CN111260259A - Coupled representation-based crop breeding evaluation method and device - Google Patents
Coupled representation-based crop breeding evaluation method and device Download PDFInfo
- Publication number
- CN111260259A CN111260259A CN202010130054.5A CN202010130054A CN111260259A CN 111260259 A CN111260259 A CN 111260259A CN 202010130054 A CN202010130054 A CN 202010130054A CN 111260259 A CN111260259 A CN 111260259A
- Authority
- CN
- China
- Prior art keywords
- character
- coupling
- features
- breeding
- trait
- 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.)
- Granted
Links
- 230000001488 breeding effect Effects 0.000 title claims abstract description 119
- 238000009395 breeding Methods 0.000 title claims abstract description 117
- 238000011156 evaluation Methods 0.000 title claims abstract description 68
- 238000010168 coupling process Methods 0.000 claims abstract description 180
- 238000005859 coupling reaction Methods 0.000 claims abstract description 180
- 230000008878 coupling Effects 0.000 claims abstract description 176
- 239000011159 matrix material Substances 0.000 claims abstract description 34
- 238000000034 method Methods 0.000 claims abstract description 32
- 238000013210 evaluation model Methods 0.000 claims abstract description 20
- 230000014509 gene expression Effects 0.000 claims abstract description 18
- 238000007781 pre-processing Methods 0.000 claims abstract description 18
- 239000004576 sand Substances 0.000 claims abstract description 12
- 238000002474 experimental method Methods 0.000 claims description 11
- 238000004590 computer program Methods 0.000 claims description 8
- 238000010276 construction Methods 0.000 claims description 7
- 238000003860 storage Methods 0.000 claims description 7
- 230000003190 augmentative effect Effects 0.000 claims 1
- 230000000694 effects Effects 0.000 abstract description 7
- 238000009826 distribution Methods 0.000 abstract description 5
- 239000000463 material Substances 0.000 description 20
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 14
- 238000005516 engineering process Methods 0.000 description 12
- 241000196324 Embryophyta Species 0.000 description 10
- 238000005259 measurement Methods 0.000 description 6
- 238000010606 normalization Methods 0.000 description 6
- 238000012545 processing Methods 0.000 description 6
- 238000006243 chemical reaction Methods 0.000 description 5
- 238000004891 communication Methods 0.000 description 5
- 238000011161 development Methods 0.000 description 5
- 230000008569 process Effects 0.000 description 5
- 238000010586 diagram Methods 0.000 description 4
- 238000012360 testing method Methods 0.000 description 4
- 238000004364 calculation method Methods 0.000 description 3
- 238000011072 cell harvest Methods 0.000 description 3
- 241000037488 Coccoloba pubescens Species 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 2
- 230000018044 dehydration Effects 0.000 description 2
- 238000006297 dehydration reaction Methods 0.000 description 2
- 210000005069 ears Anatomy 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- IUVCFHHAEHNCFT-INIZCTEOSA-N 2-[(1s)-1-[4-amino-3-(3-fluoro-4-propan-2-yloxyphenyl)pyrazolo[3,4-d]pyrimidin-1-yl]ethyl]-6-fluoro-3-(3-fluorophenyl)chromen-4-one Chemical class C1=C(F)C(OC(C)C)=CC=C1C(C1=C(N)N=CN=C11)=NN1[C@@H](C)C1=C(C=2C=C(F)C=CC=2)C(=O)C2=CC(F)=CC=C2O1 IUVCFHHAEHNCFT-INIZCTEOSA-N 0.000 description 1
- 208000035240 Disease Resistance Diseases 0.000 description 1
- 240000008042 Zea mays Species 0.000 description 1
- 235000005824 Zea mays ssp. parviglumis Nutrition 0.000 description 1
- 235000002017 Zea mays subsp mays Nutrition 0.000 description 1
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 235000005822 corn Nutrition 0.000 description 1
- 238000010219 correlation analysis Methods 0.000 description 1
- 208000022602 disease susceptibility Diseases 0.000 description 1
- 230000002708 enhancing effect Effects 0.000 description 1
- 238000003306 harvesting Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000009400 out breeding Methods 0.000 description 1
- 238000003976 plant breeding Methods 0.000 description 1
- 238000000513 principal component analysis Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000013139 quantization Methods 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000001709 templated self-assembly Methods 0.000 description 1
- 238000012546 transfer Methods 0.000 description 1
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
- 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
- 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—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/02—Agriculture; Fishing; Forestry; Mining
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Economics (AREA)
- Strategic Management (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Development Economics (AREA)
- Physics & Mathematics (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Animal Husbandry (AREA)
- Marine Sciences & Fisheries (AREA)
- Mining & Mineral Resources (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Breeding Of Plants And Reproduction By Means Of Culturing (AREA)
Abstract
The embodiment of the invention provides a crop breeding evaluation method and device based on coupling expression, wherein the method comprises the following steps: constructing a crop breeding evaluation data set, wherein each data unit in the data set comprises a trait characteristic set T of a breeding individual and an experimental result; preprocessing all the character feature sets T; performing exponential expansion of preset digit L on all character characteristics to form TL(ii) a According to TLEstablishing each character and TLDetermining L coupling characteristics corresponding to each character according to the coupling relation matrix of all character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC(ii) a Based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing TSAnd constructing a breeding evaluation model for breeding evaluation. The method can effectively describe the coupling relation between the crop character expressionsAnd the bias of evaluation effects caused by the non-independent and same distribution of the performance of each character of the crops is solved.
Description
Technical Field
The invention relates to the technical field of crop breeding, in particular to a crop breeding evaluation method and device based on coupling expression.
