CN115392582A - Crop yield prediction method based on incremental fuzzy rough set attribute reduction - Google Patents
Crop yield prediction method based on incremental fuzzy rough set attribute reduction Download PDFInfo
- Publication number
- CN115392582A CN115392582A CN202211066091.XA CN202211066091A CN115392582A CN 115392582 A CN115392582 A CN 115392582A CN 202211066091 A CN202211066091 A CN 202211066091A CN 115392582 A CN115392582 A CN 115392582A
- Authority
- CN
- China
- Prior art keywords
- crop
- subset
- fuzzy
- attribute
- crop yield
- 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
- 230000009467 reduction Effects 0.000 title claims abstract description 212
- 238000000034 method Methods 0.000 title claims abstract description 45
- 230000012010 growth Effects 0.000 claims abstract description 271
- 238000004590 computer program Methods 0.000 claims description 17
- 238000010606 normalization Methods 0.000 claims description 6
- 238000012216 screening Methods 0.000 claims description 5
- 238000012545 processing Methods 0.000 claims description 4
- 238000010276 construction Methods 0.000 claims description 2
- 238000012797 qualification Methods 0.000 abstract 1
- 238000004364 calculation method Methods 0.000 description 40
- 238000004422 calculation algorithm Methods 0.000 description 11
- 238000003860 storage Methods 0.000 description 8
- 230000008569 process Effects 0.000 description 6
- 238000004891 communication Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 230000006870 function Effects 0.000 description 3
- 230000003287 optical effect Effects 0.000 description 3
- 230000008635 plant growth Effects 0.000 description 3
- 230000007774 longterm Effects 0.000 description 2
- 239000000126 substance Substances 0.000 description 2
- 230000001133 acceleration Effects 0.000 description 1
- 238000012271 agricultural production Methods 0.000 description 1
- 238000004458 analytical method Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 150000001875 compounds Chemical class 0.000 description 1
- 230000003750 conditioning effect Effects 0.000 description 1
- 238000013500 data storage Methods 0.000 description 1
- 238000003066 decision tree Methods 0.000 description 1
- 238000010801 machine learning 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
- 238000012544 monitoring process Methods 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 238000007637 random forest analysis Methods 0.000 description 1
- 239000004065 semiconductor Substances 0.000 description 1
- 239000002689 soil Substances 0.000 description 1
- 239000007787 solid Substances 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000012706 support-vector machine 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
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- 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)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Theoretical Computer Science (AREA)
- Marketing (AREA)
- General Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- Tourism & Hospitality (AREA)
- Animal Husbandry (AREA)
- Life Sciences & Earth Sciences (AREA)
- Agronomy & Crop Science (AREA)
- Mining & Mineral Resources (AREA)
- General Health & Medical Sciences (AREA)
- Marine Sciences & Fisheries (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The application provides a crop yield prediction method based on incremental fuzzy rough set attribute reduction. The method comprises the following steps: constructing a decision table; inputting a crop growth record data subset serving as an original data subset into a fuzzy rough set attribute reduction model; calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data and the weighted consistency degree of each crop growth record to obtain a crop growth record subset with the weighted consistency degree and the qualification; calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset, and performing attribute reduction to obtain a reduced attribute subset; and taking the rest crop growth record data subsets as incremental data subsets, sequentially inputting the incremental data subsets into a fuzzy rough set attribute reduction model for attribute reduction to obtain a plurality of non-redundant reduction attribute subsets, and training to obtain a crop yield prediction model. The method and the device can improve the crop yield prediction precision and reduce the technical cost at the same time.
Description
Technical Field
The application relates to the technical field of crop yield prediction, in particular to a crop yield prediction method based on increment fuzzy rough set attribute reduction.
Background
China is a big agricultural country, grain production is the basic guarantee for ensuring the high-speed development of economy, and the change of grain yield directly influences the development stability of national economy. At present, with the rapid development of remote sensing technology, the remote sensing technology is widely applied to agricultural production, and an effective way is provided for monitoring the growth vigor of crops and predicting the yield of grains. The existing method for predicting crop yield based on remote sensing technology can directly input all preprocessed multi-source remote sensing data into a machine learning model to analyze the crop yield, the number of crop yield analysis indexes can reach hundreds, and the redundant indexes can seriously increase the technical cost of data acquisition and the time cost of calculation. Therefore, it is crucial to select as few indicators as possible for crop yield prediction while maintaining high classification accuracy.
Disclosure of Invention
The embodiment of the application provides a crop yield prediction method based on increment fuzzy rough set attribute reduction, which is used for solving the technical problem of high technical cost of the conventional crop yield prediction method.
In a first aspect, an embodiment of the present application provides a crop yield prediction method based on incremental fuzzy rough set attribute reduction, including:
step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with the same size according to the decision table;
and step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
and step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
step S7: and (3) sequentially inputting the remaining crop growth record data subsets serving as incremental data subsets into the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
In one embodiment, the obtaining of the crop growth record data, the crop yield index data, and the crop yield grade data, and the constructing of the decision table include:
acquiring crop growth record data, and clustering the crop growth record data according to crop yield to obtain crop yield grade data;
performing normalization processing on the crop yield index value of the crop growth record data to obtain crop yield index data;
and constructing a decision table DT = (U, C $) according to the crop growth record data, the crop yield index data and the crop yield grade data, wherein DT represents the decision table, U represents a crop growth record set, C represents a crop yield index set, and D represents a crop yield grade set.
In an embodiment, the calculating, by the fuzzy rough set attribute reduction model, a fuzzy similarity of each crop growth record in the original data subset under the crop yield index data, calculating a weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating crop growth records in the original data subset with a poor weighted consistency degree to obtain a crop growth record subset with a good weighted consistency degree, includes:
calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model to obtain a fuzzy set;
sorting crop growth records in the fuzzy set according to the fuzzy similarity to obtain a weighted fuzzy set;
according to the weighted fuzzy set, calculating the weighted consistency degree of each crop growth record in the original data subset with the crop yield grade under the crop yield index data;
and removing the crop growth records with the unqualified weighted consistency degree in the original data subset according to the weighted consistency degree to obtain the crop growth record subset with the qualified weighted consistency degree.
