CN113744075A - Agricultural product nutrition quality grade classification system based on artificial intelligence - Google Patents
Agricultural product nutrition quality grade classification system based on artificial intelligence Download PDFInfo
- Publication number
- CN113744075A CN113744075A CN202111049289.2A CN202111049289A CN113744075A CN 113744075 A CN113744075 A CN 113744075A CN 202111049289 A CN202111049289 A CN 202111049289A CN 113744075 A CN113744075 A CN 113744075A
- Authority
- CN
- China
- Prior art keywords
- agricultural product
- data
- quality
- artificial intelligence
- agricultural
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Mining
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G16—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR SPECIFIC APPLICATION FIELDS
- G16C—COMPUTATIONAL CHEMISTRY; CHEMOINFORMATICS; COMPUTATIONAL MATERIALS SCIENCE
- G16C20/00—Chemoinformatics, i.e. ICT specially adapted for the handling of physicochemical or structural data of chemical particles, elements, compounds or mixtures
- G16C20/70—Machine learning, data mining or chemometrics
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Theoretical Computer Science (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Medical Informatics (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Computing Systems (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Tourism & Hospitality (AREA)
- Entrepreneurship & Innovation (AREA)
- Data Mining & Analysis (AREA)
- Marketing (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Artificial Intelligence (AREA)
- Chemical & Material Sciences (AREA)
- Mining & Mineral Resources (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Agronomy & Crop Science (AREA)
- Primary Health Care (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Crystallography & Structural Chemistry (AREA)
- Databases & Information Systems (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention provides an agricultural product nutrition quality grading system based on artificial intelligence, and relates to the technical field of artificial intelligence. The method comprises the following steps: s1, detecting the agricultural products and inputting the data of the agricultural product detection; s2, carrying out data processing on the data detected by the agricultural products; the data processing comprises a multispectral instrument data processing system and an omics data analysis system; s3, modeling the agricultural product nutrition quality basic database; s4, a chemometrics and machine learning algorithm library for agricultural product grade division; and S5, constructing an agricultural product grading system. The invention promotes the deep understanding of the substance basis and action rule of the nutritional quality of agricultural products by combining the agricultural product detection with artificial intelligence, is favorable for promoting the grade division of the agricultural products, and promotes the transformation development of the agricultural production in China from the survival type food supply to the health type nutritional quality improvement.
Description
Technical Field
The invention relates to the technical field of artificial intelligence, in particular to an agricultural product nutrition quality grading system based on artificial intelligence.
Background
Currently, Chinese agriculture is accelerating to enter a new stage of meeting nutritional and health requirements, and food processing is transformed from being suitable for people to eat fully and safely and to eat healthily and pleasantly. Since the implementation of agricultural product quality safety law promulgated in 2006, the state strengthens the supervision on the quality safety indexes of agricultural products. By 2019, the limit standards of pesticide residues and the total number of the limit standards of veterinary drug residues are revised in China, the quality safety of agricultural products in China is generally stable, and the qualified rate of the quality safety risk monitoring of the agricultural products in 2020 reaches 97.8%. However, the existing agricultural product quality regulation system pays attention to safety and lacks of supervision on nutritional quality functionality, so that the construction and development of an agricultural product nutritional quality evaluation system are relatively lagged. Due to the fact that basic big data surrounding the nutritional quality of agricultural products in China and a corresponding objective evaluation technology system are lacked, the public lacks of cognition on the nutritional quality, and a wrong consumption concept of safety, namely high quality is formed; meanwhile, the specific execution standard is not clear enough, so that various evaluation confusion, market false publicity and repeated filling are forbidden. Therefore, high-quality varieties and quality resources of the origin of agricultural products are not reasonably developed, investment of production enterprises for quality improvement is short of guarantee, and the acquisition feeling of consumers and the desire for pursuing high-quality food are not fully satisfied.
In view of the above, the agricultural rural area has started the common key technology research for promoting the classification of the grade of the nutrition quality of agricultural products in recent years, scientific connotation research including accurate nutrition and health, discovery of nutrient quality markers and exploration of flavor sensory influence rules are developed by scientifically describing the overall nutrient quality of agricultural products and combining related artificial intelligence analysis technology based on big data, and a series of key application researches such as variety identification, authenticity identification, year identification, nutrition quality evaluation, flavor sensory analysis, origin tracing and the like, and construct the safety, authenticity, nutrition, land-based and traceability of agricultural products, and a layer-by-layer progressive point-surface combined agricultural product grade division innovation technology evaluation system with uniformity, therefore, a detection and evaluation standard architecture with the characteristics of accurate detection, science and intelligent evaluation is realized.