Background
The seed industry is the chip of agriculture, and the breeding and the popularization of excellent varieties are the most important and most effective ways for obtaining high and stable yield of crops, and are the fundamental power for innovation and development of the seed industry. The breeding of the modern breed is a process of continuously selecting the best from tens of thousands or even hundreds of thousands of individuals in a plurality of life cycles of crops according to a great amount of test information and professional knowledge. Crop breeding evaluation is an important link for selecting excellent varieties from hundreds of thousands of individuals, and efficient and comprehensive breeding evaluation is effective guarantee for breeding effect.
In recent years, crop breeding evaluation gradually changes from a mode of mainly taking yield to a mode of comprehensively considering factors such as yield, quality, stress resistance and the like so as to adapt to changes of grain production situations and consumption concepts. Meanwhile, rapid development of information technology drives rapid promotion of data technology, and rapid development of breeding software and equipment brings informatization accumulation of a large amount of crop phenotype character data and breeding data, so that a development opportunity is provided for data breeding and information breeding. Under the background, the information-based breeding auxiliary decision-making technology which takes the conventional breeding phenotype data as the source and combines the modern information technology with the breeding professional background gradually becomes an important development direction of the breeding evaluation technology.
Various information technologies such as correlation analysis, principal component analysis, analytic hierarchy process, fuzzy comprehensive evaluation, grey correlation evaluation and the like play an important role in crop breeding. The technologies effectively improve the datamation and informatization degree of the crop breeding evaluation technology through the analysis and utilization of the crop character data, and promote the change of the crop breeding evaluation from empirical breeding to datamation and informatization breeding. However, these breeding evaluation methods generally assume that the crop traits are independently and identically distributed. However, this assumption is not always true, and in fact, there is an objectively complex coupling relationship between crop traits.
Disclosure of Invention
In order to solve the above problems, embodiments of the present invention provide a method and an apparatus for evaluating crop breeding based on coupled representation.
In a first aspect, an embodiment of the present invention provides a coupled representation-based crop breeding evaluation method, including: constructing a crop breeding evaluation data set, wherein each data unit in the data set corresponds to a breeding individual, and each data unit comprises a trait characteristic set T formed by trait performances of the breeding individual and an individual experimental result; preprocessing all the character feature sets T in the data set to obtain a preprocessed data set; for each individual, performing exponential expansion of a preset digit L on all the character characteristics so as to enable each character of the individual to obtain L expanded characteristics from the power of 1 to the power of L to form an expanded character characteristic set TL(ii) a According to TLEstablishing each character and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC(ii) a Based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
Further, said is according to TLEstablishing each character and TLThe coupling relation matrix of all the character characteristics comprises: according to the expanded character feature set TLDetermining the Pearson correlation coefficient and the Kendell correlation coefficient of the L expansion characteristics of each characteristic and all the expansion characteristic characteristics respectively; and determining the coupling relation values of the L expansion characteristics of each character and all the character characteristics according to the L expansion characteristics of each character and the Pearson correlation coefficient and the Kendall correlation coefficient of all the character characteristics, and finally obtaining a coupling relation matrix.
Further, determining a coupling relation value of the L extended features of each trait with all trait features according to the L extended features of each trait, the pearson correlation coefficient and the kender correlation coefficient of all trait features respectively, includes determining according to the following formula:
C(Tip，Tjq)＝α·cor(Tip，Tjq)+(1-α)·tau(Tip，Tjq)，p、q∈(1，L)，j∈(1，n)；
wherein L is a predetermined number of bits, TipFor p-th power expansion features of the i-th trait, TjqExpanding the characteristic for the q power of the j character; c (T)ip，Tjq) Is TipAnd Tjqα is a predetermined parameter, cor (T)ip，Tjq) Is TipAnd TjqPearson's correlation coefficient of (tau, T)ip，Tjq) Is TipAnd TjqThe kendell correlation coefficient.
Further determining L coupling characteristics corresponding to each character according to the coupling relation matrix of each character, the weights of the L expansion characteristics with different powers and the vector of the character characteristics after expansion, wherein the L coupling characteristics corresponding to each character are determined according to the following formula:
wherein, TiCVector representation of L coupled features as character i; sLA vector of expanded trait features for an individual s; omega is sLThe weight coefficient vector of (1) is determined by the weights of the L extended features; ri TCoupling relation matrix R as character ii⊙ is a hadamard product,
is a matrix multiplication.
Optionally, the weights of the L extended features at different powers are determined according to the inverse of the factorial of each power.
Further, the base is TCAnd selecting coupling characteristics by taking the experimental result as a label to obtain scoresCoupling feature subset T with highest class accuracySThe method comprises the following steps: using trait coupled feature set TCClassifying as classification attribute, and obtaining classification accuracy A according to experimental result0(ii) a Traversing character coupling feature set TCObtaining the classification accuracy of the removed residual coupling character features and recording the maximum value of the residual coupling character features; if the maximum value is greater than A0Deleting the corresponding coupled character features in the character coupled feature set, and updating the coupled character feature set; repeatedly calculating the classification accuracy rate based on the updated coupling character feature set, and eliminating the coupling character features with higher accuracy rate using the residual coupling character features until the classification accuracy rate is not increased any more or reaches a preset number of times, so as to obtain the coupling feature subset T with the highest classification accuracy rateS。
Optionally, the preprocessing includes normalization, denoising, and normalization.
In a second aspect, an embodiment of the present invention provides a coupled representation-based crop breeding evaluation apparatus, including: the data set construction module is used for constructing a crop breeding evaluation data set, each data unit in the data set corresponds to a breeding individual, and each data unit comprises a trait characteristic set T formed by trait performances of the breeding individual and an individual experiment result; the preprocessing module is used for preprocessing all the character feature sets T in the data set to obtain a preprocessed data set; a coupling relation establishing module for performing exponential expansion of preset digits L on all the character characteristics of each individual so that each character of the individual obtains L expanded characteristics from the power of 1 to the power of L to form an expanded character characteristic set TL(ii) a A coupling characteristic constructing module for constructing a coupling characteristic according to TLEstablishing each character and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC(ii) a An evaluation model construction module for constructing an evaluation model based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
In a third aspect, an embodiment of the present invention provides an electronic device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor executes the computer program to implement the steps of the method for evaluating crop breeding based on coupled representation according to the first aspect of the present invention.
