CN117054354B - Portable seed maturity spectrum detection system and device - Google Patents
Portable seed maturity spectrum detection system and device Download PDFInfo
- Publication number
- CN117054354B CN117054354B CN202311315405.XA CN202311315405A CN117054354B CN 117054354 B CN117054354 B CN 117054354B CN 202311315405 A CN202311315405 A CN 202311315405A CN 117054354 B CN117054354 B CN 117054354B
- Authority
- CN
- China
- Prior art keywords
- seed
- data
- module
- maturity
- sub
- 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.)
- Active
Links
- 238000001228 spectrum Methods 0.000 title claims abstract description 111
- 238000001514 detection method Methods 0.000 title claims abstract description 29
- 238000005516 engineering process Methods 0.000 claims abstract description 45
- 230000010354 integration Effects 0.000 claims abstract description 34
- 238000013135 deep learning Methods 0.000 claims abstract description 13
- 238000010801 machine learning Methods 0.000 claims abstract description 8
- 238000003306 harvesting Methods 0.000 claims abstract description 7
- 238000004458 analytical method Methods 0.000 claims description 48
- 230000003595 spectral effect Effects 0.000 claims description 41
- 238000004422 calculation algorithm Methods 0.000 claims description 37
- 238000012545 processing Methods 0.000 claims description 37
- 238000012549 training Methods 0.000 claims description 35
- 238000005259 measurement Methods 0.000 claims description 20
- 239000013307 optical fiber Substances 0.000 claims description 18
- 238000003066 decision tree Methods 0.000 claims description 17
- 230000001629 suppression Effects 0.000 claims description 17
- 238000000034 method Methods 0.000 claims description 16
- 238000012216 screening Methods 0.000 claims description 14
- 238000013527 convolutional neural network Methods 0.000 claims description 12
- 238000000513 principal component analysis Methods 0.000 claims description 12
- 238000012706 support-vector machine Methods 0.000 claims description 12
- 238000000605 extraction Methods 0.000 claims description 11
- 238000013500 data storage Methods 0.000 claims description 9
- 230000005484 gravity Effects 0.000 claims description 9
- 238000001739 density measurement Methods 0.000 claims description 8
- 238000007781 pre-processing Methods 0.000 claims description 8
- 238000012163 sequencing technique Methods 0.000 claims description 8
- 238000004590 computer program Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000010191 image analysis Methods 0.000 claims description 6
- 230000000877 morphologic effect Effects 0.000 claims description 6
- 238000010606 normalization Methods 0.000 claims description 6
- 238000007637 random forest analysis Methods 0.000 claims description 6
- 238000013477 bayesian statistics method Methods 0.000 claims description 5
- 238000007621 cluster analysis Methods 0.000 claims description 5
- 238000012937 correction Methods 0.000 claims description 5
- 238000002189 fluorescence spectrum Methods 0.000 claims description 5
- 230000004927 fusion Effects 0.000 claims description 5
- 238000007477 logistic regression Methods 0.000 claims description 5
- 238000000411 transmission spectrum Methods 0.000 claims description 5
- 238000003708 edge detection Methods 0.000 claims description 4
- 238000001914 filtration Methods 0.000 claims description 4
- 238000007689 inspection Methods 0.000 claims description 4
- 230000008569 process Effects 0.000 claims description 4
- 238000010219 correlation analysis Methods 0.000 claims description 3
- 230000008901 benefit Effects 0.000 abstract description 5
- 230000003287 optical effect Effects 0.000 abstract description 5
- 239000000284 extract Substances 0.000 description 4
- 238000007726 management method Methods 0.000 description 4
- 238000001303 quality assessment method Methods 0.000 description 4
- 238000002759 z-score normalization Methods 0.000 description 4
- 239000013589 supplement Substances 0.000 description 3
- 238000012271 agricultural production Methods 0.000 description 2
- 238000007405 data analysis Methods 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000000704 physical effect Effects 0.000 description 2
- 239000000047 product Substances 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 238000010521 absorption reaction Methods 0.000 description 1
- 238000003339 best practice Methods 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000009395 breeding Methods 0.000 description 1
- 230000001488 breeding effect Effects 0.000 description 1
- 238000000546 chi-square test Methods 0.000 description 1
- 230000007797 corrosion Effects 0.000 description 1
- 238000005260 corrosion Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000001066 destructive effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000018109 developmental process Effects 0.000 description 1
- 238000009826 distribution Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000004720 fertilization Effects 0.000 description 1
- 230000035784 germination Effects 0.000 description 1
- 238000005286 illumination Methods 0.000 description 1
- 230000001678 irradiating effect Effects 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 238000003973 irrigation Methods 0.000 description 1
- 230000002262 irrigation Effects 0.000 description 1
- 244000144972 livestock Species 0.000 description 1
- 210000001161 mammalian embryo Anatomy 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 238000009304 pastoral farming Methods 0.000 description 1
- 238000011176 pooling Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 238000009374 poultry farming Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000003908 quality control method Methods 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 238000005096 rolling process Methods 0.000 description 1
- 238000012306 spectroscopic technique Methods 0.000 description 1
- 238000004611 spectroscopical analysis Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01N—INVESTIGATING OR ANALYSING MATERIALS BY DETERMINING THEIR CHEMICAL OR PHYSICAL PROPERTIES
- G01N21/00—Investigating or analysing materials by the use of optical means, i.e. using sub-millimetre waves, infrared, visible or ultraviolet light
- G01N21/17—Systems in which incident light is modified in accordance with the properties of the material investigated
- G01N21/25—Colour; Spectral properties, i.e. comparison of effect of material on the light at two or more different wavelengths or wavelength bands
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/29—Graphical models, e.g. Bayesian networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N5/00—Computing arrangements using knowledge-based models
- G06N5/01—Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
-
- 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
- Y02A—TECHNOLOGIES FOR ADAPTATION TO CLIMATE CHANGE
- Y02A40/00—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production
- Y02A40/10—Adaptation technologies in agriculture, forestry, livestock or agroalimentary production in agriculture
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Computation (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Software Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Computing Systems (AREA)
- Mathematical Physics (AREA)
- Pathology (AREA)
- Medical Informatics (AREA)
- Immunology (AREA)
- General Health & Medical Sciences (AREA)
- Biochemistry (AREA)
- Analytical Chemistry (AREA)
- Chemical & Material Sciences (AREA)
- Health & Medical Sciences (AREA)
- Spectroscopy & Molecular Physics (AREA)
- Computational Linguistics (AREA)
- Investigating Or Analysing Materials By Optical Means (AREA)
Abstract
The invention relates to the technical field of agricultural science, in particular to a portable seed maturity spectrum detection system and device. According to the invention, the optical characteristics of seeds can be more comprehensively captured through the multi-mode spectrum acquisition module, the signal to noise ratio of spectrum data is further improved through the addition of the differential time delay integration technology, a richer seed information data set is constructed through combining the spectrum data and the basic attributes of the seeds, advanced machine learning technologies such as deep learning and the like are applied, so that the accuracy and robustness of prediction are ensured, and specific and practical suggestions such as optimal harvesting time and planting schemes are provided for users through combining an intelligent decision support module of an agricultural expert knowledge base, so that the planting benefit is improved.
