 description 1
- 230000032683 aging Effects 0.000 description 1
- 235000001014 amino acid Nutrition 0.000 description 1
- 150000001413 amino acids Chemical class 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 235000021014 blueberries Nutrition 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 230000008034 disappearance Effects 0.000 description 1
- 235000013399 edible fruits Nutrition 0.000 description 1
- 238000004880 explosion Methods 0.000 description 1
- 238000000855 fermentation Methods 0.000 description 1
- 230000004151 fermentation Effects 0.000 description 1
- 239000000796 flavoring agent Substances 0.000 description 1
- 235000019634 flavors Nutrition 0.000 description 1
- 235000013305 food Nutrition 0.000 description 1
- 235000019990 fruit wine Nutrition 0.000 description 1
- 235000019674 grape juice Nutrition 0.000 description 1
- 235000021021 grapes Nutrition 0.000 description 1
- 230000005484 gravity Effects 0.000 description 1
- 229910052500 inorganic mineral Inorganic materials 0.000 description 1
- 235000010755 mineral Nutrition 0.000 description 1
- 239000011707 mineral Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 235000010987 pectin Nutrition 0.000 description 1
- 239000001814 pectin Substances 0.000 description 1
- 229920001277 pectin Polymers 0.000 description 1
- 150000008442 polyphenolic compounds Chemical class 0.000 description 1
- 235000013824 polyphenols Nutrition 0.000 description 1
- 230000009759 skin aging Effects 0.000 description 1
- 235000000346 sugar Nutrition 0.000 description 1
- 239000001648 tannin Substances 0.000 description 1
- 235000018553 tannin Nutrition 0.000 description 1
- 229920001864 tannin Polymers 0.000 description 1
- 239000011975 tartaric acid Substances 0.000 description 1
- 235000002906 tartaric acid Nutrition 0.000 description 1
- 235000013343 vitamin Nutrition 0.000 description 1
- 229940088594 vitamin Drugs 0.000 description 1
- 229930003231 vitamin Natural products 0.000 description 1
- 239000011782 vitamin Substances 0.000 description 1
- 235000020097 white wine Nutrition 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N33/00—Investigating or analysing materials by specific methods not covered by groups G01N1/00 - G01N31/00
- G01N33/02—Food
- G01N33/14—Beverages
- G01N33/146—Beverages containing alcohol
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/049—Temporal neural networks, e.g. delay elements, oscillating neurons or pulsed inputs
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Computing Systems (AREA)
- Software Systems (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Molecular Biology (AREA)
- Biophysics (AREA)
- General Engineering & Computer Science (AREA)
- Biomedical Technology (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Artificial Intelligence (AREA)
- Food Science & Technology (AREA)
- Chemical & Material Sciences (AREA)
- Medicinal Chemistry (AREA)
- Analytical Chemistry (AREA)
- Biochemistry (AREA)
- Immunology (AREA)
- Pathology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a method and a system for evaluating the quality of red wine based on a long-term and short-term memory neural network, wherein the method comprises the following steps: collecting a red wine sample, and analyzing each index of the red wine sample to obtain index data; preprocessing the index data to obtain preprocessed data, and dividing the preprocessed data into a training set and a test set according to a preset proportion; carrying out LSTM model training based on the training set to obtain an initial evaluation model, and carrying out robustness verification and debugging based on the test set to obtain a red wine quality evaluation model; and carrying out red wine quality evaluation based on the red wine quality evaluation model to obtain a red wine quality grading evaluation result. The method adopts the deep learning prediction method of the LSTM model, and can accurately analyze and evaluate the quality of the red wine by utilizing the characteristic that the LSTM model has excellent effects in the aspects of mining and utilizing hidden information and transmitting effective information.
Description
Technical Field
The application relates to the field of food quality control, in particular to a red wine quality evaluation method and system based on a long-term and short-term memory neural network.
Background
The red wine is fruit wine produced by fermenting fruits such as grapes and blueberries. Can be divided into red wine, white wine and pink wine. The red wine contains various vitamins, amino acids, polyphenol and other substances, has obvious effect on preventing skin aging, and has the effects of resisting aging, beautifying and helping sleep. Is very popular with consumers all over the world.