In a fourth aspect, embodiments of the present invention provide a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program, when executed by a processor, implements the steps of the method for evaluating crop breeding based on coupled representation according to the first aspect of the present invention.
According to the crop breeding evaluation method and device based on coupling expression provided by the embodiment of the invention, all the character characteristics are subjected to index expansion of the preset digit L for each breeding individual, the coupling relation among the character characteristics can be strengthened, and the character coupling characteristic set T based on each individual isCAnd the experimental result is used for carrying out feature selection to obtain the coupling feature subset T with the highest classification accuracySCompared with the existing breeding evaluation technology, the method can effectively describe the coupling relation among the crop character expressions, solve the problem of bias evaluation effect caused by non-independent and same distribution of the crop character expressions, and further improve the breeding efficiency and the continuous yield of the variety.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, and it is obvious that the drawings in the following description are some embodiments of the present invention, and those skilled in the art can also obtain other drawings according to the drawings without creative efforts.
FIG. 1 is a flow chart of a coupled representation-based crop breeding evaluation method provided by an embodiment of the invention;
FIG. 2 is a diagram of a coupled representation-based plant breeding evaluation apparatus according to an embodiment of the present invention;
fig. 3 is a schematic physical structure diagram of an electronic device according to an embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are some, but not all, embodiments of the present invention. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to better describe crop performance information and improve breeding auxiliary decision level, the invention provides a crop breeding evaluation method based on coupling expression, and further provides a new method and technology for the technical field of crop breeding.
To solve this problem, embodiments of the present invention provide a crop breeding evaluation method based on coupled representation. Fig. 1 is a flowchart of a coupled representation-based crop breeding evaluation method according to an embodiment of the present invention, and as shown in fig. 1, the coupled representation-based crop breeding evaluation method according to the embodiment of the present invention includes:
101, constructing a crop breeding evaluation data set, wherein each data unit in the data set corresponds to a breeding individual, and each data unit comprises a trait feature set T formed by trait performances of the breeding individual and an individual experimental result.
Firstly, a crop breeding evaluation data set is constructed, a cell which can be planted by a breeding individual is taken as a breeding individual, and each data unit in the data set corresponds to a breeding individual (or material). The evaluation data of each data unit includes: the character characteristic set T and the experimental result r can also comprise the number of the experimental material and the belonging experiment e. This embodiment will be described by taking the example including the number of the experimental material, the belonging experiment e, the trait feature set T, and the experimental result r. Wherein, the trait feature set T may be represented as:
T＝{T1，T2，T3…Tn}
wherein, TiIs the ith individual character characteristic in the character characteristic set T, i is any positive integer not larger than the number of elements in the character characteristic set T,
the j is the expression of the j material character characteristic i, j is any positive integer not greater than the number of materials, and m is the number of individuals.
This example uses data for 15 traits for 135 materials in the early corn group. The raw data are shown in table 1.
TABLE 1
In this embodiment, the example that the trait feature set T includes 15 traits in total includes the following: { cell number, cell harvest area, hectare yield, main control yield ratio, stem rot rate, number of harvested ears, gray leaf spot resistance, standard water hectare yield, cell seed yield, number of harvested plants, large leaf spot resistance, lodging rate, empty stalk rate, ear rot rate, lodging rate, and seed water content during threshing }. T isiFor the i-th trait in the trait set T, including the trait performance of each material, e.g. for the number of cell lines, T1{60, 58, 56, … …, 54, 60 }; for any experimental material, the data includes the number of the experimental material, the trait feature set T, the belonging experiment e, and the experimental result r, wherein the trait features can be represented in a key-value pair form, for example, for material individual #1, the trait feature set T is { cell number: 60, cell harvest area: 6.5, … …, reverse fold: 0.4, water content of the seeds during dehydration: 29.8 }; e is the experiment, in this exampleThe data belong to the same experiment, and E1 is used as the unique identifier of the experiment without loss of generality; r is the experimental result, i.e. the evaluation result of the current material in the experiment, in this example, the experimental result is represented by ordinal value, i.e. the conversion of { liter, stay, don } to {3, 2, 1}, and if the evaluation result of material #1 is don, it is represented as 1.
After this step is completed, any material data is represented in a quaternary data type. As material #1, the data unit can be expressed as { #1, { cell strain number: 60, cell harvest area: 6.5, … …, reverse fold: 0.4, water content of the seeds during dehydration: 29.8}, E1, 1 }.
102. And preprocessing all the character feature sets T in the data set to obtain a preprocessed data set.
Preprocessing a character characteristic set T in a data set to obtain a preprocessed data set; this example preprocesses the raw data shown in table 1 to improve the utilization efficiency and effect of the historical data of the crop breeding evaluation. The data preprocessing work mainly aims at a characteristic feature set T in the data.
As an alternative embodiment, the preprocessing includes normalization, denoising, and normalization, and the following steps are described as an example:
and (3) carrying out standardization treatment on each property characteristic in the property characteristic set T in the data set: the normalization processing comprises a uniform quantization mode and/or a uniform measurement unit and/or a uniform expression form; in this embodiment, the unified quantification method mainly aims at enumerated traits, such as gray leaf spot resistance mainly includes four trait values of { high resistance, medium resistance, disease resistance, and susceptibility }, and can be represented quantitatively using {9, 7, 5, 1 }. The unified measurement unit mainly aims at numerical characters, such as yield of seeds in a cell, some materials use g as a measurement unit, some materials use kg as a measurement unit, and the measurement is converted into kg measurement. The unified representation is not addressed by this embodiment.