Description
Technical Field
The invention relates to the technical field of agricultural science, in particular to a portable seed maturity spectrum detection system and device.
Background
Agricultural science is the scientific field relevant to agricultural production such as research crops, livestock and poultry farming, fishery. It relates to the aspects of planting, breeding, agricultural management, agricultural product processing and the like. Wherein, the seed maturity spectrum detection system is a system for detecting seed maturity. Seed maturity refers to an indicator of the degree of development of the endosperm and embryo within a seed, which is of great importance for the assessment of seed quality and germination capacity. The purpose of the detection system is to evaluate and detect seed maturity by spectroscopic techniques. The spectroscopic technology utilizes the absorption, scattering and transmission characteristics of the substances to analyze the light with different wavelengths so as to acquire the composition information and properties of the substances, aims at nondestructively determining the maturity level of the seeds, and provides accurate decision basis. The system evaluates seed quality in a non-destructive and efficient manner by rapid, accurate spectroscopic analysis.
In seed maturity spectral detection systems, existing systems often rely on a single spectral pattern for detection of seed maturity, which can result in some critical optical information being lost when handling certain seeds, resulting in detection inaccuracies. Furthermore, for the processing and analysis of spectral data, conventional systems mostly employ simple linear methods, whereas non-linear characteristics that may be present in the data are ignored, which may also lead to deviations in the detection results. Furthermore, there are few prior systems in which analysis was performed in combination with the physical properties and spectral data of the seeds, which makes it possible to generate false positives when dealing with certain seeds having similar spectra but different physical properties. Finally, conventional systems often lack intelligent decision support functionality, and after obtaining seed maturity information, the user needs to further analyze himself to determine a next planting strategy, which increases the complexity of the user's operation and the risk of planting.
Disclosure of Invention
The invention aims to solve the defects in the prior art, and provides a portable seed maturity spectrum detection system and device.
In order to achieve the above purpose, the present invention adopts the following technical scheme: the portable seed maturity spectrum detection system consists of a multi-mode spectrum acquisition module, a spectrum data processing module, a seed parameter acquisition module, a multi-source data integration module, a model training and prediction module, a sequencing and classifying module and an intelligent decision support module;
the multi-mode spectrum acquisition module adopts a portable optical fiber sensor to acquire spectrum information of seeds under the multi-mode spectrum comprising a reflection spectrum, a transmission spectrum and a fluorescence spectrum, and removes noise by utilizing a differential time delay integration technology to acquire seed multi-mode spectrum data after noise suppression;
the spectrum data processing module performs feature extraction by using principal component analysis and linear discriminant analysis on the basis of the seed multimode spectrum data after noise suppression to obtain a spectrum data key feature set;
the seed parameter acquisition module acquires seed basic attribute data comprising the size, shape and density of seeds through image analysis and a gravity sensitive element;
The multi-source data integration module combines the spectrum data key feature set and the seed basic attribute data by utilizing a data fusion technology to generate a complete seed information data set;
the model training and predicting module performs model training and prediction based on the complete seed information dataset by using a machine learning algorithm comprising deep learning and a support vector machine to generate a seed maturity predicting result;
the sorting and classifying module performs quality sorting and maturity classification on the seeds according to quality standards by utilizing a decision tree algorithm based on the seed maturity prediction result to generate a seed quality sorting and maturity classification result;
the intelligent decision support module generates an intelligent decision support report including optimal harvesting time and planting scheme through a decision tree and a logistic regression algorithm according to seed quality sorting and maturity classification results and by combining an agricultural expert knowledge base.
As a further scheme of the invention, the multimode spectrum acquisition module comprises a light source sub-module, an optical fiber sensing sub-module and a data acquisition sub-module;
the spectrum data processing module comprises a data preprocessing sub-module, a feature extraction sub-module and a primary analysis sub-module;
The seed parameter acquisition module comprises a shape measurement sub-module, a size measurement sub-module and a density measurement sub-module;
the multi-source data integration module comprises a data processing sub-module, a data integration sub-module and a data storage sub-module;
the model training and predicting module comprises a feature screening sub-module, a model training sub-module and a model predicting sub-module;
the sorting and classifying module comprises a grading sub-module, a quality sorting sub-module and a maturity classifying sub-module;
the intelligent decision support module comprises a decision suggestion generation sub-module, an agricultural knowledge base sub-module and a decision support sub-module.
As a further scheme of the invention, the light source submodule applies a modulation frequency technology and a broadband light source technology to generate continuous wavelength light from ultraviolet to near infrared so as to generate broadband light source irradiation;
the optical fiber sensing submodule accurately captures the multimode spectrum of the seed by utilizing a multichannel optical fiber technology based on broadband light source irradiation to generate original multimode spectrum data;
the data acquisition submodule applies differential time delay integration and wavelet denoising technology based on original multi-mode spectrum data to remove external noise in the spectrum data and generate spectrum data after noise suppression.
As a further scheme of the invention, the data preprocessing sub-module receives the spectral data after noise suppression, performs gaussian filtering processing and baseline correction, and generates preprocessed spectral data;
the characteristic extraction submodule generates a spectral data key characteristic set by adopting principal component analysis and linear discriminant analysis based on the preprocessed spectral data;
and the primary analysis submodule performs Bayesian statistics and cluster analysis by utilizing the spectral data key feature set, provides primary analysis for data, and generates a primary analysis report.
As a further scheme of the invention, the shape measurement submodule utilizes a convolutional neural network to carry out edge detection on the seed image, so as to realize shape measurement and generate seed shape data;
the size measurement submodule is used for measuring the size of the seeds based on the shape data of the seeds by applying a watershed algorithm and morphological analysis to generate seed size data;
the density measurement submodule is used for calculating seed density by analyzing seed size data and combining a gravity sensitive element by adopting a mass-volume method to generate seed density data.
As a further scheme of the invention, the data processing sub-module integrates the primary analysis report, the seed shape data, the seed size data and the seed density data, and adopts the Z-score normalization and normalization technology to process the data so as to generate standardized seed data;
The data integration submodule ensures the continuity of data by using correlation analysis based on standardized seed data and integrates a data set to generate a complete seed information data set;
the data storage sub-module stores the complete seed information data set in a distributed database, ensures high availability and high reliability, and generates a seed information database.