In an embodiment, the calculating, by the fuzzy rough set attribute reduction model, a fuzzy similarity of each crop growth record in the raw data subset under the crop yield index data, calculating a weighted consistency degree of each crop growth record in the raw data subset according to the fuzzy similarity, and eliminating the crop growth records in the raw data subset with the weighted consistency degree that is not good, to obtain the crop growth record subset with the weighted consistency degree that is good, further includes:
and calculating the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data according to the fuzzy similarity of each crop growth record under the crop yield index data in the original data subset.
In one embodiment, the calculating the weighted consistency degree and the crop yield index importance of the ranked subset of crop growth records according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset includes:
initializing an original reduction attribute set;
calculating the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the original reduction attribute set according to the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data to obtain an updated crop growth record subset;
according to the weighted consistency degree and the fuzzy positive area of the qualified crop growth record subset under the original reduction attribute set, calculating the importance degree of the crop yield index of the updated crop growth record subset;
and according to the importance of the crop yield index, performing attribute reduction on the crop yield index until a stopping condition is reached to obtain a reduced attribute subset.
In one embodiment, the performing redundancy check on the reduced attribute subset to obtain a non-redundant reduced attribute subset includes:
screening out redundant attributes from the reduced attribute subset according to a redundant check condition;
and removing the redundant attribute from the reduction attribute subset to obtain a non-redundant reduction attribute subset.
In one embodiment, the redundancy check condition is specifically:
and when the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data is larger than zero, and the crop yield index importance of one of the reduced attributes after being removed from the reduced attribute subset is equal to the crop yield index importance of the crop yield index data, judging that the removed reduced attribute is a redundant attribute.
In a second aspect, an embodiment of the present application provides a crop yield prediction apparatus based on incremental fuzzy rough set attribute reduction, including:
a decision table construction module for executing the step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
a crop growth record data dividing module for executing the step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with equal sizes according to the decision table;
a first input module, configured to execute step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
a crop growth record removing module for executing the step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
an attribute reduction module for executing step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
a redundancy check module for performing step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
a loop module for executing step S7: and (3) sequentially inputting the remaining crop growth record data subsets serving as incremental data subsets into the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
In a third aspect, an embodiment of the present application provides an electronic device, which includes a processor and a memory storing a computer program, where the processor, when executing the program, implements the crop yield prediction method based on incremental fuzzy rough set attribute reduction according to the first aspect.
In a fourth aspect, embodiments of the present application provide a computer program product, which includes a computer program, and when the computer program is executed by a processor, the method for predicting crop yield based on incremental fuzzy rough set attribute reduction according to the first aspect is implemented.
According to the crop yield prediction method based on incremental fuzzy rough set attribute reduction, the crop growth record data are divided into a plurality of crop growth record data subsets with equal sizes by constructing the decision table, so that the data volume of attribute reduction in each time can be reduced, the technical difficulty is reduced, and the calculation time is shortened; when the attribute reduction is carried out, one crop growth record data subset is used as an original data subset and is input into the fuzzy rough set attribute reduction model for carrying out the first attribute reduction, the rest crop growth record data subsets are used as incremental data subsets and are sequentially input into the fuzzy rough set attribute reduction model, the original data subset is updated and then the next attribute reduction is carried out until the incremental data subset is empty, the technical difficulty in the calculation process is simplified, the calculation efficiency is improved, meanwhile, a more accurate attribute reduction result can be obtained, and the accuracy of a crop yield prediction model is favorably improved; and carrying out redundancy check on the reduced attribute subset after each attribute reduction, and under the condition that the incremental data subsets are continuously increased to carry out attribute reduction calculation, ensuring that a simplified non-redundant reduced attribute subset is obtained, thereby ensuring the long-term effectiveness and reliability of the algorithm in a dynamic environment.
Drawings
In order to more clearly illustrate the technical solutions in the present application or the prior art, the drawings needed for the description of the embodiments or the prior art will be briefly introduced below, and it is obvious that the drawings in the following description are some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings based on these drawings without creative efforts.
FIG. 1 is a schematic flow chart of a crop yield prediction method based on incremental fuzzy rough set attribute reduction according to an embodiment of the present application;
FIG. 2 is a schematic structural diagram of a crop yield prediction apparatus based on incremental fuzzy rough set attribute reduction according to an embodiment of the present application;
fig. 3 is a schematic structural diagram of an electronic device provided in an embodiment of the present application.
Detailed Description
In order to make the objects, technical solutions and advantages of the present application clearer, the technical solutions of the present application will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present application, and it is obvious that the described embodiments are some, but not all embodiments of the present application. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present application.
Fig. 1 is a schematic flowchart of a crop yield prediction method based on incremental fuzzy rough set attribute reduction according to an embodiment of the present application. Referring to fig. 1, an embodiment of the present application provides a crop yield prediction method based on incremental fuzzy rough set attribute reduction, which may include:
step S1: obtaining crop growth record data U, crop yield index data C and crop yield grade data D, constructing a decision table DT = (U, C $ D) and giving a fuzzy equivalence relation
And a fuzzy similarity threshold α;
step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with the same size according to the decision table (in the two cases, the time complexity of the algorithm is very high, (1) if the existing data set is very large, the large data set needs to be divided into small data sets for calculation in an incremental mode, and the problem that the calculation cannot be performed due to insufficient hardware conditions is avoided, (2) if the data is streaming data which dynamically increases along with time, the new data set performs incremental calculation on the original data set result in an incremental mode);
and step S3: inputting one of a plurality of crop growth record data subsets as an original data subset into a fuzzy equivalence relation based on a decision table DT
A fuzzy rough set attribute reduction model constructed by the fuzzy similarity threshold value alpha;
and step S4: calculating the original data subset U through the fuzzy rough set attribute reduction model k The growth of each crop is recorded in the crop yield index data DT = (U, C $ D) C = { a = (a, a = (b) } 1 ,a 2 ,...,a m The fuzzy similarity under the condition is ranked, the weighted consistency degree of the crop growth record is calculated according to the fuzzy similarity, a consistency degree threshold eta is set, and the original data subset U is subjected to weighted consistency degree k Set of crop growth records divided into weighted consistency degrees less than eta
Set of crop growth records weighted for consistency (greater than or equal to η)
Rejecting crop growth record sets with a poor weighted consistency
Step S5: calculating a set of weighted consistency degrees and qualified crop growth records according to the decision table
According to the importance of the crop yield index, performing attribute reduction on the crop yield index according to the importance of the crop yield index, and selecting the optimal crop yield index until a stopping condition is met to obtain a reduced attribute subset red';
step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset red';
step S7: the remaining crop growth record data subset U k+1 And sequentially inputting the fuzzy rough set attribute reduction model as an incremental data subset, updating the original data subset, repeating the steps S4 to S6 by using the updated original data subset to obtain a non-redundant reduction attribute subset red', and inputting the non-redundant reduction attribute set into a classifier model to train and obtain a crop yield prediction model for predicting crop yield.