The red wine contains more than 80% of grape juice, 10-30% of alcohol produced by natural fermentation of sugar, and tartaric acid, pectin, minerals and tannin as the rest components. The total number is more than 1000, wherein more than 300 substances with larger flavor influence exist, and the substances account for lower specific gravity and are the decisive factor of the quality of the wine. The red wine has good quality and delicious taste because the red wine can present a balance of tissue structure, so that people can enjoy endless enjoyment in taste. With the increase of the consumption amount and the market scale of red wine, the knowledge of consumers on red wine is insufficient, and the red wine information is not equal, so that various losses are caused.
At present, the quality control of red wine is always a difficult problem worldwide, the grade division of the age of grape trees cannot be accurately classified according to the year of the production place, and the difference of the wine brewed in the same batch or different batches in the same production place is large.
Disclosure of Invention
The application provides a red wine quality prediction method and a red wine quality prediction system based on a long-term and short-term memory neural network, and the red wine quality is accurately analyzed and evaluated by utilizing the characteristic that an LSTM model has excellent effects in the aspects of mining and utilizing hidden information and transmitting effective information.
In order to achieve the above purpose, the present application provides the following solutions:
the red wine quality evaluation method based on the long-short term memory neural network comprises the following steps:
s1, collecting a red wine sample, and analyzing each index of the red wine sample to obtain index data;
s2, preprocessing the index data to obtain preprocessed data, and dividing the preprocessed data into a training set and a test set according to a preset proportion;
s3, carrying out LSTM model training based on the training set to obtain an initial evaluation model, and carrying out robustness verification and debugging based on the test set to obtain a red wine quality evaluation model;
and S4, carrying out red wine quality evaluation based on the red wine quality evaluation model to obtain a red wine quality grading evaluation result.
Preferably, the index data includes: volatile acid, citric acid, pH and alcohol content.
Preferably, the pretreatment method comprises the following steps:
correcting abnormal values in the index data by adopting an average value substitution method to obtain corrected data; and carrying out normalization processing on the corrected data by a decimal scaling normalization method to obtain preprocessed data.
Preferably, the predetermined ratio of the training set to the test set is 8:2.
Preferably, the training method of the initial evaluation model includes:
setting the training iteration times, the LSTM layer number, the optimizer, the input batch size and the model learning rate of the LSTM model, initializing network internal parameters, and inputting the training set into the LSTM model for training to obtain the initial evaluation model.
Preferably, the training method of the red wine quality evaluation model comprises the following steps:
inputting the test set into the initial evaluation model for processing and analysis to obtain an analysis result;
and comparing the analysis result with the index data to obtain a comparison result, and debugging according to the comparison result to obtain the red wine quality evaluation model.
Preferably, the method for evaluating the quality of the red wine comprises the following steps:
and inputting various index data of the red wine to be evaluated based on the red wine quality evaluation model to obtain a red wine quality evaluation result.
The application also provides a red wine quality evaluation system based on the long-term and short-term memory neural network, which comprises the following steps: the device comprises a data acquisition module, a preprocessing module, a training module and an evaluation module;
the data acquisition module is connected with the preprocessing module and is used for acquiring a red wine sample and analyzing each index of the red wine sample to obtain index data;
the preprocessing module is further connected with the training module and used for preprocessing the index data to obtain preprocessed data and dividing the preprocessed data into a training set and a test set according to a preset proportion;
the training module is also connected with the evaluation module, and is used for carrying out LSTM model training based on the training set to obtain an initial evaluation model, and then carrying out robustness verification and debugging based on the test set to obtain a red wine quality evaluation model;
the evaluation module is used for carrying out red wine quality evaluation based on the red wine quality evaluation model to obtain a red wine quality grading evaluation result.
The application has the following beneficial effects:
the method adopts the deep learning prediction method of the LSTM model, solves the problems of gradient disappearance and gradient explosion existing in the long sequence training process, is more stable in operation, more accurate in result, simple in implementation, and has a long-term memory function, and the LSTM model has the characteristic of excellent effect in the aspects of mining and utilizing hidden information and transmitting effective information, so that the quality of the red wine can be accurately analyzed and evaluated.
Drawings
In order to more clearly illustrate the technical solution of the present application, the drawings needed to be used in the embodiments are briefly introduced below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for a person skilled in the art to obtain other drawings without any inventive exercise.