Denoising the character feature set T after the normalization processing, wherein the denoising processing may include the following steps:
replacing data corresponding to the characteristic features which are not in the preset characteristic reference value range by the reference value, wherein the reference value range is as follows:
wherein,
is the minimum reference value of the ith personality characteristic,
is the maximum reference value of the ith personality characteristic. The characteristic data of the character when not in the reference value range is larger than
When in use, in
Alternatively, the trait feature data when not within the reference value range is less than
When in use, in
Replacement; for example, the reference value of the seed yield of the cell is 2.5-7 kg, and no data exceeds the range, so that the reference value is not required to be replaced;
substituting the data corresponding to the outlier trait characteristic with a boundary value, wherein the outlier trait characteristic is a trait characteristic satisfying the following formula:
wherein K is a preset parameter,
is TiAverage value of (a) ("sigmaiIs a trait feature TiEdge of standard deviation ofThe cut-off values are:
characteristic data of current outlier characters
Is greater than
When in use, in
Alternatively, when the trait characteristic data is outlier
Is less than
When in use, in
And (4) replacing.
For example, for the characteristic feature of the seed yield of the cell, firstly, calculating the average value of the seed yield of the cell, wherein the result is 5.18; calculating the standard deviation of the yield of the seeds in the cell, wherein the result is 0.63; in this embodiment, when K is 3, the normal value range of the yield of the cell grains is 5.18-3 × 0.63 to 5.18+3 × 0.63, i.e., 3.29 to 7.07kg, in the embodiment, the minimum value is 3.37kg, and the maximum value is 6.69kg, which do not exceed the normal value range, i.e., the yield data of the cell grains in this embodiment has no outlier. If there is an outlier, the data needs to be replaced with 3.29 or 7.07.
Carrying out standardization processing on the character feature set T subjected to denoising processing, wherein the standardization processing formula is as follows:
wherein, T'iIs TiNormalized result, min (T)i) And max (T)i) Respectively is a character characteristic TiMinimum and maximum values of.
Taking the cell grain yield data in the example as an example, the cell grain yield data of material #1 was normalized to (4.92-3.37)/(6.69-3.37) ═ 0.47.
Example data after completion of data pre-processing is shown in table 2.
TABLE 2
103, for each individual, performing exponential expansion of a preset digit L on all the character characteristics so as to enable each character of the individual to obtain L expanded characteristics from the power of 1 to the power of L, and forming an expanded character characteristic set TL。
Performing index expansion on the preprocessed characteristic feature set T, wherein the character feature set T after index expansionLComprises the following steps:
TL＝{T11，T12…T1L，T21，T22…T2L…TnL}
wherein L is the maximum expansion index, TipFor a p-th power expansion of the ith personality characteristic,
the p-th power of the jth material property characteristic i;
in this embodiment, if L is 4, the cell grain yield data for material #1 is 0.47, expanded to [ 0.470.47 ]20.4730.474]I.e., [ 0.470.220.100.05]。
104. According toTLEstablishing each character and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC。
According to the expanded character feature set TLN features are changed into nL features, and for each character i and TLEstablishing matrix coupling relation of all the character characteristics to obtain a coupling relation matrix, and recording the occasional coupling relation matrix of the character i as Ri. The coupling relation represents the association relation between the features, and different coupling relations can be preset. In this embodiment, for each trait i, the extended L personality characteristics are established, and the coupling relationship between the L personality characteristics and the nL characteristics, that is, RiIs a matrix of L × nL.
The weights of different powers are preset weights from 1 power to L power, and the expanded characteristic vector is TLVector of neutral-like features, S for an individual SLRepresented as a vector of nL. Coupling relation matrix R of each character iiThe matrix is L multiplied by nL, and the weights of L expansion characteristics with different powers appear in the character characteristic vector after expansion for many times, so that an nL vector can be constructed. Based on the three, a vector of L coupling characteristics corresponding to the property i covering the coupling relationship can be constructed, for example, through matrix multiplication and other forms.
105. Based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
From trait coupled feature set TCSelecting partial coupling features, classifying, and forming the coupling feature subset T by the coupling features with the highest accuracyS. For example, 135 individuals with tags are selected, and classified according to the selected partial coupling characteristics, and the accuracy is judged by taking the experimental result r as the tag. Finally, select outCoupling feature subset T with highest accuracySThe method can be used as a basis for constructing a breeding evaluation model to carry out breeding evaluation on crops. For example, for an individual to be classified without experimental result r, the subset of coupling features T can be relied uponSAnd constructing a breeding evaluation model for classification.
The crop breeding evaluation method based on coupling expression provided in this embodiment is capable of enhancing the coupling relationship between trait features by performing exponential expansion of a preset number L on all trait features for each individual, and based on the trait coupling feature set T of each individualCAnd the experimental result is used for carrying out feature selection to obtain the coupling feature subset T with the highest classification accuracySCompared with the existing breeding evaluation technology, the method can effectively describe the coupling relation among the crop character expressions, solve the problem of bias evaluation effect caused by non-independent and same distribution of the crop character expressions, and further improve the breeding efficiency and the continuous yield of the variety.
Based on the above description of the embodiments, as an alternative embodiment, according to TLEstablishing each character and TLThe coupling relation matrix of all the character characteristics comprises: according to the expanded character feature set TLDetermining the Pearson correlation coefficient and the Kendell correlation coefficient of the L expansion characteristics of each characteristic and all the expansion characteristic characteristics respectively; and determining the coupling relation values of the L expansion characteristics of each character and all the character characteristics according to the L expansion characteristics of each character and the Pearson correlation coefficient and the Kendall correlation coefficient of all the character characteristics, and finally obtaining a coupling relation matrix.