It should be noted that the executing subject of the crop yield prediction method based on incremental fuzzy rough set attribute reduction provided by the embodiment of the present application may be any network-side device, such as a crop yield prediction system, and the like.
In step S1, the network side device obtains crop growth record data U, crop yield index data C, and crop yield grade data D, constructs a decision table DT = (U, C $ D), and gives a fuzzy equivalence relation
And a blur similarity threshold α.
It should be noted that, in order to evaluate the crop yield according to the existing data, a decision table DT = (U, C $ D) may be defined, where U is a universe and is a set of non-empty finite crop growth records, C is a set of non-empty finite crop yield indicators (attributes), and D represents a crop yield level. Re-determining fuzzy equivalence relations
Each conditional attribute a e C can define a fuzzy relationship
Thus arbitrary subsets of attributes
Correspond to the fuzzy relation
Similarly, the fuzzy relation corresponding to the attribute set C is
Let U = { x = { [ x ] 1 ,x 2 ,...,x n Is a set of real values with n records of crop growth, C = { a } 1 ,a 2 ,...,a m The method is characterized in that the method is a crop yield index set of a crop fuzzy information system and mainly comprises m crop yield indexes, such as a vegetation index, a red edge index, a soil conditioning vegetation index, an enhanced vegetation index, an atmospheric resistance index, a greenness vegetation index, a desertification vulnerability index, a green ratio vegetation index, a spectrum index and the like. D = { D = 1 ,d 2 ,...,d r Is the r crop yield ratings of the decision table. Let us divide the decision of U into U/D = { [ x { [ X ]] D :x∈U}，[x] D D (x) = D (y) }, D is a decision class of crop growth record x, [ x ∈ U: D (x) = D (y) }, D is a decision class of crop growth record x] D Is defined as a degree of membership of
Where y ∈ U. [ x ] of] D D (x) = D (y) } represents a set of objects for which x is at the crop yield level (if the decision attribute of the object is the same as x, it belongs to the set, otherwise it does not belong to the set). Fuzzy equivalence relation
Generating a fuzzy partition on the U
Is a fuzzy set on U. Any y ∈ U, y for
Degree of membership of
Given α ∈ [0,1]，
Is a-level common set of
Is the alpha-level fuzzy equivalence class of x. Wherein the content of the first and second substances,
in one embodiment, S1 may include:
acquiring crop growth record data, and clustering the crop growth record data according to crop yield to obtain crop yield grade data;
performing normalization processing on the crop yield index value of the crop growth record data to obtain crop yield index data;
according to the crop growth record data, the crop yield index data and the crop yield grade data, a decision table DT = (U, C U D) is constructed, wherein DT represents a fuzzy decision table, U represents a crop growth record set, C represents a crop yield index set, D represents a crop yield grade set, and a fuzzy equivalence relation is given
And a blur similarity threshold α.
It should be noted that the obtained data may be multi-source remote sensing data, and the network-side device may cluster the crop growth record data according to the crop yield by using a K-means (K mean) clustering algorithm, that is, divide the crop growth record data into r yield grades D = { D } according to the crop yield 1 ,d 2 ,...,d r }。
It should be noted that, for each crop yield index a e C, the network side device may have a value range of the crop yield index a [ a ∈ C ] - ,a + ]Then each stripRecorded crop yield index a (x) for crop growth i ) The normalization can be performed by the following formula (1).
Wherein, a (x) i ) Indicates a crop yield index value, a' (x) i ) Represents the normalized crop yield index value, a' (x) i )∈[0,1]U denotes the set of crop growth records, x i Represents the record of crop growth. In the case of dynamic streaming data, the threshold value of the crop yield index of the newly added data set must be in the historical value range [ a ] - ,a + ]And if not, the historical data is reintegrated for calculation.
The network side equipment can obtain real-value data of multi-source remote sensing through normalization, data information quantity is reserved, information loss needing discretization is avoided, and reliability and dependence of crop yield estimation of a small quantity of crop yield index results are guaranteed.
For the sake of notation, the following a indicates the normalized crop yield index.
In step S2, the network side device divides the crop growth record data into a plurality of crop growth record data subsets of equal size according to the decision table.
The method is suitable for two situations, and the time complexity of the fuzzy rough set attribute reduction algorithm is very high: (1) If the existing data set is very large, the large data set needs to be divided into small data sets for calculation, and the small data sets are calculated in an incremental mode, so that the problem that the calculation cannot be performed due to insufficient hardware conditions is solved; (2) If the data is streaming data which is dynamically increased along with the time, the new data set is incrementally calculated on the original data set. In order to ensure the algorithm calculation to be smooth and improve the calculation efficiency, the crop growth record data can be divided into a plurality of crop growth record data subsets according to the actual situation.
It should be noted that the network side device may divide the crop growth record set U into t parts according to the actual situation, so as to make the crop growth record dataRandomly dividing the plant growth record data into t plant growth record data subsets with equal size, and using the t plant growth record data subsets to form a plant sample subset sequence U = { U = { (U) } 1 ,U 2 ,...,U t }. If the crop growth record data volume is too large, a mode of dividing a plurality of data can be adopted, and the running cost of a computer is effectively reduced, so that large-scale calculation can be performed, and if the crop growth record data volume is less, division can be not needed, and calculation can be directly performed.
In step S3, the network side device will input one of the crop growth record data subsets as an original data subset into the fuzzy equivalence relation based on the decision table DT
And a fuzzy rough set attribute reduction model constructed by the fuzzy similarity threshold alpha.
When attribute reduction is carried out subsequently, one crop growth record data subset is used as an original data subset and input into the fuzzy rough set attribute reduction model for carrying out first attribute reduction, the rest crop growth record data subsets are used as incremental data subsets and input into the fuzzy rough set attribute reduction model in sequence, the original data subsets are updated, and then attribute reduction is carried out next time until the incremental data subsets are null, so that the technical difficulty in the calculation process is simplified, the calculation efficiency is improved, a more accurate attribute reduction result can be obtained, and the accuracy of the crop yield prediction model is improved.