FIG. 1 is a schematic flow chart of a red wine quality prediction method based on a long-short term memory neural network according to the present application;
FIG. 2 is a schematic diagram of the LSTM model in the present application;
FIG. 3 is a schematic structural diagram of a red wine quality prediction system based on a long-short term memory neural network according to the present application.
Detailed Description
The technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the drawings in the embodiments of the present application, and it is obvious that the described embodiments are only a part of the embodiments of the present application, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
In order to make the aforementioned objects, features and advantages of the present application more comprehensible, the present application is described in further detail with reference to the accompanying drawings and the detailed description.
Example one
In the first embodiment, as shown in fig. 1, the method for predicting the quality of red wine based on the long-term and short-term memory neural network includes the following steps:
s1, collecting a red wine sample, and analyzing each index of the red wine sample to obtain index data; wherein the index data includes: volatile acid, citric acid, pH and alcohol content.
S2, preprocessing the index data to obtain preprocessed data, and dividing the preprocessed data into a training set and a test set according to a preset proportion; the pretreatment method comprises the following steps: correcting abnormal values in the index data by adopting an average value substitution method to obtain corrected data, wherein the abnormal values are conditions of data missing values caused by experimental errors in the data collection process, such as problems of volatile acids, citric acid, pH values, alcohol degree index measurement errors and the like, and the average value of the data close to the missing data is used as a substitute for the missing values or the measurement errors in the data by adopting the average value substitution method, or the input data is compared with the training set data, and the average value of the training set data close to the missing value data is used as a substitute to further obtain the corrected data; normalizing the corrected data by a decimal scaling normalization method to obtain preprocessed data; the pre-processed data is divided into a training set and a test set, wherein the proportion of the training set to the test set is 8:2.
Wherein, the normalization processing procedure comprises: after volatile acid, citric acid, pH value and alcohol content data are collected, normalization of the data is carried out by moving the position of a decimal point, and the data are mapped into the range of 0-1.
S3, carrying out LSTM model training based on the training set to obtain an initial evaluation model, and carrying out robustness verification and debugging based on the test set to obtain a red wine quality evaluation model; wherein the robustness verification process comprises: and inputting the model by using a test set or other updated experimental data, comparing the difference between the predicted output and the true value of the model, and evaluating by adopting an evaluation index. If the difference between the prediction evaluation index of the model and the evaluation index in the training stage is still small and no drastic fluctuation exists, the trained model has good robustness when being used for responding to new data.
The LSTM model in this application is shown in fig. 2 and comprises three parts: forgetting gate, input gate and output gate. The forgetting gate is used for selectively forgetting the historical information at the previous moment. Forgetting to read output h of last moment by the gate t-1 And input x of the current time t And carrying out nonlinear activation on the result through a Sigmoid activation function to obtain the output f of the forgetting gate t 。
f t =σ(w f (h t-1 ,x t )+b f )
Wherein x is t Indicating input at time t, w f Representing a forgetting gate weight, b f The method comprises the following steps of (1) representing a bias term of a forgetting gate, wherein sigma represents a Sigmoid activation function, and the calculation method comprises the following steps: σ (x) = 1/(1-e) -x ),f t The degree of forgetting the history time information in the cell state is controlled to a forgetting gate attenuation coefficient, and the calculation result is between 0 and 1. When f is t If =1, the history information is completely reserved; f. of t The time of =0 represents completely forgetting the history information.
The input gate is used for selectively memorizing the input information at the current moment and storing the information in the cell state.
a t =σ(w a (h t-1 ,x t )+b a )
C t =tan h(w c (h t-1 ,x t )+b e )
Wherein, a t Is to select data information using Sigmoid function, c t Is the selection input information obtained using the tanh function. w is a a 、w c Representing entry gate weight, b a 、b c Respectively, input gate bias terms.Representing the Hadamard product. i all right angle t The input gate attenuation coefficient is expressed, and the degree of memory of the current input time information in the cell state is controlled.
Updating the cell state according to the attenuation coefficients of the forgetting gate and the input gate, wherein the updating formula of the cell state is as follows:
C t =f t C t-1 +i t
wherein, C t-1 Indicating the state of the cells at the previous time. The output gate of LSTM determines the current output according to the current cell state, the structure uses tanh function to process the current cell state, and combines with Sigmoid function to form the output h of the current state t 。
o i =σ(w o (h t-1 ,x t )+b o )
Wherein w 0 Representing output gate weight, b o Represents a bias term, o t The output gate attenuation coefficient is indicated.