As a further scheme of the invention, the feature screening submodule performs feature screening by utilizing LASSO regularization and chi-square inspection based on the complete seed information data set, eliminates irrelevant or redundant features and generates a simplified seed information feature set;
the model training submodule is based on the simplified seed information feature set, and adopts a deep-learning convolutional neural network and a radial basis function of a support vector machine to carry out model training so as to generate a seed maturity prediction model;
the model prediction submodule carries out prediction operation on the follow-up complete seed information data set by means of a seed maturity prediction model to generate a seed maturity prediction result.
As a further scheme of the invention, the grading sub-module adopts a C4.5 decision tree algorithm to grade different maturity levels of seeds based on the seed maturity prediction result, and generates seed grade grading information;
The quality sorting submodule is used for sorting the seed quality by using a heap sorting algorithm according to the seed grade sorting information to generate a seed quality sorting list;
and the maturity classification submodule classifies the maturity of the seeds by applying a random forest algorithm according to the seed quality ordered list to generate a seed maturity classification result.
As a further scheme of the invention, the decision suggestion generation submodule refers to the seed maturity classification result, and uses a fuzzy logic rule engine to generate a preliminary decision suggestion and generate a preliminary decision suggestion;
the agricultural knowledge base submodule supplements and optimizes the decision based on the preliminary decision suggestion and combines the agricultural knowledge graph technology to generate an optimized decision suggestion;
and the decision support sub-module fuses the optimized decision suggestion with the actual agricultural policy and technical guideline to form an ultimate decision suggestion and generate an intelligent decision support report.
The portable seed maturity spectrum detection device comprises a memory and a processor, wherein a computer program is stored in the memory, and the portable seed maturity spectrum detection system is realized when the processor executes the computer program.
Compared with the prior art, the invention has the advantages and positive effects that:
according to the invention, the optical characteristics of the seeds can be more comprehensively captured through the multi-mode spectrum acquisition module, and the maturity information of the seeds can be more accurately acquired. The addition of the differential time delay integration technique further improves the signal-to-noise ratio of the spectral data. By combining the spectral data with the basic attributes of the seeds, the multi-source data integration module is able to construct a richer seed information dataset. Advanced machine learning techniques such as deep learning are applied, so that the accuracy and the robustness of prediction are ensured. The intelligent decision support module combined with the agricultural expert knowledge base provides specific and practical suggestions for users, such as optimal harvesting time and planting scheme, thereby greatly improving planting benefit.
Drawings
FIG. 1 is a system flow diagram of the present invention;
FIG. 2 is a system block diagram of the present invention;
FIG. 3 is a flow chart of a multi-mode spectrum acquisition module according to the present invention;
FIG. 4 is a flowchart of a spectral data processing module according to the present invention;
FIG. 5 is a flow chart of a seed parameter acquisition module according to the present invention;
FIG. 6 is a flowchart of a multi-source data integration module according to the present invention;
FIG. 7 is a flow chart of a model training and prediction module of the present invention;
FIG. 8 is a flow chart of the sorting and categorizing module of the present invention;
FIG. 9 is a flow chart of the intelligent decision support module of the present invention.
Detailed Description
The present invention will be described in further detail with reference to the drawings and examples, in order to make the objects, technical solutions and advantages of the present invention more apparent. It should be understood that the specific embodiments described herein are for purposes of illustration only and are not intended to limit the scope of the invention.
In the description of the present invention, it should be understood that the terms "length," "width," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," and the like indicate orientations or positional relationships based on the orientation or positional relationships shown in the drawings, merely to facilitate describing the present invention and simplify the description, and do not indicate or imply that the devices or elements referred to must have a specific orientation, be configured and operated in a specific orientation, and therefore should not be construed as limiting the present invention. Furthermore, in the description of the present invention, the meaning of "a plurality" is two or more, unless explicitly defined otherwise.
Embodiment one: referring to fig. 1, the present invention provides a technical solution: the portable seed maturity spectrum detection system consists of a multi-mode spectrum acquisition module, a spectrum data processing module, a seed parameter acquisition module, a multi-source data integration module, a model training and prediction module, a sequencing and classifying module and an intelligent decision support module;
the multi-mode spectrum acquisition module adopts a portable optical fiber sensor to acquire spectrum information of seeds under the multi-mode spectrum comprising a reflection spectrum, a transmission spectrum and a fluorescence spectrum, and removes noise by utilizing a differential time delay integration technology to acquire seed multi-mode spectrum data after noise suppression;
the spectrum data processing module is used for extracting features by using principal component analysis and linear discriminant analysis based on the seed multimode spectrum data after noise suppression to obtain a spectrum data key feature set;
the seed parameter acquisition module acquires seed basic attribute data comprising the size, shape and density of seeds through image analysis and a gravity sensitive element;
the multi-source data integration module utilizes a data fusion technology to combine the spectrum data key feature set and the seed basic attribute data to generate a complete seed information data set;
The model training and predicting module performs model training and prediction based on the complete seed information data set by using a machine learning algorithm comprising deep learning and a support vector machine to generate a seed maturity predicting result;
the sorting and classifying module is used for sorting the quality and classifying the maturity of the seeds according to the quality standard by utilizing a decision tree algorithm based on the seed maturity prediction result to generate a seed quality sorting and maturity classifying result;
the intelligent decision support module generates an intelligent decision support report including optimal harvesting time and planting scheme through decision trees and logistic regression algorithm according to seed quality sorting and maturity classification results and combining with an agricultural expert knowledge base.
Firstly, the multimode spectrum acquisition module acquires multimode spectrum data of seeds by using an optical fiber sensor, and removes noise by a differential time delay integration technology, so that high-quality seed spectrum information is obtained. This helps to accurately understand the spectral characteristics of the seed, providing a reliable basis for subsequent data processing.
The spectrum data processing module extracts a key feature set from the seed multimode spectrum data after noise suppression by using methods such as principal component analysis, linear discriminant analysis and the like. These features may reflect important information such as seed maturity and quality. By the data processing method, the system can accurately analyze the characteristics of the seeds and provide support for subsequent seed maturity prediction and quality assessment.
The seed parameter acquisition module acquires basic attribute data such as the size, the shape, the density and the like of seeds through technologies such as image analysis, gravity sensitive elements and the like. These parameters are critical to assessing seed maturity and quality. By collecting the data of the seed parameters, the system can more comprehensively understand the characteristics of the seeds, and improve the accuracy of the maturity prediction and quality assessment of the seeds.
The multi-source data integration module combines the spectrum data key feature set and the seed basic attribute data by adopting a data fusion technology to generate a complete seed information data set. By integrating data from different sources, the system can describe the characteristics and properties of seeds more comprehensively, and the comprehensive analysis capability of the maturity and quality of the seeds is improved.