In step S4, the network side device may calculate the original data subset U through the fuzzy rough set attribute reduction model k Wherein each crop growth record in the crop yield index data C = { a = 1 ,a 2 ,...,a m And sorting the fuzzy similarity under the points. Setting a weighted consistency degree threshold eta, calculating the weighted consistency degree of crop growth records according to the fuzzy similarity, and performing primary data subset U according to the weighted consistency degree k Set of crop growth records partitioned into weighted consistency degrees of failure
Set of crop growth records weighted for consistency
Rejecting sets of crop growth records with a poor weighted consistency
According to the invention, the crop growth records with the unqualified weighting consistency degree in the original data subset are removed through the fuzzy rough set attribute reduction model and the fuzzy rough set attribute reduction algorithm, so that the calculation of interference data is effectively avoided, the calculation cost is reduced, and the convenience of the fuzzy rough set attribute reduction algorithm in the actual application process is ensured.
In one embodiment, S4 may include:
calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model to obtain a fuzzy set;
sorting crop growth records in the fuzzy set according to the fuzzy similarity to obtain a weighted fuzzy set;
according to the weighted fuzzy set, calculating the weighted consistency degree of each crop growth record in the original data subset with the crop yield grade under the crop yield index data;
removing the crop growth records with the unqualified weighted consistency degree in the original data subset according to the weighted consistency degree to obtain a crop growth record subset with the qualified weighted consistency degree;
and calculating the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data according to the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data.
It should be noted that, the network side device may calculate the original data subset (crop sample subset) U first by using equations (2) and (3) k Growth of every crop in the seedRecord x i C = { a) under crop yield index data 1 ,a 2 ,...,a m The fuzzy similarity of the points is obtained to obtain a fuzzy set
In the formula, x i 、x j Representing the original data subset U k A (x) of j ) Representing the normalized crop yield index value,
x under the crop yield index a i And x j The fuzzy relation between the two or more of the above-mentioned components,
denotes x under the overall crop yield index C i And x j The fuzzy similarity between them, theta, represents a calculation parameter.
After obtaining the fuzzy set, the network side device can record x according to the crop growth i In fuzzy sets
Fuzzy similarity in (1), record of crop growth x i In fuzzy sets
The similarity in the data is sorted from big to small, and the network side equipment can calculate the original data subset U by the formula (4) k Record of growth per crop in x i Degree of weighted agreement with crop yield rating D under all crop yield indicators C
Wherein the content of the first and second substances,
denotes crop growth record x i The degree of consistency with the weight w,
the calculation is mainly performed by the fuzzy sets
The fuzzy similarity of each member in the group is subjected to descending order calculation to form ordinal numbers {1,2,3, …, n }, when the ordinal numbers are equal to the ordinal numbers {1,2,3, …, n }, the fuzzy similarity of each member in the group is subjected to descending order calculation, and the ordinal numbers are subjected to descending order calculation to form ordinal numbers {1,2,3, …, n }, when the fuzzy similarity of each member in the group is subjected to descending order calculation
The ordinal number of (1) is w, then w j And (k) =1/k. Setting a weighted consistency degree threshold eta, and weighting the size of the consistency degree to enable the original data subset U k Set of crop growth records partitioned into weighted consistency degrees of failure
Set of crop growth records weighted for consistency
Rejecting sets of crop growth records with a poor weighted consistency
Obtaining a set of crop growth records weighted for consistency
When in use
Is less than a predetermined threshold eta (e.g. 0.9), the crop growth record x is determined i The crop growth records with the lower weighted consistency degree are removed from the original data subset according to the weighted consistency degree to obtain a crop growth record U 'with the lower weighted consistency degree' k . The removed crop growth records do not participate in the subsequent attribute reduction step, so that the calculation of some inconsistent samples is effectively reduced, and the calculation efficiency and precision are improved.
Further, the subset U 'of crop growth records with weighted consistency degrees qualified is obtained' k Later, the network side device may be based on fuzzy sets
Dividing the weighted consistency degree and the qualified crop growth record subset U 'according to the upper and lower approximate expression (5)' k Fuzzy positive area under all crop yield index C
In the formula (I), the compound is shown in the specification,
inside is provided with
To represent
All the similarity in the interior is less than or equal to [ x ] i ] D I.e. by
Inside is provided with
Representing two fuzzy sets
Wherein the empty set in the fuzzy set is
0/x n Is a zade notation of fuzzy set, representing x n Has a fuzzy degree of membership of 0, [ x ] i ] D Denotes x i A set of objects at a crop yield level (belonging to the set if the decision attribute of the object is the same as x, otherwise not belonging to the set),
represents satisfaction
All x of this condition i Set of (2), U' k Subset of crop growth records, x, representing weighted degrees of uniformity i Denotes crop growth record, D denotes crop yield rating,
crop growth record subset U 'representing weighted degree of consistency and lattice' k Fuzzy positive areas under all crop yield indicators C.
In step S5, the network-side device calculates a weighted consistency degree and a qualified subset U 'of crop growth records according to the decision table' k The importance Sig of the crop yield index α (a, red, D, U'), a belongs to C, and the crop yield index is calculated according to the importance degree of the crop yield indexAnd (5) line attribute reduction, selecting the optimal crop yield index a belongs to C until a stopping condition is met, and obtaining a reduced attribute subset red'.
In one embodiment, S5 may include:
initializing an original reduction attribute set;
subset U 'of crop growth records based on weighted degree of consistency and lattice' k Calculating weighted consistency degrees and ranked crop growth record subsets U 'under all crop yield indicators C' k Obtaining an updated crop growth record subset in a fuzzy positive area under the original reduction attribute set;
subset U 'of crop growth records based on weighted degree of consistency and lattice' k Calculating weighted consistency degrees and ranked crop growth record subsets U 'under all crop yield indicators C' k The importance Sig of the crop yield index α (a,red,D,U′),a∈C；
And (4) according to the importance of the crop yield indexes, performing attribute reduction on the crop yield indexes, selecting the optimal crop yield indexes a, belonging to the element C, until a stopping condition is reached, and obtaining a reduced attribute subset red'.