The training method of the initial evaluation model comprises the following steps:
setting the training iteration times of the LSTM model, the number of LSTM layers, the optimizer, the input batch size and the model learning rate, initializing network internal parameters, and inputting a training set into the LSTM model for training to obtain an initial evaluation model.
The training method of the red wine quality evaluation model comprises the following steps:
inputting the test set into an initial evaluation model for processing and analysis to obtain an analysis result; and comparing the analysis result with the index data to obtain a comparison result, and debugging according to the comparison result to obtain a red wine quality evaluation model.
And S4, based on a red wine quality evaluation model, measuring values of volatile acid, citric acid, pH value and alcoholic strength by adopting a national standard method, inputting the values into a system for operation, outputting an operation result, carrying out robustness comparison on the operation result and training set information, and outputting an evaluation value if the prediction evaluation index of the model corresponds to the evaluation index of the training data set and does not fluctuate violently.
Example two
In the second embodiment, as shown in fig. 3, the red wine quality prediction system based on the long-short term memory neural network includes: the device comprises a data acquisition module, a preprocessing module, a training module and an evaluation module.
The data acquisition module is connected with the preprocessing module and is used for acquiring red wine samples and analyzing various indexes of the red wine samples to obtain index data; the index data includes: volatile acid, citric acid, pH and alcohol content.
The preprocessing module is also connected with the training module and is used for preprocessing the index data to obtain preprocessed data and dividing the preprocessed data into a training set and a test set according to a preset proportion; the pretreatment method comprises the following steps: correcting abnormal values in the index data by adopting an average value substitution method to obtain corrected data, wherein the abnormal values are conditions of missing values of the data caused by experimental errors in the data collection process, such as problems of volatile acid, citric acid, pH value and alcohol degree index measurement errors, and the like; the pre-processed data is divided into a training set and a test set, wherein the proportion of the training set to the test set is 8:2.
Wherein, the normalization processing process comprises the following steps: after volatile acid, citric acid, pH value and alcohol content data are collected, normalization of the data is carried out by moving the position of a decimal point, and the data are mapped into the range of 0-1.
The training module is also connected with the evaluation module, and is used for carrying out LSTM model training based on the training set to obtain an initial evaluation model, and then carrying out robustness verification and debugging based on the test set to obtain a red wine quality evaluation model; setting the training iteration times of the LSTM model, the number of LSTM layers, the optimizer, the input batch size and the model learning rate, initializing network internal parameters, and inputting a training set into the LSTM model for training to obtain an initial evaluation model; inputting the test set into an initial evaluation model for processing and analysis to obtain an analysis result; and comparing the analysis result with the index data to obtain a comparison result, and debugging according to the comparison result to obtain a red wine quality evaluation model.
Based on a red wine quality evaluation model, the numerical values of volatile acid, citric acid, pH value and alcoholic strength are measured by adopting a national standard method, the numerical values are input into a system for operation and output operation results, the robustness of the operation results is compared with the training set information, and if the prediction evaluation index of the model corresponds to the evaluation index of the training data set at the moment and does not fluctuate violently, an evaluation value is output.
The above-described embodiments are merely illustrative of the preferred embodiments of the present application, and do not limit the scope of the present application, and various modifications and improvements made to the technical solutions of the present application by those skilled in the art without departing from the design spirit of the present application should fall within the protection scope defined by the claims of the present application.
Claims (8)
1. The red wine quality evaluation method based on the long-term and short-term memory neural network is characterized by comprising the following steps of:
s1, collecting a red wine sample, and analyzing each index of the red wine sample to obtain index data;
s2, preprocessing the index data to obtain preprocessed data, and dividing the preprocessed data into a training set and a test set according to a preset proportion;
s3, carrying out LSTM model training based on the training set to obtain an initial evaluation model, and carrying out robustness verification and debugging based on the test set to obtain a red wine quality evaluation model;
and S4, carrying out red wine quality evaluation based on the red wine quality evaluation model to obtain a red wine quality grading evaluation result.
2. A red wine quality evaluation method based on long-short term memory neural network as claimed in claim 1, wherein said index data comprises: volatile acid, citric acid, pH and alcohol content.