The model training and predicting module performs model training and prediction based on the complete seed information data set by using machine learning algorithms such as deep learning and support vector machine, and the like, and generates a maturity predicting result of the seeds. Such predictions enable rapid and accurate assessment of seed maturity levels based on seed characteristics and attributes.
And the sorting and classifying module performs quality sorting and maturity classification on the seeds by utilizing a decision tree algorithm according to the maturity prediction result of the seeds. This helps to targeted treatment and management for different seed quality and maturity levels, improving the effectiveness and yield of planting.
And finally, the intelligent decision support module combines an agricultural expert knowledge base according to the seed quality sorting and maturity classification result, and adopts a decision tree and a logistic regression algorithm to generate an intelligent decision support report. These reports may provide suggestions for optimal harvest time and planting schemes, etc., helping the agricultural practitioner make informed decisions to maximize crop yield and quality.
Referring to fig. 2, the multi-mode spectrum acquisition module includes a light source sub-module, an optical fiber sensing sub-module, and a data acquisition sub-module;
the spectrum data processing module comprises a data preprocessing sub-module, a feature extraction sub-module and a primary analysis sub-module;
the seed parameter acquisition module comprises a shape measurement sub-module, a size measurement sub-module and a density measurement sub-module;
the multi-source data integration module comprises a data processing sub-module, a data integration sub-module and a data storage sub-module;
the model training and predicting module comprises a feature screening sub-module, a model training sub-module and a model predicting sub-module;
the sorting and classifying module comprises a grading sub-module, a quality sorting sub-module and a maturity classifying sub-module;
the intelligent decision support module comprises a decision suggestion generation sub-module, an agricultural knowledge base sub-module and a decision support sub-module.
Multimode spectrum acquisition module: the optical fiber sensing sub-module is used for collecting multi-mode spectrum information such as reflection spectrum, transmission spectrum, fluorescence spectrum and the like of seeds by providing proper illumination conditions through the light source sub-module. The data acquisition sub-module is responsible for transmitting the spectral data to other modules for subsequent processing. Such multi-mode spectral acquisition can provide rich spectral features that help to more accurately assess seed maturity and quality.
And a spectrum data processing module: the data preprocessing sub-module is responsible for performing noise suppression, normalization and other processing on the optical data, and improves the quality and usability of the data. The feature extraction submodule applies methods such as principal component analysis, linear discriminant analysis and the like to extract a key feature set from the spectrum data. The primary analysis submodule carries out primary analysis on the extracted characteristics, and lays a foundation for subsequent seed maturity prediction and quality assessment. By processing the spectrum data and extracting the characteristics, the system can more accurately characterize the seeds, and the detection accuracy is improved.
Seed parameter acquisition module: the shape measurement submodule obtains shape information of the seeds through technologies such as image analysis, the size measurement submodule obtains size information of the seeds, and the density measurement submodule obtains density data of the seeds. These basic attribute data are of great importance for assessing seed maturity and quality. By acquiring the parameter information of the seeds, the system can more comprehensively understand the characteristics of the seeds, and accuracy of maturity prediction and quality assessment is improved.
And the multi-source data integration module is used for: the data processing sub-module is responsible for processing and integrating the spectral data feature set and the seed parameter data. The data integration sub-module combines the data from different sources to generate a complete seed information data set. The data storage sub-module is responsible for storing and managing the integrated data. By integrating the information of multiple data sources, the system can provide more comprehensive and accurate seed information, and a reliable data basis is provided for subsequent model training and decision support.
Model training and prediction module: the feature screening submodule screens the integrated data set and selects features related to seed maturity and quality. The model training submodule trains sample data by utilizing algorithms such as deep learning, a support vector machine and the like, and a model with prediction capability is generated. And the model prediction submodule predicts the seed maturity by using the trained model according to new data input. The model training and prediction based on machine learning can efficiently analyze the maturity of seeds and provide basis for subsequent sorting and classification.
The sorting and classifying module: the grading sub-module is used for grading the seeds into different grades according to a preset quality standard. The quality sequencing submodule sequences the seeds according to the characteristics of the seeds and the maturity prediction result, and determines the quality level of the seeds. The maturity classification submodule classifies the seeds according to corresponding standards. Through the strategy of sequencing and classifying, the system can realize the classification and classification of seed quality, and provides specific guidance for agricultural production.
An intelligent decision support module: the decision suggestion generation submodule combines the results of seed quality sequencing and maturity classification, and an intelligent decision support report is generated through the agricultural knowledge base submodule and the decision support submodule. These reports include recommendations of optimal harvest time and planting scheme, etc., providing basis for agricultural practitioners to make decisions to optimize crop yield and quality.
Referring to fig. 3, the light source sub-module applies a modulation frequency technology and a broadband light source technology to generate continuous wavelength light from ultraviolet to near infrared, so as to generate broadband light source irradiation;
the optical fiber sensing sub-module precisely captures the multimode spectrum of the seed by utilizing a multichannel optical fiber technology based on broadband light source irradiation to generate original multimode spectrum data;
the data acquisition submodule applies differential time delay integration and wavelet denoising technology based on original multi-mode spectrum data to remove external noise in the spectrum data and generate spectrum data after noise suppression.
The application of the modulation frequency technology and the broadband light source technology of the light source sub-module can generate continuous wavelength light from ultraviolet to near infrared, and provide a wide spectrum range for irradiating seeds. The broadband light source irradiation can more comprehensively capture multimode spectrum information of seeds, including reflection spectrum, transmission spectrum, fluorescence spectrum and the like.
The optical fiber sensing submodule can accurately capture the multimode spectrum of the seed based on the irradiation of a broadband light source by utilizing a multichannel optical fiber technology. Through multichannel optical fiber, the system can collect spectrum signals in different wavelength ranges at the same time, so that the comprehensive acquisition of the spectrum characteristics of seeds is realized. The raw multi-mode spectral data so generated provides a reliable basis for subsequent data processing and analysis.
The data acquisition sub-module applies differential time delay integration and wavelet denoising technology to remove external noise in spectrum data on the basis of original multimode spectrum data. The processing technology can effectively reduce the influence of factors such as environment, equipment and the like on spectrum data, and improve the quality and usability of the data. By the spectral data after noise suppression, the system can more accurately perform subsequent data analysis and feature extraction.
Referring to fig. 4, the data preprocessing sub-module receives the spectral data after noise suppression, performs gaussian filtering processing and baseline correction, and generates preprocessed spectral data;
the feature extraction submodule generates a key feature set of the spectrum data by adopting principal component analysis and linear discriminant analysis based on the preprocessed spectrum data;
The primary analysis submodule performs Bayesian statistics and cluster analysis by utilizing the spectral data key feature set, provides primary analysis for data, and generates a primary analysis report.