It should be noted that, the network side device may initialize an original reduction attribute set red = { } (red is an original reduction set representing a crop yield index, the reduction set of the crop yield index is empty, and then important indexes are continuously selected, so that the indexes are continuously increased. And then according to the original reduction attribute set red and the weighted consistency degree and the qualified crop growth record subset U' k Fuzzy positive area under all crop yield index C
Obtaining weighted consistency degree and qualified crop growth record subset U 'through formula (7)' k Fuzzy positive region under original reduced attribute set red
Obtaining updated crop growth record subsets
Is from U's' k ×U′ k Reduced to U * ×U′ k 。
The principle of the formula (7) is the same as that of the formula (5), wherein,
inside is provided with
To represent
All the membership degrees of each row are less than or equal to [ x ] i ] D I.e. by
Inside is provided with
Representing two fuzzy sets
In which the space in the collection is blurredIs collected as
0/x n Is a Zade notation of fuzzy set, representing x n Has a fuzzy degree of membership of 0, [ x ] i ] D Denotes x i The set of objects at the crop level are,
represents satisfaction
All x of this condition i The set of (a) and (b),
represents satisfaction
All x of this condition i Set of (2), U' k Set of crop growth records, x, representing weighted degrees of consistency i Denotes crop growth record, D denotes crop yield rating,
crop growth record subset U 'representing weighted degree of consistency and lattice' k The fuzzy positive area under the original reduced attribute set red.
Further, the network side equipment can select each crop yield index a e B, and calculate and update the crop growth record subset U through the formula (9) * The importance Sig of the crop yield index α (a,red,D,U * )。
In the formula Sig α (a,red,D,U * ) Representing updated crop growth record subset U * Of the crop yield index importance, gamma α (red∪{a},D,U * ) Representing current based update operationsSubset of growth records U * Deterministic metric function, γ, under a given set of attributes red { [ a } α (red,D,U * ) Representing a subset U of updated crop growth records based on current * Deterministic metric function, x, under a given set of attributes red i The record of the growth of the crop is shown,
denotes x i The set of fuzzy membership under red @, [ x ] of i ] D Denotes x i Set of objects (crop growth records) at the crop level,
denotes x i The set of fuzzy membership under red,
denotes x i Fuzzy similarity (fuzzy membership) in the set of fuzzy membership under red ^ a, [ x ^ b i ] D (x j ) Denotes 0 or 1,x i And x j The same crop grade is 1, otherwise, the grade is 0,
denotes x i Fuzzy similarity (fuzzy membership) in the set of fuzzy membership under red.
The network side device may continuously select an optimal crop yield index, for example, the crop yield index with the highest importance of the crop yield index is subjected to attribute reduction through equations (10) - (12), so as to update the crop yield index set and the original reduction attribute set.
Sig α (a*,red,D,U * )＝max{Sig α (a k ,red,D,U * ),a k ∈B}(10),
B＝B-{a*}(11),
red＝red∪a*(12),
In the formula, a denotes a crop yield index (attribute) with the most important crop yield index (sig maximum), and red denotes a crop yield indexThe original reduction set of the target, the reduction set of the crop yield index at the beginning is empty, and important indexes are continuously selected later, so that the reduction set is continuously increased. B is initialized to be all crop yield indexes C, and each time one index a belongs to C and enters red, B needs to delete a, so that red U.B = C. D denotes the crop yield rating, U * Representing the updated subset of crop growth records, B 'representing the updated set of crop yield indicators, red' representing the updated set of original reduction attributes.
In the process of attribute reduction, it is necessary to determine whether a stop condition is reached to obtain a final reduced attribute subset. Different stop conditions are used for different situations.
When in use
Then, the stop condition 1:
Sig α (a,red,D,U * ) δ ≦ δ, δ =0.005, wherein Sig α (a,red,D,U * ) And delta represents a first preset parameter which can be adjusted according to the actual condition.
When in use
Then, stop condition 2 is adopted:
wherein
Representing a subset of records based on current crop growth
A deterministic metric function under a given set of attributes red { [ a },
representing the record of crop growth entering a fuzzy positive area under the full set of crop yield indicators C, i.e.
Denotes x i Set of fuzzy membership under red, [ x ] i ] D Denotes x i Set of objects (crop growth records) at crop level, phi denotes a second preset parameter phi = [0,1 =]The current algorithm may take 0.95 depending on the actual adjustment.
If the fuzzy rough set attribute reduction algorithm reaches the stop condition, stopping selecting the optimal crop index, ending the attribute reduction step, otherwise, continuously selecting the optimal index until the stop condition is reached or
Until now.
In step S6, the network side device performs redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset.
In one embodiment, S6 may include:
screening out redundant attributes from the reduced attribute subset according to a redundant check condition;
and removing the redundant attribute from the reduction attribute subset to obtain a non-redundant reduction attribute subset.
It should be noted that the redundancy check condition specifically includes:
fuzzy positive area of the subset of crop growth records under the crop yield index data when the weighted consistency degree is passed
And when one of the reduction attributes a belongs to red' is removed from the reduction attribute subset, the requirement of gamma is met α (red'\{a},D,U′)＝γ α (C, D, U'), judging the removed reduction attribute as a redundant attribute.
That is, the network side device can pass the judgment
By satisfying the condition gamma if a ∈ red α (red'\{a},D,U′)＝γ α (C, D, U '), then a can be regarded as the redundant attribute, make red "= red' \ { a }, reduce the redundant attribute of the attribute subset of the reduction, get the attribute subset red of the simplified non-redundant reduction, reduce.
In step S7, the network side device will sequentially input the remaining crop growth record data subsets as incremental data subsets into the fuzzy rough set attribute reduction model, update the original data subsets, repeat steps S4 to S6 using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and input the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
It should be noted that the classifier model may be an SVM support vector machine model, or may be replaced by a decision tree, a random forest, a neural network, or the like.
According to the crop yield prediction method based on incremental fuzzy rough set attribute reduction, the crop growth record data are divided into a plurality of crop growth record data subsets with equal sizes by constructing the decision table, so that the data volume of attribute reduction in each time can be reduced, the technical difficulty is reduced, and the calculation time is shortened; when the attribute reduction is carried out, one crop growth record data subset is used as an original data subset and is input into the fuzzy rough set attribute reduction model to carry out the first attribute reduction, the rest crop growth record data subsets are used as incremental data subsets and are sequentially input into the fuzzy rough set attribute reduction model, the original data subset is updated, and then the next attribute reduction is carried out until the incremental data subsets are empty, so that the technical difficulty in the calculation process is simplified, the calculation efficiency is improved, meanwhile, a more accurate attribute reduction result can be obtained, and the accuracy of the crop yield prediction model is favorably improved; and after each attribute reduction, carrying out redundancy check on the reduced attribute subset, and under the condition of continuously increasing the incremental data subsets to carry out attribute reduction calculation, ensuring that a simplified non-redundant reduced attribute subset is obtained, thereby ensuring the long-term effectiveness and reliability of the algorithm in a dynamic environment.