However, most of the existing detection methods such as national standards still remain in the aspect of qualitative and quantitative analysis for a single index or a single detection item, or the external quality such as the appearance, the size and the like of agricultural products is used as a specification classification basis, and a technical method for comprehensively evaluating the internal quality such as the authenticity, the origin, the sense, the nutritional quality and the like of the agricultural products in an all-round and multi-angle manner by combining large data of representative samples with an intelligent analysis instrument is lacked, particularly the application of large data and artificial intelligence technology is still blank. In addition, the application of the existing instrument rapid detection methods such as near infrared spectroscopy and mass spectrum real-time analysis methods in crops mostly focuses on monitoring rough indexes and safety indexes, and the deep exploration and system integration application of the advanced research methods related to the classification of the nutritional quality and the grade of agricultural products such as fingerprint spectrum, flavor organoleptic group, food nutrition substance group, metabonomics, proteomics and the like are lacked. Therefore, the invention provides an agricultural product nutrition quality grading system based on artificial intelligence.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects of the prior art, the invention provides an artificial intelligence-based agricultural product nutrition quality grading system, which realizes one-stop data modeling of complex agricultural product detection data and relates to agricultural product safety evaluation, authenticity evaluation, nutrition quality grading evaluation, consistency evaluation and sensory evaluation by comprehensively utilizing a machine learning algorithm aiming at the characteristics of the agricultural product nutrition quality. The deep knowledge of the substance basis and action rule of the nutritional quality of agricultural products is promoted, the grade division of the agricultural products is promoted, and the transformation development of the agricultural production in China from the survival type food supply to the promotion of the health type nutritional quality is promoted.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme: the utility model provides an agricultural product nutritional quality grade system of dividing based on artificial intelligence which characterized in that: the method comprises the following steps:
s1, detecting the agricultural products and inputting the data of the agricultural product detection;
s2, carrying out data processing on the data detected by the agricultural products; the data processing comprises a multispectral instrument data processing system and an omics data analysis system;
s3, modeling the agricultural product nutrition quality basic database;
s4, a chemometrics and machine learning algorithm library for agricultural product grade division;
and S5, constructing an agricultural product grading system.
Preferably, in S1, the agricultural product is detected by using a multispectral instrument, the multispectral instrument includes a mass spectrometer instrument, a spectroscopic instrument, a chromatographic instrument and a nuclear magnetic resonance spectrum, and the detection data is directly derived from the workstations of the mass spectrometer manufacturer and the nuclear magnetic resonance manufacturer or is completed by means of a data conversion function.
Preferably, the multi-spectral instrument data processing system in S2 includes mass spectrometry data, spectroscopic data, chromatographic data and nuclear magnetic resonance spectroscopy data.
Preferably, the S2 omics data analysis system comprises analysis and record of data of inorganic nutritional quality elements, small molecular nutritional quality elements, large molecular nutritional quality elements, fingerprint, authenticity, traceability analysis and safety risk substances.
Preferably, the database in S3 includes an agricultural product sample library and a database of marker compounds, the agricultural product sample library includes basic information of sample sampling and processing traceability, and records of corresponding raw data and analysis results of the targeted and non-targeted detection spectrum instruments, the database of marker compounds includes compounds for nutritional quality grading, the compounds include quality and flavor sensory markers of various types of agricultural products.
Preferably, the stoichiometries and machine learning algorithm library of agricultural product grade division in S4 includes a similarity discrimination algorithm, a dimensionality reduction analysis algorithm, an unsupervised cluster analysis algorithm, a supervised pattern recognition algorithm and a regression analysis algorithm, and the data modeling of the database of step S3 is completed through step S4.
Preferably, the step S3 and the step S4 constitute an accurate matching system of the big data of the quality of agricultural products, which includes safety evaluation, authenticity evaluation, nutrition quality grading evaluation, consistency evaluation and sensory evaluation.