3. A red wine quality evaluation method based on a long-short term memory neural network as claimed in claim 1, wherein the preprocessing method comprises:
correcting abnormal values in the index data by adopting an average value substitution method to obtain corrected data; and carrying out normalization processing on the corrected data by a decimal scaling normalization method to obtain preprocessed data.
4. A method as claimed in claim 1, wherein the predetermined ratio of the training set to the testing set is 8:2.
5. A red wine quality evaluation method based on a long-short term memory neural network as claimed in claim 1, wherein the training method of the initial evaluation model comprises the following steps:
and setting the training iteration times, LSTM layer number, optimizer, input batch size and model learning rate of the LSTM model, initializing network internal parameters, and inputting the training set into the LSTM model for training to obtain the initial evaluation model.
6. A red wine quality evaluation method based on a long-short term memory neural network as claimed in claim 5, wherein the training method of the red wine quality evaluation model comprises the following steps:
inputting the test set into the initial evaluation model for processing and analysis to obtain an analysis result;
and comparing the analysis result with the index data to obtain a comparison result, and debugging according to the comparison result to obtain the red wine quality evaluation model.
7. A red wine quality evaluation method based on a long-short term memory neural network as claimed in claim 1, wherein the red wine quality evaluation method comprises the following steps:
and inputting various index data of the red wine to be evaluated based on the red wine quality evaluation model to obtain a red wine quality evaluation result.
8. Red wine quality evaluation system based on long-term and short-term memory neural network, characterized by including: the device comprises a data acquisition module, a preprocessing module, a training module and an evaluation module;
the data acquisition module is connected with the preprocessing module and is used for acquiring red wine samples and analyzing various indexes of the red wine samples to obtain index data;
the preprocessing module is further connected with the training module and used for preprocessing the index data to obtain preprocessed data and dividing the preprocessed data into a training set and a test set according to a preset proportion;
the training module is also connected with the evaluation module, and is used for carrying out LSTM model training based on the training set to obtain an initial evaluation model, and then carrying out robustness verification and debugging based on the test set to obtain a red wine quality evaluation model;
the evaluation module is used for carrying out red wine quality evaluation based on the red wine quality evaluation model to obtain a red wine quality grading evaluation result.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210998982.2A CN115372569A (en) | 2022-08-19 | 2022-08-19 | Red wine quality evaluation method and system based on long-term and short-term memory neural network |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202210998982.2A CN115372569A (en) | 2022-08-19 | 2022-08-19 | Red wine quality evaluation method and system based on long-term and short-term memory neural network |
Publications (1)
Publication Number | Publication Date |
---|---|
CN115372569A true CN115372569A (en) | 2022-11-22 |
Family
ID=84066706
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202210998982.2A Pending CN115372569A (en) | 2022-08-19 | 2022-08-19 | Red wine quality evaluation method and system based on long-term and short-term memory neural network |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN115372569A (en) |
Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008164A (en) * | 2014-05-29 | 2014-08-27 | 华东师范大学 | Generalized regression neural network based short-term diarrhea multi-step prediction method |
CN110009053A (en) * | 2019-04-12 | 2019-07-12 | 浙江树人学院(浙江树人大学) | A kind of comprehensive classification judgment method of the yellow rice wine based on BP deep neural network |
CN112101789A (en) * | 2020-09-16 | 2020-12-18 | 清华大学合肥公共安全研究院 | Water pollution alarm grade identification method based on artificial intelligence |
CN112990567A (en) * | 2021-03-10 | 2021-06-18 | 中国矿业大学(北京) | Method, device, terminal and storage medium for establishing coal bed gas content prediction model |
CN113011796A (en) * | 2021-05-06 | 2021-06-22 | 北京工商大学 | Edible oil safety early warning method based on hierarchical analysis-neural network |
CN114357852A (en) * | 2021-11-12 | 2022-04-15 | 中法渤海地质服务有限公司 | Layered water injection optimization method based on long-short term memory neural network and particle swarm optimization algorithm |