Pearson Correlation Coefficient (Pearson Correlation Coefficient) is used to measure whether two data sets are on a line, and is used to measure the linear relation between distance variables. The Kendel correlation coefficient is a statistical value used to measure the correlation between two random variables. Determining the coupling relation value of each character characteristic and all character characteristics based on the Pearson correlation coefficient and the Kendel correlation coefficient, and strengthening the coupling relation between the character characteristics, thereby constructing an accurate character coupling characteristic set TCFurther improving the breeding efficiency and varietyThe continuous output rate.
Based on the content of the foregoing embodiment, as an optional embodiment, the determining, according to the L extended features of each trait, the pilson correlation coefficient and the kender correlation coefficient respectively associated with all trait features, a coupling relationship value of the L extended features of each trait respectively associated with all trait features includes determining according to the following formula:
C(Tip，Tjq)＝α·cor(Tip，Tjq)+(1-α)·tau(Tip，Tjq)，p、q∈(1，L)，j∈(1，n)；
wherein L is a predetermined number of bits, TipFor p-th power expansion features of the i-th trait, TjqExpanding the characteristic for the q power of the j character; c (T)ip，Tjq) Is TipAnd Tjqα is a predetermined parameter, cor (T)ip，Tjq) Is TipAnd TjqPearson's correlation coefficient of (tau, T)ip，Tjq) Is TipAnd TjqThe kendell correlation coefficient.
According to TLEstablishing each character and TLThe coupling relation matrix of all the character characteristics in the character set, the coupling relation matrix R of the character iiThe method comprises the following steps:
taking the data of the yield ratio of the cell seed yield to the hectare yield in the embodiment as an example, the pearson correlation coefficient of the two to the power of 1 is 0.54, the kender correlation coefficient is 0.39, α is 0.8, the coupling relation of the two to the power of 1 is 0.8 × 0.54+ (1-0.8) × 0.39 ═ 0.51, and the coupling relation matrix of the cell seed yield is as follows:
based on the content of the foregoing embodiment, as an optional embodiment, the determining, according to the coupling relationship matrix of each trait, the weights of the L extended features, and the vector of the trait features after the extension, the L coupling features corresponding to each trait includes determining according to the following formula:
wherein, Ti CVector representation of L coupled features as character i; sLA vector of expanded trait features for an individual s; omega is sLThe weight coefficient vector of (1) is determined by the weights of the L extended features; ri TCoupling relation matrix R as character ii⊙ is a hadamard product,
is a matrix multiplication.
Optionally, the weights of the L extended features at different powers are determined according to the inverse of the factorial of each power. For example, the weight coefficient ω may be expressed as:
in this embodiment, 15 features, the weight coefficient ω is:
the data of the examples after completion of the trait coupling representation after pretreatment are shown in table 3.
TABLE 3
Based on the above description of the embodiment, as an alternative embodiment, based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySThe method comprises the following steps:
using trait coupled feature set TCAsClassifying according to the classification attribute, and obtaining classification accuracy A according to the experimental result0(ii) a Traversing character coupling feature set TCObtaining the classification accuracy of the removed residual coupling character features and recording the maximum value of the residual coupling character features; if the maximum value is greater than A0Deleting the corresponding coupled character features in the character coupled feature set, and updating the coupled character feature set; repeatedly calculating the classification accuracy rate based on the updated coupling character feature set, and eliminating the coupling character features with higher accuracy rate using the residual coupling character features until the classification accuracy rate is not increased any more or reaches a preset number of times, so as to obtain the coupling feature subset T with the highest classification accuracy rateS。
In this embodiment, the data set T after the conversion of the coupled data is usedCAnd performing feature selection on the experimental result r to obtain a coupling feature subset TSThe method specifically comprises the following steps:
initializing a subset of coupling characteristics TS＝TS(0)＝TCThe optimum accuracy rate is A ═ A0To use TSAnd as a classification attribute, an experimental result r is used as the classification accuracy of the classifier constructed by the classification label, and the iteration step number k is 1.
In this embodiment, the coupling feature subset T is initializedS＝TS(0) For coupling the converted data set TCUsing a linear kernel SVM as a classifier using TSAs a classification attribute, the experimental result r is constructed as a classification label, and the classification accuracy is 0.91, which is the optimal accuracy a ═ a0The iteration step number k is initialized to 1.
If k is greater than nxL, the calculation is completed, TSI.e. a subset of the coupling features that are selected for the completion feature.
In this embodiment, the initialization k value is 1, the nxl value is 60, and the calculation is not completed.
Otherwise, go through TSCoupling behavior characteristic T in (k-1)i C∈TS(k-1), recording use TS(k-1)-Ti CAs a classification attribute, the experimental result r is used as a classification label structureAnd (5) the classification accuracy of the established classifier.
In this embodiment, first traverse TS(0) And recording the classification accuracy of the coupling character features after the coupling character features are removed and other coupling character features are used.
According to the calculation results of the steps, recording the coupling character characteristics T removed when the classification accuracy is highesti CUpdating the subset of coupling characteristics T selected in this stepS(k)＝TS(k-1)-Ti CAccuracy AkTo use TS(k) And (5) the classification accuracy of the constructed classifier.
In this example, the 4 th power of the standard water hectare yield is extended from T when k is 1S(0) The classification effect is the best after the medium-sized culling, and the character characteristic is
Then
If AkIf > A, then update A ═ Ak，TS＝TS(k)。
In this example A1＜A0Therefore, when k is 1, a and T are not updatedS。
And repeating the steps until the coupling characteristic selection is completed.