The data preprocessing sub-module receives the spectral data after noise suppression, performs Gaussian filtering processing and baseline correction, and generates preprocessed spectral data. The Gaussian filter processing can smooth the spectrum curve and remove high-frequency noise, so that the spectrum data has better readability and stability. The baseline correction can eliminate background offset of the spectrum curve, so that subsequent analysis is more accurate and reliable.
The feature extraction submodule extracts a key feature set of the spectrum data by adopting technologies such as Principal Component Analysis (PCA) and Linear Discriminant Analysis (LDA) based on the preprocessed spectrum data. Principal component analysis can convert complex spectral data into fewer principal components by dimension reduction, preserving the most important information. The linear discriminant analysis can project samples to the directions between classes and in the classes in the low-dimensional space respectively, so that effective distinction between different classes is realized. These key feature sets provide more representative and distinguishing spectral features, providing an important basis for subsequent analysis and classification.
The primary analysis submodule performs operations such as Bayesian statistics, cluster analysis and the like by utilizing the key feature set of the spectrum data, and performs primary analysis on the data. Bayesian statistics can classify and judge the optical data through a probability model and priori knowledge, and provide more accurate data analysis results. Cluster analysis may then group the spectral data to find potential patterns and structures therein, providing clues for further interpretation and use of the data. The primary analysis report may summarize the results of the primary analysis, providing a primary understanding and interpretation of the data.
Referring to fig. 5, the shape measurement submodule performs edge detection on the seed image by using a convolutional neural network to realize shape measurement and generate seed shape data;
the size measurement submodule is used for measuring the size of the seeds based on the shape data of the seeds by applying a watershed algorithm and morphological analysis to generate seed size data;
the density measurement submodule is used for calculating seed density by analyzing seed size data and combining a gravity sensitive element by adopting a mass-volume method to generate seed density data.
The shape measurement submodule utilizes a Convolutional Neural Network (CNN) to carry out edge detection on the seed image, so that measurement and analysis on the shape of the seed are realized. By training the CNN model, edge information in the seed image can be extracted, the outline and shape characteristics of the seed can be identified, and corresponding shape data can be generated. These shape data may include indicators of perimeter, area, aspect ratio, etc. of the seed to describe the diversity and variability of morphological features of the seed.
The size measurement submodule measures the size of the seeds by applying a watershed algorithm, morphological analysis and other methods based on the shape data of the seeds. The watershed algorithm can separate the seed region from the background region, and further calculate the size and the size characteristics of the seeds. Morphological analysis can eliminate noise points and irregular areas in the image through operations such as corrosion, expansion and the like, so that the size of seeds can be measured more accurately. The size data can comprise parameters such as diameter, length, width and the like of the seeds, and provides important basis for researching biological characteristics and quality of the seeds.
The density measurement submodule calculates the density of the seeds by adopting a mass-volume method through analyzing the size data of the seeds and combining the technologies of gravity sensitive elements and the like. From the mass and volume of the seed, the mass per unit volume of the seed can be deduced, thereby obtaining density data of the seed. The density data can be used for evaluating the quality and maturity of seeds, and has important significance for links such as planting and storing of seeds.
Referring to fig. 6, the data processing sub-module integrates the primary analysis report, the seed shape data, the seed size data and the seed density data, and processes the data by adopting the Z-score normalization and normalization technology to generate normalized seed data;
The data integration sub-module is used for ensuring the continuity of data by applying correlation analysis based on standardized seed data and integrating the data sets to generate a complete seed information data set;
the data storage sub-module stores the complete seed information data set in a distributed database, ensures high availability and high reliability, and generates a seed information database.
The data processing sub-module integrates the primary analysis report, the seed shape data, the seed size data and the seed density data, and applies the Z-score normalization and normalization technology to process the data to generate normalized seed data. The Z-score normalization can convert data into standard normal distribution, and eliminate dimension differences among different variables, so that the data is more comparable and interpretable. The normalization technology can scale the data to a specified range, ensure that the data are compared on the same scale, and reduce deviation caused by data difference.
The data integration submodule ensures the continuity of data by using methods such as relevance analysis and the like based on standardized seed data, integrates the data sets and generates a complete seed information data set. The relevance analysis can explore relevance and relevance relations in the seed data, and find out rules and potential relevance modes in the relevance and relevance relations. By taking the relevance among different data into consideration, the accuracy and the completeness of data integration can be ensured, and a consistent data basis is provided for subsequent analysis and application.
The data storage sub-module stores the complete seed information data set in a distributed database to ensure high availability and high reliability. The distributed database can disperse the load of data storage and processing, and improve the performance and expansibility of the system. By storing the seed information database in a distributed environment, backup and redundancy of data can be realized, and reliability and durability of the data are ensured.
Referring to fig. 7, the feature screening submodule performs feature screening by using LASSO regularization and chi-square inspection based on the complete seed information data set, eliminates irrelevant or redundant features, and generates a simplified seed information feature set;
the model training sub-module is based on the simplified seed information feature set, and adopts a deep learning convolutional neural network and a radial basis function of a support vector machine to carry out model training so as to generate a seed maturity prediction model;
the model prediction sub-module carries out prediction operation on the follow-up complete seed information data set by means of the seed maturity prediction model to generate a seed maturity prediction result.
The feature screening submodule performs feature screening by utilizing the technologies of LASSO regularization, chi-square inspection and the like based on the complete seed information data set. LASSO regularization can be performed by introducing an L1 norm penalty term to prompt the model to select features with strong relevance and reject irrelevant or redundant features. The chi-square test can measure the correlation between the characteristics and the target variable, and the significant characteristics related to the seed maturity prediction are screened out. Through feature screening, a simplified seed information feature set can be generated, redundant information is removed, and the effect and the interpretability of the prediction model are improved.
The model training submodule adopts a deep-learning Convolutional Neural Network (CNN) and a radial basis function of a Support Vector Machine (SVM) to carry out model training based on the simplified seed information feature set. The deep learning CNN model can extract characteristics by utilizing operations such as rolling and pooling, and the like, and can carry out classification or regression tasks through the full connection layer. The support vector machine uses a radial basis function as a kernel function to map input features into a high-dimensional space, and establishes an optimal hyperplane for classification or regression. The training of the models can construct a seed maturity prediction model, and accurate prediction of seed maturity is realized by learning patterns and rules related to feature sets.