According to the crop yield prediction method based on increment fuzzy rough set attribute reduction, the fuzzy rough set is used for describing crop growth record data, the crop growth record data conform to the actual crop growth information yield prediction process, the information content of original data is reserved, and certain information loss is avoided. Moreover, the crop yield prediction method based on incremental fuzzy rough set attribute reduction provided by the embodiment of the application analyzes inconsistent data in the data by using the fuzzy rough set model based on the fuzzy similarity, effectively avoids the interference on the calculation of the data, reduces the calculation cost, effectively integrates the consistent data, further reduces the calculation cost, and ensures the rapidness and convenience of the algorithm in practical application.
Furthermore, the crop yield prediction method based on incremental fuzzy rough set attribute reduction provided by the embodiment of the application constructs an incremental fuzzy rough set acceleration model based on an incremental learning theory, the model meets the characteristic that data can be continuously calculated even if the data is continuously increased, the newly added data can be calculated while the reduction result of historical data is kept, static calculation cost is effectively avoided, incremental learning can be used for calculating a large-scale data set, and the problem of operation memory is avoided.
The following describes a crop yield prediction apparatus based on incremental fuzzy rough set attribute reduction provided in an embodiment of the present application, and the following described crop yield prediction apparatus based on incremental fuzzy rough set attribute reduction and the above described crop yield prediction method based on incremental fuzzy rough set attribute reduction may be referred to correspondingly.
Fig. 2 is a schematic structural diagram of a crop yield prediction apparatus based on incremental fuzzy rough set attribute reduction according to an embodiment of the present application. Referring to fig. 2, an embodiment of the present application provides a crop yield prediction apparatus based on incremental fuzzy rough set attribute reduction, which may include:
a decision table constructing module 210, configured to execute step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
a crop growth record data dividing module 220, configured to perform step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with equal sizes according to the decision table;
a first input module 230, configured to perform step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
a crop growth record removing module 240, configured to execute step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
an attribute reduction module 250, configured to perform step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
a redundancy check module 260 for performing step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
a loop module 270, configured to perform step S7: and (4) taking the remaining crop growth record data subsets as incremental data subsets, sequentially inputting the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps from S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets to a classifier model to train and obtain a crop yield prediction model.
In one embodiment, the decision table building module 210 may include:
a crop yield rating data obtaining module for: acquiring crop growth record data, and clustering the crop growth record data according to crop yield to obtain crop yield grade data;
a crop yield indicator data obtaining module for: performing normalization processing on the crop yield index value of the crop growth record data to obtain crop yield index data;
a build module to: and constructing a decision table DT = (U, C $) according to the crop growth record data, the crop yield index data and the crop yield grade data, wherein DT represents the decision table, U represents a crop growth record set, C represents a crop yield index set, and D represents a crop yield grade set.
In one embodiment, the crop growth record culling module 240 may include:
a fuzzy set deriving module to: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model to obtain a fuzzy set;
a weighted fuzzy set deriving module for: sorting the crop growth records in the fuzzy set according to the fuzzy similarity to obtain a weighted fuzzy set;
a weighted consistency degree calculation module to: according to the weighted fuzzy set, calculating the weighted consistency degree of each crop growth record in the original data subset with the crop yield grade under the crop yield index data;
a culling module for: and removing the crop growth records with the unqualified weighted consistency degree in the original data subset according to the weighted consistency degree to obtain the crop growth record subset with the qualified weighted consistency degree.
In one embodiment, the crop growth record removing module 240 may further include:
a fuzzy positive region first calculation module for: and calculating the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data according to the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data.
In one embodiment, the attribute reduction module 250 may include:
an initialization module to: initializing an original reduction attribute set;
a fuzzy positive region second calculation module for: calculating the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the original reduction attribute set according to the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data to obtain an updated crop growth record subset;
an index importance calculation module for: calculating the importance of the crop yield index of the updated crop growth record subset according to the weighted consistency degree and the qualified fuzzy positive area of the crop growth record subset under the original reduction attribute set;
an attribute reduction calculation module to: and according to the importance of the crop yield index, performing attribute reduction on the crop yield index until a stopping condition is reached to obtain a reduced attribute subset.
In one embodiment, the redundancy check module 260 may include:
a redundancy attribute screening module to: screening out redundant attributes from the reduced attribute subset according to a redundant check condition;
a redundant attribute culling module to: and removing the redundant attribute from the reduction attribute subset to obtain a non-redundant reduction attribute subset.
It should be noted that the redundancy check condition specifically includes:
and when the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data is larger than zero, and the crop yield index importance of one reduced attribute which is removed from the reduced attribute subset is equal to the crop yield index importance of the crop yield index data, judging that the removed reduced attribute is a redundant attribute.
Fig. 3 illustrates a physical structure diagram of an electronic device, which may include, as shown in fig. 3: a processor (processor) 810, a Communication Interface 820, a memory 830 and a Communication bus 840, wherein the processor 810, the Communication Interface 820 and the memory 830 communicate with each other via the Communication bus 840. The processor 810 may invoke computer programs in the memory 830 to perform the steps of a crop yield prediction method based on incremental fuzzy rough set attribute reduction, including, for example:
step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with equal sizes according to the decision table;
and step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
and step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
step S7: and (3) sequentially inputting the remaining crop growth record data subsets serving as incremental data subsets into the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
In addition, the logic instructions in the memory 830 may be implemented in 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 application or portions thereof that substantially contribute to the prior art may be embodied in the form of a software product stored in a storage medium and including 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 method according to the embodiments of the present application. And the aforementioned storage medium includes: various media capable of storing program codes, such as a usb disk, a removable hard disk, a Read-only memory (ROM), a Random Access Memory (RAM), a magnetic disk, or an optical disk.