Preferably, the construction of the agricultural product rating system in step S5 includes the steps of:
A. the model is supervised and trained, and based on chemometrics and a machine learning algorithm, the mode recognition or quantitative regression is realized aiming at the multispectral data of the agricultural products, and markers related to the quality of the agricultural products are recognized and screened;
B. the modeling quality evaluation, the system carries out objective evaluation on the model quality by taking specificity and sensitivity as measuring bases through cross validation, replacement check and validation set validation modes;
C. and predicting a sample to be tested, wherein for an unknown sample to be tested, data is imported into a system, and then data alignment and scaling are automatically performed according to the configuration of the selected corresponding model, and the data is substituted into the model to perform qualitative judgment classification and quantitative regression prediction different types of calculation, so that a predicted value output by the model is obtained and is used as a judgment calculation result of the sample.
The invention provides an artificial intelligence-based agricultural product nutrition quality grading system, which has the following beneficial effects:
(1) according to the invention, by constructing a basic database and a quality marker compound library of the agricultural product nutrition quality and a special algorithm library for chemometrics and machine learning for agricultural product grade division, the complex agricultural product samples are effectively managed and data analysis and mining are carried out in a big data mode, so that workers can conveniently manage various large and complex agricultural product detection samples.
(2) The invention realizes the automation and standardization of agricultural product nutrition quality data analysis and modeling process, realizes scientific detection record and grade division evaluation of agricultural product nutrition quality through the designed methods of data pretreatment, model supervised training, modeling quality evaluation and to-be-detected sample prediction, and greatly improves the existing basis.
(3) According to the invention, through a machine learning algorithm based on mass spectrum data, chromatographic data and nuclear magnetic resonance spectrum data, the origin tracing analysis based on the internal quality of the agricultural products is established, the existing tracing technology of a block chain and an Internet of things 'one object and one code' can be replaced, and the method is applied to detection of relevant authenticity, land characteristics and geographic markers of the agricultural products, so that the detection and tracing cost is effectively reduced, and the tampering of the origin of the products is effectively prevented.
(4) The invention realizes one-stop data modeling of complex agricultural product detection data and relates to agricultural product safety evaluation, authenticity evaluation, nutrition quality grading evaluation, consistency evaluation and sensory evaluation by comprehensively utilizing a machine learning algorithm aiming at the characteristics of the nutrition quality of the agricultural products, can realize complete grading model development and application including sample processing, quality marker discovery, model training, model maintenance, sample prediction and the like by an automatic grading prediction model development system based on detection data of various spectrums, mass spectrums, chromatograms and the like, and greatly improves the combination level of the current agricultural product detection and artificial intelligence. The deep knowledge of the substance basis and action rule of the nutritional quality of agricultural products is promoted, the grade division of the agricultural products is promoted, and the transformation development of the agricultural production in China from the survival type food supply to the promotion of the health type nutritional quality is promoted.
Drawings
FIG. 1 is a flow chart of the present invention;
FIG. 2 is a diagram of a corresponding analytical technique for different substances in accordance with the present invention;
FIG. 3 is a flow chart of the grade division and evaluation of the nutritional quality of agricultural products according to the present invention;
FIG. 4 is a flow chart of the construction of the agricultural product nutritional quality grading system of the present invention.
Detailed Description
The agricultural product nutrition quality grading system based on artificial intelligence provided by the embodiment of the invention comprises the following steps:
s1, detecting the agricultural products and inputting the data of the agricultural product detection;
s2, carrying out data processing on the data detected by the agricultural products; the data processing comprises a multispectral instrument data processing system and an omics data analysis system;
s3, modeling the agricultural product nutrition quality basic database;
s4, a chemometrics and machine learning algorithm library for agricultural product grade division;
and S5, constructing an agricultural product grading system.
In this embodiment: in the step S1, a multispectral instrument is used for detecting the agricultural product, the multispectral instrument includes a mass spectrometer instrument, a spectroscopy instrument, a chromatography instrument and a nuclear magnetic resonance spectrum, and the detection data can be directly derived from the workstations of a mass spectrometer manufacturer and a nuclear magnetic resonance manufacturer or completed by means of a data conversion function.