In this embodiment, when k is 47, a47Obtaining the maximum classification accuracy rate of 0.93, and selecting the coupled character features including<Number of plants in cell>1，<Number of plants in cell>2，<Number of plants in cell>3，<Hectare yield master control yield ratio>2，<Hectare yield master control yield ratio>3，<Hectare yield master control yield ratio>4，<Seed yield in the community>1，<Seed yield in the community>2，<Rate of empty rod>3，<Water content of seed during threshing>1，<Water content of seed during threshing>2，<Water content of seed during threshing>3，<ThreshingWater content of grains>4}。
Finally, a subset of coupling features T is usedSAnd constructing a breeding evaluation model for breeding evaluation according to the experimental result r.
In this embodiment, the selected coupling character feature subset T is usedS＝{<Number of plants in cell>1，<Number of plants in cell>2，<Number of plants in cell>3，<Hectare yield master control yield ratio>2，<Hectare yield master control yield ratio>3，<Hectare yield master control yield ratio>4，<Seed yield in the community>1，<Seed yield in the community>2，<Rate of empty rod>3，<Water content of seed during threshing>1，<Water content of seed during threshing>2，<Water content of seed during threshing>3，<Water content of seed during threshing>4And (4) constructing a breeding evaluation model for breeding evaluation according to the experimental result r, wherein the model can be used for analyzing the data of the experimental materials to be evaluated in the similar experiment and obtaining the evaluation result.
In this embodiment, 13 pieces of test data (10%) are taken as all data in an experiment to be evaluated, a data set is constructed, data preprocessing is performed, coupling relationship analysis and data conversion are performed on the preprocessed test data, and a data set T after coupling data conversion is obtainedCIt should be noted that only the selected coupling character subset T is needed to perform data preprocessing and data coupling conversionSThe relevant traits were treated and the test data for the examples after treatment are shown in Table 4.
TABLE 4
And classifying the plants by using a trained breeding evaluation model, wherein the accuracy of classification results is 0.93 compared with the real results.
In the embodiment of the invention, the coupling relation among the crop character expressions can be effectively described, and the bias of evaluation effects caused by the non-independent and same distribution of the crop character expressions is solved; the expert experience accumulated by a breeder in the crop breeding process is effectively utilized; a large amount of data information accumulated in the crop breeding process can be scientifically utilized; scientific and data-based crop breeding evaluation results can be generated; can further improve the breeding efficiency and the continuous yield of the variety.
Based on the content of the foregoing embodiment, as an alternative embodiment, the trait feature set T includes: the number of plants in a cell, the harvest area of the cell, the yield per hectare, the yield ratio of a main control, the stem rot rate, the number of harvested ears, the gray leaf spot resistance, the yield per hectare of standard water, the yield of seeds in the cell, the number of plants harvested, the resistance to the large leaf spot, the lodging rate, the empty stalk rate, the ear rot rate, the lodging rate and the water content of the seeds during threshing are exemplified in the above embodiments, and are not repeated herein.
Fig. 2 is a block diagram of a coupled representation-based crop breeding evaluation apparatus according to an embodiment of the present invention, and as shown in fig. 2, the coupled representation-based crop breeding evaluation apparatus includes: the system comprises a data set building module 201, a preprocessing module 202, a coupling relation building module 203, a coupling characteristic building module 204 and an evaluation model building module 205. The data set construction module 201 is configured to construct a crop breeding evaluation data set, where each data unit in the data set corresponds to a breeding individual, and each data unit includes a trait feature set T formed by trait performances of the breeding individual and an individual experimental result; the preprocessing module 202 is configured to preprocess all the trait feature sets T in the data set to obtain a preprocessed data set; the coupling relationship establishing module 203 is configured to perform exponential expansion of a preset number L on all the trait features of each individual, so that each trait of each individual obtains L expanded features from the power of 1 to the power of L, and an expanded trait feature set T is formedL(ii) a The coupling characteristic construction module 204 is used for constructing the module according to TLEstablishing each character i and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set according to the coupling characteristics of all charactersTC(ii) a The evaluation model construction module 205 is for T-basedCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
The device embodiment provided in the embodiments of the present invention is for implementing the above method embodiments, and for details of the process and the details, reference is made to the above method embodiments, which are not described herein again.
The crop breeding evaluation device based on coupling expression provided by the embodiment of the invention can strengthen the coupling relation among the character characteristics by performing the index expansion of the preset digit L on all the character characteristics for each breeding individual, and is based on the character coupling characteristic set T of each individualCAnd the experimental result is used for carrying out feature selection to obtain the coupling feature subset T with the highest classification accuracySCompared with the existing breeding evaluation technology, the method can effectively describe the coupling relation among the crop character expressions, solve the problem of bias evaluation effect caused by non-independent and same distribution of the crop character expressions, and further improve the breeding efficiency and the continuous yield of the variety.
Fig. 3 is a schematic entity structure diagram of an electronic device according to an embodiment of the present invention, and as shown in fig. 3, the server may include: a processor (processor)301, a communication Interface (communication Interface)302, a memory (memory)303 and a bus 304, wherein the processor 301, the communication Interface 302 and the memory 303 complete communication with each other through the bus 304. The communication interface 302 may be used for information transfer of an electronic device. Processor 301 may call logic instructions in memory 303 to perform a method comprising: constructing a crop breeding evaluation data set, wherein each data unit in the data set corresponds to a breeding individual, and each data unit comprises a trait characteristic set T formed by trait performances of the breeding individual and an individual experimental result; preprocessing all the character feature sets T in the data set to obtain a preprocessed data set; for each individual, performing exponential expansion of a preset digit L on all character characteristics so as to enable each character of the individual to obtain L1 sThe expanded characteristics from the power of the order of the power of L form an expanded characteristic set TL(ii) a According to TLEstablishing each character and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC(ii) a Based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
In addition, the logic instructions in the memory 303 may be implemented in the form of software functional units and stored in a computer readable storage medium when the logic instructions are sold or used as independent products. Based on such understanding, the technical solution of the present invention may be embodied in the form of a software product, which is stored in a storage medium and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device) to execute all or part of the steps of the above-described method embodiments of the present invention. And the aforementioned storage medium includes: a U-disk, a removable hard disk, a Read-Only Memory (ROM), a Random Access Memory (RAM), a magnetic disk or an optical disk, and other various media capable of storing program codes.