In another aspect, the present application further provides a computer program product, where the computer program product includes a computer program, where the computer program is storable on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, a computer is capable of executing the steps of the crop yield prediction method based on incremental fuzzy rough set attribute reduction provided by the foregoing embodiments, for example, the steps include:
step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with equal sizes according to the decision table;
and step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
and step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
step S7: and (3) sequentially inputting the remaining crop growth record data subsets serving as incremental data subsets into the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
On the other hand, embodiments of the present application further provide a processor-readable storage medium, where the processor-readable storage medium stores a computer program, where the computer program is configured to cause a processor to perform the steps of the method provided in each of the above embodiments, for example, including:
step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with the same size according to the decision table;
and step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
and step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
step S7: and (3) sequentially inputting the remaining crop growth record data subsets serving as incremental data subsets into the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
The processor-readable storage medium can be any available medium or data storage device that can be accessed by a processor, including, but not limited to, magnetic memory (e.g., floppy disks, hard disks, magnetic tape, magneto-optical disks (MOs), etc.), optical memory (e.g., CDs, DVDs, BDs, HVDs, etc.), and semiconductor memory (e.g., ROMs, EPROMs, EEPROMs, non-volatile memory (NAND FLASH), solid State Disks (SSDs)), etc.
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 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 described in the embodiments or some parts of the embodiments.
Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should 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 in the embodiments of the present application.
Claims (10)
1. A crop yield prediction method based on incremental fuzzy rough set attribute reduction, comprising:
step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with equal sizes according to the decision table;
and step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
and step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
step S7: and (3) sequentially inputting the remaining crop growth record data subsets serving as incremental data subsets into the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
2. The method for predicting crop yield based on incremental fuzzy rough set attribute reduction according to claim 1, wherein the obtaining of the crop growth record data, the crop yield index data and the crop yield grade data to construct the decision table comprises:
acquiring crop growth record data, and clustering the crop growth record data according to crop yield to obtain crop yield grade data;
performing normalization processing on the crop yield index value of the crop growth record data to obtain crop yield index data;
and constructing a decision table DT = (U, C $) according to the crop growth record data, the crop yield index data and the crop yield grade data, wherein DT represents the decision table, U represents a crop growth record set C represents a crop yield index set, and D represents a crop yield grade set.
3. The method for predicting crop yield based on incremental fuzzy rough set attribute reduction according to claim 1, wherein the step of calculating fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree comprises:
calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model to obtain a fuzzy set;
sorting crop growth records in the fuzzy set according to the fuzzy similarity to obtain a weighted fuzzy set;
according to the weighted fuzzy set, calculating the weighted consistency degree of each crop growth record in the original data subset with the crop yield grade under the crop yield index data;
and removing the crop growth records with the unqualified weighted consistency degree in the original data subset according to the weighted consistency degree to obtain the crop growth record subset with the qualified weighted consistency degree.
4. The method for predicting crop yield based on incremental fuzzy rough set attribute reduction according to claim 3, wherein the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data is calculated through the fuzzy rough set attribute reduction model, the weighted consistency degree of each crop growth record in the original data subset is calculated according to the fuzzy similarity, the crop growth records with the unqualified weighted consistency degree in the original data subset are removed, and the crop growth record subset with the qualified weighted consistency degree is obtained, further comprising:
and calculating the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the crop yield index data according to the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data.
5. The method of claim 4, wherein the calculating the weighted consistency degree and the crop yield index importance of the qualified subset of crop growth records according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset comprises:
initializing an original reduction attribute set;
calculating the fuzzy positive area of the weighted consistency degree and the qualified crop growth record subset under the original reduction attribute set according to the weighted consistency degree and the qualified fuzzy positive area of the crop growth record subset under the crop yield index data to obtain an updated crop growth record subset;
calculating the importance of the crop yield index of the updated crop growth record subset according to the weighted consistency degree and the qualified fuzzy positive area of the crop growth record subset under the original reduction attribute set;
and according to the importance of the crop yield index, performing attribute reduction on the crop yield index until a stopping condition is reached to obtain a reduced attribute subset.
6. The method of predicting crop yield based on incremental fuzzy rough set attribute reduction as claimed in claim 1, wherein said performing redundancy check on said subset of reduction attributes to obtain a non-redundant subset of reduction attributes comprises:
screening out redundant attributes from the reduced attribute subset according to a redundant check condition;
and removing the redundant attribute from the reduction attribute subset to obtain a non-redundant reduction attribute subset.
7. The method for predicting crop yield based on incremental fuzzy rough set attribute reduction according to claim 6, wherein the redundancy check condition is specifically:
and when the fuzzy positive area of the subset of the weighted consistency degrees and the qualified crop growth records under the crop yield index data is larger than zero, and the crop yield index importance degree of the subset of the reduction attributes after one reduction attribute is removed from the subset of the reduction attributes is equal to the crop yield index importance degree of the crop yield index data, judging the removed reduction attribute to be a redundant attribute.
8. A crop yield prediction apparatus based on incremental fuzzy rough set attribute reduction, comprising:
a decision table construction module for executing the step S1: acquiring crop growth record data, crop yield index data and crop yield grade data, constructing a decision table, and setting a fuzzy equivalence relation and a fuzzy similarity threshold;
a crop growth record data dividing module for executing the step S2: dividing the crop growth record data into a plurality of crop growth record data subsets with equal sizes according to the decision table;
a first input module, configured to execute step S3: inputting one of the crop growth record data subsets serving as an original data subset into a fuzzy rough set attribute reduction model constructed based on a decision table, a fuzzy equivalence relation and a fuzzy similarity threshold;
a crop growth record removing module for executing the step S4: calculating the fuzzy similarity of each crop growth record in the original data subset under the crop yield index data through the fuzzy rough set attribute reduction model, calculating the weighted consistency degree of each crop growth record in the original data subset according to the fuzzy similarity, and eliminating the crop growth records with the unqualified weighted consistency degree in the original data subset to obtain the crop growth record subset with the qualified weighted consistency degree;
an attribute reduction module for executing step S5: calculating the weighted consistency degree and the crop yield index importance of the qualified crop growth record subset according to the decision table, and performing attribute reduction on the crop yield index according to the crop yield index importance to obtain a reduced attribute subset;
a redundancy check module for performing step S6: carrying out redundancy check on the reduction attribute subset to obtain a non-redundant reduction attribute subset;
a loop module for executing step S7: and (3) sequentially inputting the remaining crop growth record data subsets serving as incremental data subsets into the fuzzy rough set attribute reduction model, updating the original data subsets, repeating the steps S4 to S6 by using the updated original data subsets to obtain a plurality of non-redundant reduction attribute subsets, and inputting the non-redundant reduction attribute subsets into a classifier model to train and obtain a crop yield prediction model.