In this embodiment: as shown in FIG. 2, the data processing system of the multi-spectral instrument in S2 includes various types of spectra (including but not limited to infrared spectrum, near infrared spectrum, Raman spectrum, three-dimensional fluorescence spectrum, etc.), mass spectra (including but not limited to MALDI-MS, DESI-MS, ICP-MS, IR-MS stable isotope ratio, DART-MS, MSI ion mobility spectrum, etc.), chromatograms (including but not limited to liquid chromatogram, gas chromatogram, etc.), and nuclear magnetic resonance spectra (including but not limited to hydrogen spectrum and carbon spectrum, etc.), etc., and provides corresponding processing functions, including qualitative and quantitative processing functions, such as spectrum multivariate correction, chromatographic peak integration and retention time alignment, and two-stage mass spectrum fragmentation matching, etc.
In this embodiment: as shown in fig. 2, the S2 omics data analysis system includes analysis and record of data of inorganic nutritional quality elements, small molecular nutritional quality elements, large molecular nutritional quality elements, fingerprint, authenticity, traceability analysis and safety risk substances.
In this embodiment: as shown in fig. 3, the database in S3 includes an agricultural product sample library and a database of marker compounds, the agricultural product sample library includes basic information of sample sampling and processing tracing, and records of raw data and analysis results of corresponding targeted and non-targeted detection spectrum instruments, the database of marker compounds includes compounds for nutritional quality grading, the compounds include various agricultural product qualities and flavor sensory markers, the latter mainly stores known compounds or unknown and stable compounds which can be labeled and have reference values for research and model establishment of nutritional quality grading mechanism, and the known compounds and the flavor sensory markers include various agricultural product qualities and flavor sensory markers. The database is designed to effectively manage huge and complex agricultural product detection samples and multi-spectral data in a big data mode and conduct subsequent data mining and modeling, so that the requirements of deeply conducting agricultural product grade division research and prediction model development are met. The marking compound database and the atlas database realize seamless association, and automatic compound labeling can be carried out. The database realizes one-stop analysis and data modeling through seamless data exchange with a model analysis and management system, and meets the urgent requirements on agricultural product nutrition quality sample management and data modeling in aspects of multi-spectrum analysis, agricultural product quality marker group design concept, system database architecture and the like.
In this embodiment: the chemometrics and machine learning algorithm library for agricultural product grade division in the S4 has strong specialization of agricultural product nutrition quality detection data, complex data processing, qualitative and quantitative analysis processes, and needs to introduce various chemometrics and machine learning algorithms to cooperatively complete data modeling, so that a machine learning algorithm library special for instrument data analysis is designed and developed, thereby realizing standardization, good applicability and reusability of a model algorithm, the algorithm library provides various algorithms which cover chemometrics and artificial neural network technologies and are highly optimized according to analysis characteristics of instrument analysis data, and the algorithms comprise a similarity discrimination algorithm (such as an included angle cosine algorithm), a supervised pattern recognition algorithm (such as a BP neural network, a support vector machine, a random forest, a partial discrimination algorithm and the like), a dimension reduction analysis algorithm (such as principal component analysis and the like), and a least square algorithm, Unsupervised clustering analysis algorithms (such as clustering heatmaps, k-means clustering and the like), quantitative regression analysis algorithms (such as partial least squares regression, decision tree regression, support vector machine regression) and the like, thereby cooperatively realizing automation and standardization of the modeling process, obtaining high-quality and high-precision modeling prediction results, and completing data modeling on the database of the step S3 through the step S4.
In this embodiment: an accurate matching system of the agricultural product quality big data is formed through the steps S3 and S4, and comprises safety evaluation, authenticity evaluation, nutrition quality grading evaluation, consistency evaluation and sensory evaluation.
In this embodiment: as shown in fig. 4, the construction of the agricultural product rating system in the step S5 includes the steps of:
A. the method comprises the following steps of carrying out supervised training on a model, realizing supervised pattern recognition or quantitative regression aiming at multi-spectral data of agricultural products and recognizing and screening markers related to the quality of the agricultural products based on chemometrics and a machine learning algorithm, specifically, inputting the multi-spectral data of the sample as independent variables of a training set and grading the grade of the sample as dependent variables, and carrying out model training in the model through self-defining steps of data alignment, labeling, data preprocessing and the like;
B. and (3) evaluating the modeling quality, wherein the system objectively evaluates the quality of the model by taking the specificity and the sensitivity as a measuring basis through cross-check verification, replacement verification and verification set verification, namely, inspects the generalization degree of the model and supports the optimization and adjustment aiming at a specific algorithm. More algorithms can be further flexibly expanded in a mode of a model interface according to needs;
C. and predicting a sample to be tested, wherein for an unknown sample to be tested, data is imported into a system, and then data alignment and scaling are automatically performed according to the configuration of the selected corresponding model, and the data is substituted into the model to perform qualitative judgment classification and quantitative regression prediction different types of calculation, so that a predicted value output by the model is obtained and is used as a judgment calculation result of the sample.