CN114819719A (en) * | 2022-05-19 | 2022-07-29 | 中国石油大学(华东) | White spirit base liquor grading method and system based on artificial intelligence |
CN114912343A (en) * | 2022-03-30 | 2022-08-16 | 南通大学 | LSTM neural network-based air quality secondary prediction model construction method |
-
2022
- 2022-08-19 CN CN202210998982.2A patent/CN115372569A/en active Pending
Patent Citations (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104008164A (en) * | 2014-05-29 | 2014-08-27 | 华东师范大学 | Generalized regression neural network based short-term diarrhea multi-step prediction method |
CN110009053A (en) * | 2019-04-12 | 2019-07-12 | 浙江树人学院(浙江树人大学) | A kind of comprehensive classification judgment method of the yellow rice wine based on BP deep neural network |
CN112101789A (en) * | 2020-09-16 | 2020-12-18 | 清华大学合肥公共安全研究院 | Water pollution alarm grade identification method based on artificial intelligence |
CN112990567A (en) * | 2021-03-10 | 2021-06-18 | 中国矿业大学(北京) | Method, device, terminal and storage medium for establishing coal bed gas content prediction model |
CN113011796A (en) * | 2021-05-06 | 2021-06-22 | 北京工商大学 | Edible oil safety early warning method based on hierarchical analysis-neural network |
CN114357852A (en) * | 2021-11-12 | 2022-04-15 | 中法渤海地质服务有限公司 | Layered water injection optimization method based on long-short term memory neural network and particle swarm optimization algorithm |
CN114912343A (en) * | 2022-03-30 | 2022-08-16 | 南通大学 | LSTM neural network-based air quality secondary prediction model construction method |
CN114819719A (en) * | 2022-05-19 | 2022-07-29 | 中国石油大学(华东) | White spirit base liquor grading method and system based on artificial intelligence |
Non-Patent Citations (2)
Title |
---|
刘攀: "基于RBF和朴素贝叶斯的红葡萄酒质量等级分类", 《电子技术与软件工程》, no. 4, pages 144 - 145 * |
陈宇 等: "《人工智能在教育治理中的应用与发展》", 31 December 2021, 华中科技大学出版社, pages: 108 - 110 * |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108875913B (en) | Tricholoma matsutake rapid nondestructive testing system and method based on convolutional neural network | |
CN101692053B (en) | Multi-sensing information fusion based instrumental intelligent evaluation method for quality of famous tea | |
Brillante et al. | Investigating the use of gradient boosting machine, random forest and their ensemble to predict skin flavonoid content from berry physical–mechanical characteristics in wine grapes | |
CN106093321B (en) | A kind of market for farm products monitoring system and method | |
CN100575950C (en) | A kind of predicting method for fruit maturity | |
CN102788752A (en) | Non-destructive detection device and method of internal information of crops based on spectrum technology | |
CN111340132A (en) | Machine olfaction mode identification method based on DA-SVM | |
CN102937575A (en) | Watermelon sugar degree rapid modeling method based on secondary spectrum recombination | |
CN113008984A (en) | Voiceprint detection fruit maturity analysis instrument | |
CN113409072A (en) | Empirical mode decomposition and distributed GRU neural network and price prediction method | |
Wang et al. | Development of near‐infrared online grading device for long jujube | |
CN109145685A (en) | Fruits and vegetables EO-1 hyperion quality detecting method based on integrated study | |
Bejjani et al. | A sharper characterization of the geographical origin of Lebanese wines by a new interpretation of the hydrogen isotope ratios of ethanol | |
CN115372569A (en) | Red wine quality evaluation method and system based on long-term and short-term memory neural network | |
Kaufmann | Multivariate statistics as a classification tool in the food laboratory | |
Ivanovski et al. | Fruit firmness prediction using multiple linear regression | |
CN110823966A (en) | Grape wine SO based on electronic nose2Method for rapidly measuring concentration | |
CN116183843A (en) | Tomato fruit taste evaluation method | |
CN108507972B (en) | Near infrared spectrum trans-year apple brix prediction method based on distance measurement and semi-supervised learning | |
Yu et al. | Construction method of quantitative evaluation model for the maturity of Korla fragrant pear | |
Anticuando et al. | Electronic Nose and Deep Learning Approach in Identifying Ripe Lycopersicum esculentum L. TomatoFruit | |
CN113935413A (en) | Distribution network wave recording file waveform identification method based on convolutional neural network | |
Gehlken et al. | Near-infrared spectroscopy in process control and quality management of fruits and wine | |
Eunicia et al. | Modeling red wine quality based on physicochemical tests: a data mining approach | |
Stevan Jr et al. | Discrimination analysis of wines made from four species of blueberry through their olfactory signatures using an E-nose |
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 |