9. An electronic device comprising a processor and a memory storing a computer program, wherein the processor when executing the computer program implements the method of crop yield prediction based on incremental fuzzy rough set attribute reduction of any of claims 1 to 7.
10. A computer program product comprising a computer program, wherein the computer program when executed by a processor implements the method of crop yield prediction based on incremental fuzzy rough set attribute reduction of any of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211066091.XA CN115392582B (en) | 2022-09-01 | 2022-09-01 | Crop yield prediction method based on increment fuzzy rough set attribute reduction |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202211066091.XA CN115392582B (en) | 2022-09-01 | 2022-09-01 | Crop yield prediction method based on increment fuzzy rough set attribute reduction |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN115392582A true CN115392582A (en) | 2022-11-25 |
| CN115392582B CN115392582B (en) | 2023-11-14 |
Family
ID=84124546
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202211066091.XA Active CN115392582B (en) | 2022-09-01 | 2022-09-01 | Crop yield prediction method based on increment fuzzy rough set attribute reduction |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN115392582B (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117111585A (en) * | 2023-09-08 | 2023-11-24 | 广东工业大学 | Numerical control machine tool health state prediction method based on tolerance sub-relation rough set |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632051A (en) * | 2013-11-27 | 2014-03-12 | 电子科技大学 | Data analyzing method of attribute reduction based on conditional entropy of fuzzy rough set |
| CN104063230A (en) * | 2014-07-09 | 2014-09-24 | 中国科学院重庆绿色智能技术研究院 | Rough set parallel reduction method, device and system based on MapReduce |
| CN105892287A (en) * | 2016-05-09 | 2016-08-24 | 河海大学常州校区 | Crop irrigation strategy based on fuzzy judgment and decision making system |
| US20180033102A1 (en) * | 2015-02-12 | 2018-02-01 | Maurice Duault | Process for computing a score for a search engine used for accessing a database of real estate properties |
| CN109828996A (en) * | 2018-12-21 | 2019-05-31 | 西安交通大学 | A kind of Incomplete data set rapid attribute reduction |
| CN110097934A (en) * | 2018-12-29 | 2019-08-06 | 蚌埠医学院 | A kind of attributive character reduction method of electrocardio Ontological concept |
-
2022
- 2022-09-01 CN CN202211066091.XA patent/CN115392582B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103632051A (en) * | 2013-11-27 | 2014-03-12 | 电子科技大学 | Data analyzing method of attribute reduction based on conditional entropy of fuzzy rough set |
| CN104063230A (en) * | 2014-07-09 | 2014-09-24 | 中国科学院重庆绿色智能技术研究院 | Rough set parallel reduction method, device and system based on MapReduce |
| US20180033102A1 (en) * | 2015-02-12 | 2018-02-01 | Maurice Duault | Process for computing a score for a search engine used for accessing a database of real estate properties |
| CN105892287A (en) * | 2016-05-09 | 2016-08-24 | 河海大学常州校区 | Crop irrigation strategy based on fuzzy judgment and decision making system |
| CN109828996A (en) * | 2018-12-21 | 2019-05-31 | 西安交通大学 | A kind of Incomplete data set rapid attribute reduction |
| CN110097934A (en) * | 2018-12-29 | 2019-08-06 | 蚌埠医学院 | A kind of attributive character reduction method of electrocardio Ontological concept |
Non-Patent Citations (1)
| Title |
|---|
| 郭婉;吴昊;王安宁;易涛;勾志营;叶新玉;: "基于粗糙集的农机化发展水平评价方法", 农机化研究, no. 02 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117111585A (en) * | 2023-09-08 | 2023-11-24 | 广东工业大学 | Numerical control machine tool health state prediction method based on tolerance sub-relation rough set |
| CN117111585B (en) * | 2023-09-08 | 2024-02-09 | 广东工业大学 | Numerical control machine tool health state prediction method based on tolerance sub-relation rough set |
Also Published As
| Publication number | Publication date |
|---|---|
| CN115392582B (en) | 2023-11-14 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN112990284B (en) | Individual trip behavior prediction method, system and terminal based on XGboost algorithm | |
| CN110135167B (en) | Edge computing terminal security level evaluation method for random forest | |
| CN107563429A (en) | A kind of sorting technique and device of network user colony | |
| CN109818961B (en) | Network intrusion detection method, device and equipment | |
| CN110796485A (en) | Method and device for improving prediction precision of prediction model | |
| CN106934410A (en) | The sorting technique and system of data | |
| CN115392582A (en) | Crop yield prediction method based on incremental fuzzy rough set attribute reduction | |
| CN113468796A (en) | Voltage missing data identification method based on improved random forest algorithm | |
| CN115033591A (en) | Intelligent detection method and system for electricity charge data abnormity, storage medium and computer equipment | |
| CN113837266B (en) | Software defect prediction method based on feature extraction and Stacking ensemble learning | |
| CN113011788B (en) | Emergency decision method for offshore traffic accident, terminal equipment and storage medium | |
| CN112287468B (en) | Ship collision risk degree judging method and system | |
| CN113901705A (en) | Fire risk assessment method and device, terminal equipment and storage medium | |
| CN111352926A (en) | Data processing method, device, equipment and readable storage medium | |
| CN115577259A (en) | Fault pole selection method and device for high-voltage direct-current transmission system and computer equipment | |
| CN115221955A (en) | Multi-depth neural network parameter fusion system and method based on sample difference analysis | |
| CN111654853B (en) | Data analysis method based on user information | |
| CN113221966A (en) | Differential privacy decision tree construction method based on F _ Max attribute measurement | |
| CN113205274A (en) | Quantitative ranking method for construction quality | |
| CN111488520A (en) | Crop planting species recommendation information processing device and method and storage medium | |
| CN111753992A (en) | Screening method and screening system | |
| Ivanytska et al. | Study of Methods of Complex Data Analysis that Based on Machine Learning Technologies | |
| CN116384508A (en) | Low-quality data active forgetting method for transverse federal learning | |
| CN116341767A (en) | New energy power prediction characteristic recursion screening method based on random forest | |
| Kowalski et al. | Feature selection for regression tasks base on explainable artificial intelligence procedures |
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 |