The foregoing shows and describes the general principles, essential features, and advantages of the invention. It will be understood by those skilled in the art that the present invention is not limited to the embodiments described above, and the preferred embodiments of the present invention are described in the above embodiments and the description, and are not intended to limit the present invention. The scope of the invention is defined by the appended claims and equivalents thereof.
Claims (8)
1. The utility model provides an agricultural product nutritional quality grade system of dividing based on artificial intelligence which characterized in that: the method comprises the following steps:
s1, detecting the agricultural products and inputting the data of the agricultural product detection;
s2, carrying out data processing on the data detected by the agricultural products; the data processing comprises a multispectral instrument data processing system and an omics data analysis system;
s3, modeling the agricultural product nutrition quality basic database;
s4, a chemometrics and machine learning algorithm library for agricultural product grade division;
and S5, constructing an agricultural product grading system.
2. The artificial intelligence based agricultural product nutritional quality grading system of claim 1, wherein: in the step S1, a multispectral instrument is used for detecting the agricultural product, the multispectral instrument includes a mass spectrometer instrument, a spectroscopy instrument, a chromatography instrument and a nuclear magnetic resonance spectrum, and the detection data can be directly derived from the workstations of a mass spectrometer manufacturer and a nuclear magnetic resonance manufacturer or completed by means of a data conversion function.
3. The artificial intelligence based agricultural product nutritional quality grading system of claim 1, wherein: the multi-spectral instrument data processing system in the S2 comprises mass spectrum data, chromatographic data and nuclear magnetic resonance spectrum data.
4. The artificial intelligence based agricultural product nutritional quality grading system of claim 1, wherein: the S2 omics data analysis system comprises the steps of analyzing and recording data of inorganic nutritional quality elements, micromolecular nutritional quality elements, macromolecular nutritional quality elements, fingerprint spectrums, authenticity, traceability analysis and safety risk substances.
5. The method for making an artificial intelligence based agricultural product nutritional quality grading system according to claim 1, wherein the method comprises the following steps: the database in the S3 comprises an agricultural product sample database and a marker compound database, wherein the agricultural product sample database comprises basic information of sample sampling and processing tracing, and records of corresponding original data and analysis results of a targeted detection spectrum instrument and a non-targeted detection spectrum instrument, the marker compound database comprises compounds for grading nutritional quality, and the compounds comprise quality and flavor sensory markers of various agricultural products.
6. The artificial intelligence based agricultural product nutritional quality grading system of claim 1, wherein: the chemometrics and machine learning algorithm library for agricultural product grade division in the step S4 includes a similarity discrimination algorithm, a dimension reduction analysis algorithm, an unsupervised cluster analysis algorithm, a supervised pattern recognition algorithm and a regression analysis algorithm, and data modeling is completed on the database of the step S3 through the step S4.
7. The artificial intelligence based agricultural product nutritional quality grading system of claim 1, wherein: an accurate matching system of the agricultural product quality big data is formed through the steps S3 and S4, and comprises safety evaluation, authenticity evaluation, nutrition quality grading evaluation, consistency evaluation and sensory evaluation.