And the model prediction submodule predicts the subsequent complete seed information data set by using the trained seed maturity prediction model to generate a seed maturity prediction result. By inputting the complete seed information dataset, the predictive model can infer the maturity of each seed using learned patterns and rules. The prediction results can be used for measuring the maturity of seeds, providing references for screening and classifying the seeds, and also can be used for decision making of seed production and quality control.
Referring to fig. 8, the grading sub-module adopts a C4.5 decision tree algorithm to grade different maturity levels of the seeds based on the seed maturity prediction result, and generates seed grade grading information;
the quality sorting submodule relies on seed grade sorting information, sorts seed quality by using a heap sorting algorithm, and generates a seed quality sorting list;
and the maturity classification submodule classifies the maturity of the seeds by applying a random forest algorithm according to the seed quality ordered list to generate a seed maturity classification result.
The grading submodule adopts a C4.5 decision tree algorithm to grade different maturity grades of the seeds based on the seed maturity prediction result. By analyzing the characteristics and the values of the seed maturity prediction result, the C4.5 decision tree algorithm can construct a decision tree, and the seeds are divided into different maturity levels according to the division rules of different characteristics. These grades may be classified according to the degree of seed maturity, such as immature, semi-mature, and fully mature grades. Seed ranking information may provide a detailed description and classification of seed maturity.
The quality sorting submodule sorts the quality of the seeds by using a heap sorting algorithm according to the seed grading information. According to the seed grading, the seeds are ranked according to the maturity level, and the heap ranking algorithm can construct a heap data structure according to a predefined ranking rule and rank the seeds according to a specified order. Through quality sorting, seeds can be arranged according to the quality of the seeds, and a seed quality sorting list is generated.
And the maturity classification submodule classifies the maturity of the seeds by using a random forest algorithm according to the seed quality ordered list. The random forest is an integrated learning algorithm, and a method for classifying samples is realized by constructing a plurality of decision trees and voting. In the seed maturity classification, various characteristics of seeds can be comprehensively considered by utilizing a random forest algorithm, and the seeds can be classified in maturity. And (5) generating a seed maturity classification result by predicting the specific maturity level to which each seed belongs.
Referring to fig. 9, the decision suggestion generation submodule refers to the seed maturity classification result, and uses the fuzzy logic rule engine to generate a preliminary decision suggestion, and generates a preliminary decision suggestion;
the agricultural knowledge base submodule supplements and optimizes the decision based on the preliminary decision suggestion and combines the agricultural knowledge graph technology to generate an optimized decision suggestion;
the decision support sub-module fuses the optimized decision advice with the actual agricultural policy and technical guidelines to form an ultimate decision advice and generate an intelligent decision support report.
The decision suggestion generation submodule generates preliminary decision suggestions by using a fuzzy logic rule engine based on the seed maturity classification result. The fuzzy logic rule engine may generate preliminary decision suggestions based on the seed maturity classification result and the corresponding decision rules. Corresponding agricultural measures and management suggestions, such as planting time, fertilization scheme, irrigation strategy and the like, can be formulated according to different maturity levels and other relevant characteristics. These preliminary decision suggestions may provide a farmer or agricultural practitioner with preliminary guidance and decision direction.
The agricultural knowledge base submodule supplements and optimizes the decisions based on the preliminary decision suggestions and combines the agricultural knowledge graph technology. The agricultural knowledge base submodule can provide rich agricultural knowledge and professional agricultural information, and related agricultural technologies and best practices are retrieved from the agricultural knowledge map in combination with the characteristics and requirements of the decision suggestion. By integrating the decision advice and the knowledge of the domain expert, the preliminary decision advice can be optimized, and a more reasonable and feasible decision scheme can be provided.
The decision support sub-module fuses the optimized decision advice with the actual agricultural policy and technical guideline to form an ultimate decision advice. The decision support sub-module can comprehensively consider factors such as seed maturity, agricultural knowledge, industry specifications, policy requirements and the like to generate an intelligent decision support report. This report will provide decision advice based on the latest agricultural technologies and industry standards, and guidance for personalization and customization for specific agricultural environments and actual needs. The agricultural practitioner can make decisions according to these final decision suggestions, improving the benefits of planting and the quality of agricultural products.
A portable seed maturity spectrum detection device comprises a memory and a processor, wherein a computer program is stored in the memory, and the portable seed maturity spectrum detection system is realized when the processor executes the computer program.
Working principle: firstly, a multi-mode spectrum acquisition module acquires spectrum information of seeds in different spectrum modes through a portable optical fiber sensor, and removes noise by utilizing a differential time delay integration technology to obtain seed multi-mode spectrum data after noise suppression. The spectral data processing module then extracts a key set of spectral data features based on the data using principal component analysis and linear discriminant analysis. Meanwhile, the seed parameter acquisition module acquires basic attribute data such as the size, the shape, the density and the like of the seeds through image analysis and the gravity sensitive element.
And the multi-source data integration module integrates the key feature set of the spectrum data with the basic attribute data of the seeds by utilizing a data fusion technology to generate a complete seed information data set. And then, the model training and predicting module performs model training and prediction based on the complete seed information data set by using machine learning algorithms such as deep learning and support vector machines and the like to generate a seed maturity predicting result.
Further, the sorting and classifying module sorts the quality sorting and maturity of the seeds by utilizing a decision tree algorithm according to the maturity prediction result of the seeds, and generates a corresponding sorting list and classification result. Finally, the intelligent decision support module combines the quality sequencing and maturity classification results of the seeds, and utilizes an agricultural expert knowledge base, a decision tree and a logistic regression algorithm to generate an intelligent decision support report. By integrating the modules of spectrum acquisition, data processing, model training and prediction, sequencing and classification, intelligent decision support and the like, the system can help farmers optimize planting management and improve crop yield and quality.
The present invention is not limited to the above embodiments, and any equivalent embodiments which can be changed or modified by the technical disclosure described above can be applied to other fields, but any simple modification, equivalent changes and modification made to the above embodiments according to the technical matter of the present invention will still fall within the scope of the technical disclosure.