In another aspect, an embodiment of the present invention further provides a non-transitory computer-readable storage medium, on which a computer program is stored, where the computer program is implemented to perform the transmission method provided in the foregoing embodiments when executed by a processor, and for example, the method includes: constructing a crop breeding evaluation data set, wherein each data unit in the data set corresponds to a breeding individual, and each data unit comprises a trait characteristic set T formed by trait performances of the breeding individual and an individual experimental result; all the character feature sets T in the data set are processedPreprocessing to obtain a preprocessed data set; for each individual, performing exponential expansion of a preset digit L on all the character characteristics so as to enable each character of the individual to obtain L expanded characteristics from the power of 1 to the power of L to form an expanded character characteristic set TL(ii) a According to TLEstablishing each character and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC(ii) a Based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
The above-described embodiments of the apparatus are merely illustrative, and the units described as separate parts may or may not be physically separate, and the parts displayed as units may or may not be physical units, may be located in one place, or may be distributed on a plurality of network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the solution of the present embodiment. One of ordinary skill in the art can understand and implement it without inventive effort.
Through the above description of the embodiments, those skilled in the art will clearly understand that each embodiment can be implemented by software plus a necessary general hardware platform, and certainly can also be implemented by hardware. With this understanding in mind, the above-described technical solutions may be embodied in the form of a software product, which can be stored in a computer-readable storage medium, such as ROM/RAM, magnetic disk, optical disk, etc., and includes instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute the methods of the various embodiments or some parts of the embodiments.
Finally, it should be noted that: the above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; and such modifications or substitutions do not depart from the spirit and scope of the corresponding technical solutions of the embodiments of the present invention.
Claims (8)
1. A coupled representation-based crop breeding evaluation method is characterized by comprising the following steps:
constructing a crop breeding evaluation data set, wherein each data unit in the data set corresponds to a breeding individual, and each data unit comprises a trait characteristic set T formed by trait performances of the breeding individual and an individual experimental result;
preprocessing all the character feature sets T in the data set to obtain a preprocessed data set;
for each individual, performing exponential expansion of a preset digit L on all the character characteristics so as to enable each character of the individual to obtain L expanded characteristics from the power of 1 to the power of L to form an expanded character characteristic set TL；
According to TLEstablishing each character and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC；
Based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
2. The coupling-based of claim 1The method for evaluating the breeding of a crop as described above, wherein the method is characterized byLEstablishing each character and TLThe coupling relation matrix of all the character characteristics comprises:
according to the expanded character feature set TLDetermining the Pearson correlation coefficient and the Kendell correlation coefficient of the L expansion characteristics of each characteristic and all the expansion characteristic characteristics respectively;
and determining the coupling relation values of the L expansion characteristics of each character and all the character characteristics according to the L expansion characteristics of each character and the Pearson correlation coefficient and the Kendall correlation coefficient of all the character characteristics, and finally obtaining a coupling relation matrix.
3. The coupled expression-based crop breeding evaluation method of claim 2, wherein the determining the coupling relationship values of the L extended features of each trait with all trait features respectively according to the Pearson correlation coefficient and Kendall correlation coefficient of the L extended features of each trait with all trait features respectively comprises determining according to the following formula:
C(Tip，Tjq)＝α·cor(Tip，Tjq)+(1-α)·tau(Tip，Tjq)，p、q∈(1，L)，j∈(1，n)；
wherein L is a predetermined number of bits, TipFor p-th power expansion features of the i-th trait, TjqExpanding the characteristic for the q power of the j character; c (T)ip，Tjq) Is TipAnd Tjqα is a predetermined parameter, cor (T)ip，Tjq) Is TipAnd TjqPearson's correlation coefficient of (tau, T)ip，Tjq) Is TipAnd TjqThe kendell correlation coefficient.
4. The coupled expression-based crop breeding evaluation method of claim 1, wherein the determining of the L coupled features corresponding to each trait according to the coupled relation matrix of each trait, the weights of the L extended features with different powers and the vector of the augmented trait features comprises determining according to the following formula:
wherein, Ti CVector representation of L coupled features as character i; sLA vector of expanded trait features for an individual s; omega is sLThe weight coefficient vector of (1) is determined by the weights of the L extended features; ri TCoupling relation matrix R as character ii⊙ is a hadamard product,
is a matrix multiplication.
5. The coupled representation-based crop breeding evaluation method of claim 1, wherein the T-based isCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySThe method comprises the following steps:
using trait coupled feature set TCClassifying as classification attribute, and obtaining classification accuracy A according to experimental result0；
Traversing character coupling feature set TCObtaining the classification accuracy of the removed residual coupling character features and recording the maximum value of the residual coupling character features;
if the maximum value is greater than A0Deleting the corresponding coupled character features in the character coupled feature set, and updating the coupled character feature set;
repeatedly calculating the classification accuracy rate based on the updated coupling character feature set, and eliminating the coupling character features which enable the accuracy rate of the residual coupling character features to be larger until the classification accuracy rate is not increased any more or reaches a preset number of times, so as to obtain the coupling feature subset T with the highest classification accuracy rateS。
6. A coupled representation-based crop breeding evaluation device is characterized by comprising:
the data set construction module is used for constructing a crop breeding evaluation data set, each data unit in the data set corresponds to a breeding individual, and each data unit comprises a trait characteristic set T formed by trait performances of the breeding individual and an individual experiment result;
the preprocessing module is used for preprocessing all the character feature sets T in the data set to obtain a preprocessed data set;
a coupling relation establishing module for performing exponential expansion of preset digits L on all the character characteristics of each individual so that each character of the individual obtains L expanded characteristics from the power of 1 to the power of L to form an expanded character characteristic set TL；
A coupling characteristic constructing module for constructing a coupling characteristic according to TLEstablishing each character i and TLDetermining L coupling characteristics corresponding to each character according to the coupling relationship matrix of each character, the weights of different powers of L expansion characteristics and the vector of the expanded character characteristics, and constructing a character coupling characteristic set T according to the coupling characteristics of all charactersC；
An evaluation model construction module for constructing an evaluation model based on TCAnd selecting the coupling characteristics by taking the experimental result as a label to obtain a coupling characteristic subset T with the highest classification accuracySUsing said subset of coupling features TSAnd constructing a breeding evaluation model for breeding evaluation.