8. The artificial intelligence based agricultural product nutritional quality grading system of claim 1, wherein: the construction of the agricultural product rating system in the step S5 includes the steps of:
A. the model is supervised and trained, and based on chemometrics and a machine learning algorithm, the mode recognition or quantitative regression is realized aiming at the multispectral data of the agricultural products, and markers related to the quality of the agricultural products are recognized and screened;
B. the modeling quality evaluation, the system carries out objective evaluation on the model quality by taking specificity and sensitivity as measuring bases through cross-check verification, replacement verification and verification set verification;
C. and predicting a sample to be tested, wherein for an unknown sample to be tested, data is imported into a system, and then data alignment and scaling are automatically performed according to the configuration of the selected corresponding model, and the data is substituted into the model to perform qualitative judgment classification and quantitative regression prediction different types of calculation, so that a predicted value output by the model is obtained and is used as a judgment calculation result of the sample.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111049289.2A CN113744075A (en) | 2021-09-08 | 2021-09-08 | Agricultural product nutrition quality grade classification system based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111049289.2A CN113744075A (en) | 2021-09-08 | 2021-09-08 | Agricultural product nutrition quality grade classification system based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113744075A true CN113744075A (en) | 2021-12-03 |
Family
ID=78736981
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111049289.2A Pending CN113744075A (en) | 2021-09-08 | 2021-09-08 | Agricultural product nutrition quality grade classification system based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113744075A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116224949A (en) * | 2023-05-10 | 2023-06-06 | 山东一方制药有限公司 | Traditional Chinese medicine formula granule production process data processing system based on artificial intelligence |
-
2021
- 2021-09-08 CN CN202111049289.2A patent/CN113744075A/en active Pending
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN116224949A (en) * | 2023-05-10 | 2023-06-06 | 山东一方制药有限公司 | Traditional Chinese medicine formula granule production process data processing system based on artificial intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Cozzolino et al. | Can spectroscopy geographically classify Sauvignon Blanc wines from Australia and New Zealand? | |
| CN108181263B (en) | Tobacco leaf position feature extraction and discrimination method based on near infrared spectrum | |
| Ren et al. | Intelligent assessment of tea quality employing visible-near infrared spectra combined with a hybrid variable selection strategy | |
| Schlesier et al. | Characterisation and determination of the geographical origin of wines. Part I: overview | |
| Li et al. | Non-destructive evaluation of pork freshness using a portable electronic nose (E-nose) based on a colorimetric sensor array | |
| CN108875913A (en) | A kind of matsutake Fast nondestructive evaluation system and method based on convolutional neural networks | |
| CN101915744A (en) | Near infrared spectrum nondestructive testing method and device for material component content | |
| CN109254107A (en) | The general tea Fast Classification discrimination method of mandarin orange | |
| Dębska et al. | Decision trees in selection of featured determined food quality | |
| CN109668859A (en) | The near infrared spectrum recognition methods in the Chinese prickly ash place of production and kind based on SVM algorithm | |
| Kalogiouri et al. | Liquid chromatographic methods coupled to chemometrics: A short review to present the key workflow for the investigation of wine phenolic composition as it is affected by environmental factors | |
| Yang et al. | Laser-induced breakdown spectroscopy assisted chemometric methods for rice geographic origin classification | |
| CN115905881B (en) | Yellow pearl classification method and device, electronic equipment and storage medium | |
| Large et al. | Detecting forged alcohol non-invasively through vibrational spectroscopy and machine learning | |
| CN109187443A (en) | Water body bacterial micro-organism based on multi-wavelength transmitted spectrum accurately identifies method | |
| CN109784390B (en) | Artificial intelligent smell dynamic response atlas gas detection and identification method | |
| CN113744075A (en) | Agricultural product nutrition quality grade classification system based on artificial intelligence | |
| CN113049499A (en) | Indirect remote sensing inversion method for water total nitrogen concentration, storage medium and terminal equipment | |
| Strojnik et al. | Geographical identification of strawberries based on stable isotope ratio and multi-elemental analysis coupled with multivariate statistical analysis: A Slovenian case study | |
| Jin et al. | Rapid identification of the geographic origin of Taiping Houkui green tea using near‐infrared spectroscopy combined with a variable selection method | |
| CN108663334B (en) | Method for searching spectral characteristic wavelength of soil nutrient based on multi-classifier fusion | |
| Ranaweera et al. | Absorbance-transmission and fluorescence excitation-emission matrix (A-TEEM) with multi-block data analysis and machine learning for accurate intraregional classification of Barossa Shiraz wine | |
| CN116858822A (en) | Quantitative analysis method for sulfadiazine in water based on machine learning and Raman spectrum | |
| CN111426657B (en) | Identification comparison method of three-dimensional fluorescence spectrogram of soluble organic matter | |
| CN202794093U (en) | Device for fast detecting quality of baked food based on bionic olfaction |
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 |