Claims (9)
1. A portable seed maturity spectrum detection system, characterized by: the portable seed maturity spectrum detection system consists of a multi-mode spectrum acquisition module, a spectrum data processing module, a seed parameter acquisition module, a multi-source data integration module, a model training and prediction module, a sequencing and classifying module and an intelligent decision support module;
the multi-mode spectrum acquisition module adopts a portable optical fiber sensor to acquire spectrum information of seeds under the multi-mode spectrum comprising a reflection spectrum, a transmission spectrum and a fluorescence spectrum, and removes noise by utilizing a differential time delay integration technology to acquire seed multi-mode spectrum data after noise suppression;
The spectrum data processing module performs feature extraction by using principal component analysis and linear discriminant analysis on the basis of the seed multimode spectrum data after noise suppression to obtain a spectrum data key feature set;
the seed parameter acquisition module acquires seed basic attribute data comprising the size, shape and density of seeds through image analysis and a gravity sensitive element;
the multi-source data integration module combines the spectrum data key feature set and the seed basic attribute data by utilizing a data fusion technology to generate a complete seed information data set;
the model training and predicting module performs model training and prediction based on the complete seed information dataset by using a machine learning algorithm comprising deep learning and a support vector machine to generate a seed maturity predicting result;
the sorting and classifying module performs quality sorting and maturity classification on the seeds according to quality standards by utilizing a decision tree algorithm based on the seed maturity prediction result to generate a seed quality sorting and maturity classification result;
the intelligent decision support module generates an intelligent decision support report including optimal harvesting time and planting scheme through a decision tree and a logistic regression algorithm according to seed quality sorting and maturity classification results and by combining an agricultural expert knowledge base.
2. The portable seed maturity spectral detection system of claim 1, wherein: the multi-mode spectrum acquisition module comprises a light source sub-module, an optical fiber sensing sub-module and a data acquisition sub-module;
the spectrum data processing module comprises a data preprocessing sub-module, a feature extraction sub-module and a primary analysis sub-module;
the seed parameter acquisition module comprises a shape measurement sub-module, a size measurement sub-module and a density measurement sub-module;
the multi-source data integration module comprises a data processing sub-module, a data integration sub-module and a data storage sub-module;
the model training and predicting module comprises a feature screening sub-module, a model training sub-module and a model predicting sub-module;
the sorting and classifying module comprises a grading sub-module, a quality sorting sub-module and a maturity classifying sub-module;
the intelligent decision support module comprises a decision suggestion generation sub-module, an agricultural knowledge base sub-module and a decision support sub-module.
3. The portable seed maturity spectral detection system of claim 2, wherein: the light source submodule applies a modulation frequency technology and a broadband light source technology to generate continuous wavelength light from ultraviolet to near infrared so as to generate broadband light source irradiation;
The optical fiber sensing submodule accurately captures the multimode spectrum of the seed by utilizing a multichannel optical fiber technology based on broadband light source irradiation to generate original multimode spectrum data;
the data acquisition submodule applies differential time delay integration and wavelet denoising technology based on original multi-mode spectrum data to remove external noise in the spectrum data and generate spectrum data after noise suppression.
4. The portable seed maturity spectral detection system of claim 2, wherein: the data preprocessing sub-module receives the spectral data after noise suppression, performs Gaussian filtering processing and baseline correction, and generates preprocessed spectral data;
the characteristic extraction submodule generates a spectral data key characteristic set by adopting principal component analysis and linear discriminant analysis based on the preprocessed spectral data;
and the primary analysis submodule performs Bayesian statistics and cluster analysis by utilizing the spectral data key feature set, provides primary analysis for data, and generates a primary analysis report.
5. The portable seed maturity spectral detection system of claim 2, wherein: the shape measurement submodule performs edge detection on the seed image by using a convolutional neural network to realize shape measurement and generate seed shape data;
The size measurement submodule is used for measuring the size of the seeds based on the shape data of the seeds by applying a watershed algorithm and morphological analysis to generate seed size data;
the density measurement submodule is used for calculating seed density by analyzing seed size data and combining a gravity sensitive element by adopting a mass-volume method to generate seed density data.
6. The portable seed maturity spectral detection system of claim 2, wherein: the data processing sub-module integrates the primary analysis report, the seed shape data, the seed size data and the seed density data, and adopts a Z-score standardization and normalization technology to process the data so as to generate standardized seed data;
the data integration submodule ensures the continuity of data by using correlation analysis based on standardized seed data and integrates a data set to generate a complete seed information data set;
the data storage sub-module stores the complete seed information data set in a distributed database, ensures high availability and high reliability, and generates a seed information database.
7. The portable seed maturity spectral detection system of claim 2, wherein: the feature screening submodule performs feature screening by utilizing LASSO regularization and chi-square inspection based on the complete seed information data set, eliminates irrelevant or redundant features and generates a simplified seed information feature set;
The model training submodule is based on the simplified seed information feature set, and adopts a deep-learning convolutional neural network and a radial basis function of a support vector machine to carry out model training so as to generate a seed maturity prediction model;
the model prediction submodule carries out prediction operation on the follow-up complete seed information data set by means of a seed maturity prediction model to generate a seed maturity prediction result.
8. The portable seed maturity spectral detection system of claim 2, wherein: the grading submodule adopts a C4.5 decision tree algorithm to grade different maturity levels of the seeds based on the seed maturity prediction result, and generates seed grading information;
the quality sorting submodule is used for sorting the seed quality by using a heap sorting algorithm according to the seed grade sorting information to generate a seed quality sorting list;
and the maturity classification submodule classifies the maturity of the seeds by applying a random forest algorithm according to the seed quality ordered list to generate a seed maturity classification result.