7. An electronic device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, wherein the processor when executing the program performs the steps of the method for coupled representation-based crop breeding assessment according to any of claims 1 to 5.
8. A non-transitory computer readable storage medium, on which a computer program is stored, which, when being executed by a processor, performs the steps of the method for crop breeding evaluation based on coupled representations according to any one of claims 1 to 5.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010130054.5A CN111260259B (en) | 2020-02-28 | 2020-02-28 | Crop breeding evaluation method and device based on coupling representation |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010130054.5A CN111260259B (en) | 2020-02-28 | 2020-02-28 | Crop breeding evaluation method and device based on coupling representation |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111260259A true CN111260259A (en) | 2020-06-09 |
| CN111260259B CN111260259B (en) | 2023-06-30 |
Family
ID=70951498
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010130054.5A Active CN111260259B (en) | 2020-02-28 | 2020-02-28 | Crop breeding evaluation method and device based on coupling representation |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111260259B (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325355A1 (en) * | 2012-05-30 | 2013-12-05 | Agrigenetics, Inc. | Multivariate Genetic Evaluation Of Maize For Grain Yield And Moisture Content |
| CN104572900A (en) * | 2014-12-25 | 2015-04-29 | 北京农业信息技术研究中心 | Trait characteristic selection method for crop breeding evaluation |
| CN104951987A (en) * | 2015-06-19 | 2015-09-30 | 北京农业信息技术研究中心 | Decision tree based crop breeding evaluation method |
| CN110487975A (en) * | 2019-08-28 | 2019-11-22 | 上海市农业科学院 | A kind of measuring method and its evaluation method of mushroom comprehensive nutrient quality |
-
2020
- 2020-02-28 CN CN202010130054.5A patent/CN111260259B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20130325355A1 (en) * | 2012-05-30 | 2013-12-05 | Agrigenetics, Inc. | Multivariate Genetic Evaluation Of Maize For Grain Yield And Moisture Content |
| CN104572900A (en) * | 2014-12-25 | 2015-04-29 | 北京农业信息技术研究中心 | Trait characteristic selection method for crop breeding evaluation |
| CN104951987A (en) * | 2015-06-19 | 2015-09-30 | 北京农业信息技术研究中心 | Decision tree based crop breeding evaluation method |
| CN110487975A (en) * | 2019-08-28 | 2019-11-22 | 上海市农业科学院 | A kind of measuring method and its evaluation method of mushroom comprehensive nutrient quality |
Non-Patent Citations (1)
| Title |
|---|
| 邹永潘;王儒敬;李伟;: "随机森林算法在小麦育种辅助评价中的应用", 计算机***应用 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111260259B (en) | 2023-06-30 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11663493B2 (en) | Method and system of dynamic model selection for time series forecasting | |
| US11222385B2 (en) | Method and system for forecasting crop yield | |
| CN111696101A (en) | Light-weight solanaceae disease identification method based on SE-Inception | |
| CN107563645A (en) | A kind of Financial Risk Analysis method based on big data | |
| CN109272202A (en) | A kind of enterprise credit risk method and system based on convolutional neural networks | |
| CN109214503B (en) | Power transmission and transformation project cost prediction method based on KPCA-LA-RBM | |
| Chakrabarty | A regression approach to distribution and trend analysis of quarterly foreign tourist arrivals in India | |
| CN112232387B (en) | Effective characteristic identification method for disease symptoms of grain crops based on LSELM-RFE | |
| CN113344615A (en) | Marketing activity prediction method based on GBDT and DL fusion model | |
| CN113221913A (en) | Agriculture and forestry disease and pest fine-grained identification method and device based on Gaussian probability decision-level fusion | |
| CN115018357A (en) | Farmer portrait construction method and system for production performance improvement | |
| Panigrahi et al. | Normalize time series and forecast using evolutionary neural network | |
| CN113450141B (en) | Intelligent prediction method and device based on electricity sales quantity characteristics of large power customer group | |
| Balasubramaniyan et al. | Color contour texture based peanut classification using deep spread spectral features classification model for assortment identification | |
| CN117557265A (en) | Block chain transaction behavior prediction method based on graphic neural network | |
| CN111260259B (en) | Crop breeding evaluation method and device based on coupling representation | |
| CN110458438A (en) | The calculation method and device of the impact factor of vegetation water use efficiency WUE | |
| CN114004513B (en) | Demand prediction method, system and storage medium | |
| CN111753992A (en) | Screening method and screening system | |
| Berger et al. | Combining machine learning and simulation modelling for better predictions of crop yield and farmer income | |
| Zha et al. | A hierarchical reinforcement learning framework for stock selection and portfolio | |
| CN109255370B (en) | Intelligent farmland pesticide spraying method based on PAUC algorithm | |
| Lin | Improvement on behavior scores by dual-model scoring system | |
| Zadeh | A New Sales Forecasting method for industrial supply chain | |
| CN116862654A (en) | Financial wind control method, device, equipment and medium for agriculture and animal husbandry supply chain |
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 |