9. A portable seed maturity spectrum detection device comprising a memory and a processor, wherein said memory has a computer program stored therein, said processor implementing the portable seed maturity spectrum detection system of any one of claims 1-8 when said computer program is executed.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311315405.XA CN117054354B (en) | 2023-10-12 | 2023-10-12 | Portable seed maturity spectrum detection system and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202311315405.XA CN117054354B (en) | 2023-10-12 | 2023-10-12 | Portable seed maturity spectrum detection system and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN117054354A CN117054354A (en) | 2023-11-14 |
| CN117054354B true CN117054354B (en) | 2024-03-05 |
Family
ID=88653971
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202311315405.XA Active CN117054354B (en) | 2023-10-12 | 2023-10-12 | Portable seed maturity spectrum detection system and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN117054354B (en) |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6080950A (en) * | 1996-05-02 | 2000-06-27 | Centrum Voor Plantenveredelings | Method for determining the maturity and quality of seeds and an apparatus for sorting seeds |
| CN103636315A (en) * | 2013-11-20 | 2014-03-19 | 华南理工大学 | Hyperspectrum-based seed germination rate online-detection apparatus and method thereof |
| CN104990892A (en) * | 2015-06-24 | 2015-10-21 | 中国农业大学 | Spectrum image lossless identification model establishing method for seeds and seed identification method |
| WO2017053273A1 (en) * | 2014-09-12 | 2017-03-30 | The Climate Corporation | Estimating intra-field properties within a field using hyperspectral remote sensing |
| CN106908408A (en) * | 2017-03-01 | 2017-06-30 | 四川农业大学 | A kind of assay method of Itanlian rye crude protein content |
| CN111665215A (en) * | 2020-05-26 | 2020-09-15 | 西北农林科技大学 | Apple maturity detection system and method based on embedded mode |
| CN112955000A (en) * | 2018-10-24 | 2021-06-11 | 克莱米特公司 | Computer-assisted farm operation using machine learning based seed harvest moisture prediction |
| CN113767472A (en) * | 2019-03-04 | 2021-12-07 | 克莱米特公司 | Data storage and transmission device for agricultural intelligent computing system |
| CN114112932A (en) * | 2021-11-08 | 2022-03-01 | 南京林业大学 | Hyperspectral detection method and sorting equipment for maturity of oil-tea camellia fruits based on deep learning |
| CN116859007A (en) * | 2023-09-04 | 2023-10-10 | 云南省林业和草原科学院 | Automatic monitoring device for growth condition of grass seeds |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7745602B2 (en) * | 2007-02-06 | 2010-06-29 | Board Of Trustees Of Michigan State University | Compositions and methods for drought tolerance |
| US20160224703A1 (en) * | 2015-01-30 | 2016-08-04 | AgriSight, Inc. | Growth stage determination system and method |
| US11568340B2 (en) * | 2017-11-09 | 2023-01-31 | Climate Llc | Hybrid seed selection and seed portfolio optimization by field |
| US20200005166A1 (en) * | 2018-07-02 | 2020-01-02 | The Climate Corporation | Automatically assigning hybrids or seeds to fields for planting |
-
2023
- 2023-10-12 CN CN202311315405.XA patent/CN117054354B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US6080950A (en) * | 1996-05-02 | 2000-06-27 | Centrum Voor Plantenveredelings | Method for determining the maturity and quality of seeds and an apparatus for sorting seeds |
| CN103636315A (en) * | 2013-11-20 | 2014-03-19 | 华南理工大学 | Hyperspectrum-based seed germination rate online-detection apparatus and method thereof |
| WO2017053273A1 (en) * | 2014-09-12 | 2017-03-30 | The Climate Corporation | Estimating intra-field properties within a field using hyperspectral remote sensing |
| CN104990892A (en) * | 2015-06-24 | 2015-10-21 | 中国农业大学 | Spectrum image lossless identification model establishing method for seeds and seed identification method |
| CN106908408A (en) * | 2017-03-01 | 2017-06-30 | 四川农业大学 | A kind of assay method of Itanlian rye crude protein content |
| CN112955000A (en) * | 2018-10-24 | 2021-06-11 | 克莱米特公司 | Computer-assisted farm operation using machine learning based seed harvest moisture prediction |
| CN113767472A (en) * | 2019-03-04 | 2021-12-07 | 克莱米特公司 | Data storage and transmission device for agricultural intelligent computing system |
| CN111665215A (en) * | 2020-05-26 | 2020-09-15 | 西北农林科技大学 | Apple maturity detection system and method based on embedded mode |
| CN114112932A (en) * | 2021-11-08 | 2022-03-01 | 南京林业大学 | Hyperspectral detection method and sorting equipment for maturity of oil-tea camellia fruits based on deep learning |
| CN116859007A (en) * | 2023-09-04 | 2023-10-10 | 云南省林业和草原科学院 | Automatic monitoring device for growth condition of grass seeds |
Non-Patent Citations (4)
| Title |
|---|
| Root diameter decreases and rhizosheath carboxylates and acid phosphatases increase in chickpea during plant development;Pang JY et al;《PLANT AND SOIL》;第476卷(第1-2期);219-238 * |
| 刘宇等.《智能搜索和推荐*** 原理、算法与应用》.北京：机械工业出版社,2021,(第第一版版),257. * |
| 干热河谷优良乡土草种三芒草驯化应用研究;常恩福等;《西部林业科学》;第52卷(第3期);47-54 * |
| 玉米种子质量的THz检测机理与分析方法研究;李慧;《中国优秀硕士学位论文全文数据库 (农业科技辑)》(第12期);D047-62 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN117054354A (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Xing et al. | Combination of chemometric tools and image processing for bruise detection on apples | |
| Rizzo et al. | Fruit ripeness classification: A survey | |
| Gruszczyński et al. | Supporting soil and land assessment with machine learning models using the Vis-NIR spectral response | |
| Liu et al. | Variety classification of coated maize seeds based on Raman hyperspectral imaging | |
| Sahu et al. | A systematic literature review of machine learning techniques deployed in agriculture: A case study of banana crop | |
| Chen et al. | Discrimination of Fresh Tobacco Leaves with Different Maturity Levels by Near‐Infrared (NIR) Spectroscopy and Deep Learning | |
| Haque et al. | Computer vision approach to characterize size and shape phenotypes of horticultural crops using high-throughput imagery | |
| CN113657158A (en) | Google Earth Engine-based large-scale soybean planting region extraction algorithm | |
| Gencturk et al. | Detection of hazelnut varieties and development of mobile application with CNN data fusion feature reduction-based models | |
| Pratama et al. | Deep learning for assessing unhealthy lettuce hydroponic using convolutional neural network based on faster R-CNN with Inception V2 | |
| Qi et al. | Rapid and non-destructive determination of soluble solid content of crown pear by visible/near-infrared spectroscopy with deep learning regression | |
| Fan et al. | Non-destructive detection of single-seed viability in maize using hyperspectral imaging technology and multi-scale 3D convolutional neural network | |
| Jin et al. | A Novel Tran_NAS Method for the Identification of Fe-and Mg-Deficient Pear Leaves from N-and P-Deficient Pear Leaf Data | |
| CN117054354B (en) | Portable seed maturity spectrum detection system and device | |
| Wang et al. | SVM classification method of waxy corn seeds with different vitality levels based on hyperspectral imaging | |
| Luyssaert et al. | Evaluation of forest nutrition based on large-scale foliar surveys: are nutrition profiles the way of the future? | |
| Chauhan et al. | Classification of Nutritional Deficiencies in Cabbage Leave Using Random Forest | |
| CN117077868A (en) | Model-based grain yield prediction system and method | |
| Ramya et al. | A review of different classification techniques in machine learning using WEKA for plant disease detection | |
| Rößle et al. | Efficient noninvasive FHB estimation using RGB images from a novel multiyear, multirater dataset | |
| Wu et al. | Nitrogen status assessment for multiple cultivars of strawberries using portable FT-NIR spectrometers combined with cultivar recognition and multivariate analysis | |
| Sajitha et al. | Smart farming application using knowledge embedded-graph convolutional neural network (KEGCNN) for banana quality detection | |
| Ruby et al. | An effective feature descriptor method to classify plant leaf diseases using eXtreme Gradient Boost | |
| Wang et al. | Detection of Insect-Damaged Maize Seed Using Hyperspectral Imaging and Hybrid 1D-CNN-BiLSTM Model | |
| Zhang et al. | Drought recognition based on feature extraction of multispectral images for the soybean canopy |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |