CN111489021A - Beet yield prediction method based on particle swarm optimization BP neural network - Google Patents
Beet yield prediction method based on particle swarm optimization BP neural network Download PDFInfo
- Publication number
- CN111489021A CN111489021A CN202010245280.8A CN202010245280A CN111489021A CN 111489021 A CN111489021 A CN 111489021A CN 202010245280 A CN202010245280 A CN 202010245280A CN 111489021 A CN111489021 A CN 111489021A
- Authority
- CN
- China
- Prior art keywords
- neural network
- particle swarm
- prediction
- beet
- 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.)
- Pending
Links
- 238000013528 artificial neural network Methods 0.000 title claims abstract description 51
- 239000002245 particle Substances 0.000 title claims abstract description 39
- 235000016068 Berberis vulgaris Nutrition 0.000 title claims abstract description 36
- 241000335053 Beta vulgaris Species 0.000 title claims abstract description 36
- 238000005457 optimization Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 title claims abstract description 14
- 238000012549 training Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 5
- 238000010606 normalization Methods 0.000 claims abstract description 4
- CURLTUGMZLYLDI-UHFFFAOYSA-N Carbon dioxide Chemical compound O=C=O CURLTUGMZLYLDI-UHFFFAOYSA-N 0.000 claims description 10
- 239000002689 soil Substances 0.000 claims description 9
- 229910002092 carbon dioxide Inorganic materials 0.000 claims description 5
- 239000001569 carbon dioxide Substances 0.000 claims description 5
- 238000005286 illumination Methods 0.000 claims description 5
- 230000009191 jumping Effects 0.000 claims description 4
- 238000004088 simulation Methods 0.000 claims description 4
- 239000011159 matrix material Substances 0.000 claims description 3
- 238000012360 testing method Methods 0.000 description 17
- 238000004458 analytical method Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 4
- 238000011161 development Methods 0.000 description 3
- 230000002262 irrigation Effects 0.000 description 3
- 238000003973 irrigation Methods 0.000 description 3
- 238000007781 pre-processing Methods 0.000 description 3
- NINIDFKCEFEMDL-UHFFFAOYSA-N Sulfur Chemical group [S] NINIDFKCEFEMDL-UHFFFAOYSA-N 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 241000190079 Turnera Species 0.000 description 1
- 238000003556 assay Methods 0.000 description 1
- 238000013142 basic testing Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000011056 performance test Methods 0.000 description 1
- 230000002028 premature Effects 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Strategic Management (AREA)
- Artificial Intelligence (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- Human Resources & Organizations (AREA)
- Economics (AREA)
- Biomedical Technology (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Mining & Mineral Resources (AREA)
- Primary Health Care (AREA)
- Agronomy & Crop Science (AREA)
- Marine Sciences & Fisheries (AREA)
- Animal Husbandry (AREA)
- Entrepreneurship & Innovation (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a beet yield prediction method based on a particle swarm optimization BP neural network. Step 1: importing data required by BP neural network training and prediction, and carrying out normalization processing on related samples of the beet; step 2: constructing a network structure of the BP neural network, and determining the structural characteristics of the neural network; and step 3: initializing a BP neural network numerical threshold; and 4, step 4: initializing relevant parameters of a particle swarm algorithm, and determining self-adaptive inertia weight w and evolution times parameters of the particle swarm; and 5: setting a fitness function; step 6: when the termination condition is reached, obtaining a threshold value of an optimal numerical value; and 7: and after obtaining the threshold value of the optimal value, completing the optimized prediction of the beet yield. The invention is used for solving the problem that the prediction error is larger due to the fact that a plurality of data are not ideal to be preprocessed in the conventional BP neural network prediction system.
Description
Technical Field
The invention belongs to the technical field of yield prediction, and particularly relates to a beet yield prediction method based on a particle swarm optimization BP neural network.
Background
In a yield prediction system, the input is typically directly trained by a prediction algorithm and then yield predicted. In systems in industries such as agriculture and planting, training and prediction are directly performed through input data, so that large errors are inevitably caused, great influence is brought to subsequent yield prediction, and data such as yield cannot be accurately predicted. Therefore, in these systems, preprocessing of data is an important part thereof.
In modern society, although systems such as agricultural yield prediction and the like are not applied on a large scale, the systems still become an important direction for the development of the agricultural industry in the future. At present, the prediction of the agricultural industry is mainly based on the z planting experience of farmers and the prediction of the yield over the years, so that the yield cannot be effectively predicted, and manpower and material resources are greatly wasted. The yield of crops is predicted through the BP neural network, historical data can be trained, and the existing data are analyzed to obtain a prediction result. By the method, data such as agricultural yield and irrigation quantity can be effectively predicted, so that the yield of crops is improved. Meanwhile, under the background of the development trend of the Internet of things and agriculture, data are visually predicted by means of a BP neural network technology, and effective assistance is provided for the development of the agricultural Internet of things. However, many existing prediction systems of the BP neural network have problems that data preprocessing is not ideal, and prediction errors are large.
Disclosure of Invention
The invention provides a beet yield prediction method based on a particle swarm optimization BP neural network, which is used for solving the problem that the prediction error is larger due to the fact that a plurality of data are not ideal to preprocess in the existing BP neural network prediction system.
The invention is realized by the following technical scheme:
a beet yield prediction method based on an improved particle swarm optimization BP neural network comprises the following steps:
step 1: leading in BP neural network training and predicting required beet yield input sample data, and carrying out normalization processing on the beet yield sample;
step 2: constructing a network structure of the BP neural network, and determining the structural characteristics of the neural network;
and step 3: initializing a BP neural network numerical threshold;
and 4, step 4: initializing relevant parameters of a particle swarm algorithm, and determining self-adaptive inertia weight w and evolution times parameters of the particle swarm;
and 5: setting a fitness function, and taking an error obtained by training the BP neural network as a fitness value calculated by the fitness function;
step 6: judging whether the termination condition of the initialization setting is reached, if so, acquiring a threshold value of an optimal numerical value, otherwise, continuing to execute the step 5;
and 7: after obtaining the threshold value of the optimal numerical value, calculating the error obtained by BP neural network training, calculating an updated threshold value, judging whether the threshold value meets a termination condition, if so, carrying out simulation classification identification, comparing the beet yield data obtained by BP prediction with the real beet yield data, and outputting a comparison graph and a relative error; and if not, continuing to execute the step 7 until a termination condition is met, and finishing the beet yield optimization prediction.
Further, the step 1 specifically includes that the sample is divided into an input sample and an output sample, wherein the input sample includes air temperature, air humidity, soil temperature, soil humidity, illumination intensity and carbon dioxide content, and the output sample is the yield of the beet.
Further, the initialized BP neural network numerical threshold in the step 3 is to set a system coefficient, an evolution frequency and a population scale of the particle swarm algorithm; setting a speed threshold and a population threshold of a population, and performing correlation operation of a subsequent particle swarm according to the set threshold; and determining the self-adaptive inertia weight w of the particle swarm.
Further, the step 4 comprises the following steps:
step 4.1: calculating weight matrixes W1 and W2 of the BP neural network and related thresholds B1 and B2;
step 4.2: assigning a network weight value, assigning a net structure, and storing a related matrix;
step 4.3: and (5) outputting by using the trained BP neural network prediction function, and calculating the error.
Further, the step 5 comprises the following steps:
step 5.1: calculating the fitness value of each particle, and calculating the optimal values of individuals and groups according to the fitness values;
step 5.2: by introducing self-adaptive inertia weight and escape strategy to optimize the particle swarm algorithm, the aim of jumping out of local extreme values in time is fulfilled.
The invention has the beneficial effects that:
in the prediction of data such as agricultural yield and irrigation quantity, errors inevitably occur in the result of the data in the BP neural network. The yield of crops is predicted through the BP neural network, historical data can be trained, and the existing data are analyzed to obtain a prediction result. By the method, data such as agricultural yield and irrigation quantity can be effectively predicted, so that the yield of crops is improved. However, many existing prediction systems of the BP neural network have problems that data preprocessing is not ideal, and prediction errors are large. The particle swarm algorithm has a strong optimizing effect on data and can effectively preprocess the data, so that the prediction error of the BP neural network is reduced, and the predicted beet yield is more accurate.
Drawings
FIG. 1 is a schematic structural view of the present invention.
FIG. 2 is a graph showing the fitness function values of four particle swarm algorithms of the present invention as the number of iterations increases, and FIG. 2- (a) f1Testing function variationsFIG. 2- (b) f2Graph of the variation of the test function, FIG. 2- (c) f3Graph of the variation of the test function, FIG. 2- (d) f4Graph of the variation of the test function, FIG. 2- (e) f5Graph of the variation of the test function, FIG. 2- (f) f6A graph of the variation of the test function.
FIG. 3 is a diagram of a prediction system of the present invention.
FIG. 4 compares the predicted values with the true values for different prediction models of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be described clearly and completely with reference to the accompanying drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
Example 1
Step 1: leading in BP neural network training and predicting required beet yield input sample data, and carrying out normalization processing on the beet yield sample;
step 2: constructing a network structure of the BP neural network, and determining the structural characteristics of the neural network;
and step 3: initializing a BP neural network numerical threshold; the occurrence of over-dimension errors is avoided;
and 4, step 4: initializing relevant parameters of a particle swarm algorithm, and determining self-adaptive inertia weight w and evolution times parameters of the particle swarm;
and 5: setting a fitness function, and taking an error obtained by training the BP neural network as a fitness value calculated by the fitness function;
step 6: judging whether the termination condition of the initialization setting is reached, if so, acquiring a threshold value of an optimal numerical value, otherwise, continuing to execute the step 5;
and 7: after obtaining the threshold value of the optimal numerical value, calculating the error obtained by BP neural network training, calculating an updated threshold value, judging whether the threshold value meets a termination condition, if so, carrying out simulation classification identification, comparing the beet yield data obtained by BP prediction with the real beet yield data, and outputting a comparison graph and a relative error; and if not, continuing to execute the step 7 until a termination condition is met, and finishing the beet yield optimization prediction.
Further, the step 1 specifically includes that the sample is divided into an input sample and an output sample, wherein the input sample includes air temperature, air humidity, soil temperature, soil humidity, illumination intensity and carbon dioxide content, and the output sample is the yield of the beet.
Further, the initialized BP neural network numerical threshold in the step 3 is to set a system coefficient, an evolution frequency and a population scale of the particle swarm algorithm; setting a speed threshold and a population threshold of a population, and performing correlation operation of a subsequent particle swarm according to the set threshold; and determining the self-adaptive inertia weight w of the particle swarm.
Further, the step 4 comprises the following steps:
step 4.1: calculating weight matrixes W1 and W2 of the BP neural network and related thresholds B1 and B2;
step 4.2: assigning a network weight value, assigning a net structure, and storing a related matrix;
step 4.3: and (5) outputting by using the trained BP neural network prediction function, and calculating the error.
Further, the step 5 comprises the following steps:
step 5.1: calculating the fitness value of each particle, and calculating the optimal values of individuals and groups according to the fitness values;
step 5.2: by introducing self-adaptive inertia weight and escape strategy to optimize the particle swarm algorithm, the aim of jumping out of local extreme values in time is fulfilled.
Example 2
Assay analysis
NCPSO algorithm performance test
In order to verify the performance of the improved PSO algorithm based on the adaptive inertia weight and the escape strategy, six test functions are selected to test the PSO (the inertia weight w takes a fixed value of 0.85), L PSO (the inertia weight w takes a linear value), CPSO (the inertia weight w takes a nonlinear value) and NCPSO (the PSO algorithm based on the adaptive inertia weight and the reverse strategy provided by the invention), each test function is operated for 30 times, and the specific experimental data is set as follows, wherein the population scale N is 20, and the iteration time T is 100.
TABLE 1 test function characteristics
The following simulation analysis employed six basic test functions listed in the above table, including Sphere function, Schwefel function, Ackley function, shaffer function, Exponential function, and Duadric function.
Table 2 test function results
Analysis of Table 1 reveals that for a single-peak function f1(Sphere function), compared with the three PSO algorithms, the NCPSO algorithm has higher convergence speed and convergence precision reaching 10-40(ii) a For function f2(Schwefel function) has higher optimization difficulty, and the fact proves that the optimization precision of the function is lower, but based on the NCPSO algorithm provided by the invention, the order of magnitude of the optimization precision reaches 10-21Compared with the first three PSO algorithms, the method has certain improvement; for function f3(Ackley function) shows that the minimum values searched by the CPSO algorithm and the NCPSO algorithm are the same, and the precision is not high; for function f4(snapshot function) which has only one local minimum point but not high optimizing precision, wherein the optimizing precision of each of PSO, L PSO and CPSO is 10-3The optimizing precision of the optimized NCPSO algorithm is 10-10Compared with the prior art, the effect is better; for function f5(Exponental function) which isA two-dimensional function with local minimum value of-1, and optimization accuracy of PSO, L PSO, CPSO and NCPSO algorithms all reaching-1, and for function f6(Duadric function), the local minimum value of the function is 0, the optimizing precision of PSO, L PSO, CPSO and NCPSO is higher, and the optimizing precision of NCPSO reaches 10-83。
The foregoing fig. 2 shows a graph in which fitness function values of four particle swarm algorithms change with the increase of iteration times, where in fig. 2- (a), fig. 2- (b), fig. 2- (c), and fig. 2- (f), horizontal and vertical coordinates are logarithmic values, the PSO algorithm lacks a mechanism for jumping out local extreme points, the search effect on the multi-peak function is poor, and the "premature" phenomenon is likely to occur.
NCPSO-BP beet yield prediction test
Prediction system
The prediction system mainly comprises four plates, namely a data acquisition, a data transmission, a data processing and an uploading intelligent agricultural platform, and the structure of the prediction system is shown in figure 3. In the test, 6 groups of data of 40 black dragon river turnera river test fields from 28 days in 7 months in 2019 to 28 days in 10 months in 2019 are selected, wherein the 6 groups are respectively air temperature, air humidity, illumination intensity, carbon dioxide content, soil temperature and soil humidity.
Analysis of test results
In the test, 40 groups of sample data including air temperature and humidity, soil temperature and humidity, illumination intensity and carbon dioxide concentration are collected, wherein the training data is 30 groups, and the test data is 10 groups.
TABLE 3 sample data
In the construction of the BP network model, an input layer is a prediction quantity influencing an output layer, the number of the input layers of the beet yield prediction model is 6, and the number of the output layers is 1. The determination of the number of the hidden layers plays an important role in the accuracy of the prediction model, the number of the hidden layers from 4 to 12 is selected for BP network training by comparing training errors under different numbers of the hidden layers, and results shown in Table 4 are obtained through 8 times of experiments. When the number of the hidden layers is 8, the training error is 0.1969, and the training result is optimal.
TABLE 4 network training error for different hidden layer node numbers
FIG. 4 is a comparison of the predicted values and the true values of the two prediction models, and it can be seen that the NCPSO-BP prediction model has higher fitness to the prediction data of beet yield. Table 5 shows three indices of the mean absolute error, the variance of the absolute error and the mean of the relative error of PSO-BP and NCPSO-BP to evaluate the prediction results.
TABLE 5 comparison of the predicted results
The data in the above table are not initialized, and it can be seen from table 5 that the average of the absolute error of NCPSO-BP is 0.1969, and the average of the relative error is 3.59% smaller than the PSO-BP value, indicating higher prediction accuracy and fitting degree. The variance of the absolute error of the NCPSO-BP is smaller than that of a PSO-BP prediction model, which shows that the prediction result of the NCPSO-BP is more stable. The combination shows that the NCPSO-BP prediction model has better training precision and prediction effect.
The invention provides a prediction model for optimizing a BP neural network by improving a particle swarm algorithm, which is applied to beet yield prediction.
1) Optimizing a particle swarm algorithm, and introducing dynamic self-adaptive inertial weight to enhance the searching capability and improve the convergence speed; meanwhile, a reverse escape strategy is used, and the algorithm is prevented from falling into a local extreme value.
2) And combining the improved particle swarm algorithm with a BP prediction network to establish an NCPSO-BP yield prediction model.
3) Experiments show that the relative error average value of the optimal prediction result of the NCPSO-BP prediction model is 3.59%, and the absolute error average value of 0.1969 is reduced compared with that of the NCPSO-BP, so that the NCPSO-BP prediction model has better adaptability in the aspect of beet yield prediction.
Claims (5)
1. A beet yield prediction method based on particle swarm optimization BP neural network is characterized by comprising the following steps:
step 1: leading in BP neural network training and predicting required beet yield input sample data, and carrying out normalization processing on the beet yield sample;
step 2: constructing a network structure of the BP neural network, and determining the structural characteristics of the neural network;
and step 3: initializing a BP neural network numerical threshold;
and 4, step 4: initializing relevant parameters of a particle swarm algorithm, and determining self-adaptive inertia weight w and evolution times parameters of the particle swarm;
and 5: setting a fitness function, and taking an error obtained by training the BP neural network as a fitness value calculated by the fitness function;
step 6: judging whether the termination condition of the initialization setting is reached, if so, acquiring a threshold value of an optimal numerical value, otherwise, continuing to execute the step 5;
and 7: after obtaining the threshold value of the optimal numerical value, calculating the error obtained by BP neural network training, calculating an updated threshold value, judging whether the threshold value meets a termination condition, if so, carrying out simulation classification identification, comparing the beet yield data obtained by BP prediction with the real beet yield data, and outputting a comparison graph and a relative error; and if not, continuing to execute the step 7 until a termination condition is met, and finishing the beet yield optimization prediction.
2. The method as claimed in claim 1, wherein the step 1 specifically comprises dividing the samples into input samples and output samples, wherein the input samples comprise air temperature, air humidity, soil temperature, soil humidity, illumination intensity and carbon dioxide content, and the output samples are beet yield.
3. The method for predicting the yield of the beet based on the particle swarm optimization BP neural network as claimed in claim 1, wherein the initialized BP neural network numerical threshold in the step 3 is to set the system coefficients, the evolution times and the population scale of the particle swarm algorithm; setting a speed threshold and a population threshold of a population, and performing correlation operation of a subsequent particle swarm according to the set threshold; and determining the self-adaptive inertia weight w of the particle swarm.
4. The method for predicting the yield of beet based on particle swarm optimization BP neural network as claimed in claim 1, wherein said step 4 comprises the following steps:
step 4.1: calculating weight matrixes W1 and W2 and related thresholds B1 and B2 of the BP neural network;
step 4.2: assigning a network weight value, assigning a net structure, and storing a related matrix;
step 4.3: and (5) outputting by using the trained BP neural network prediction function, and calculating the error.
5. The method for predicting the yield of beet based on particle swarm optimization BP neural network as claimed in claim 2, wherein said step 5 comprises the following steps:
step 5.1: calculating the fitness value of each particle, and calculating the optimal values of individuals and groups according to the fitness values;
step 5.2: by introducing self-adaptive inertia weight and escape strategy to optimize the particle swarm algorithm, the aim of jumping out of local extreme values in time is fulfilled.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010245280.8A CN111489021A (en) | 2020-03-31 | 2020-03-31 | Beet yield prediction method based on particle swarm optimization BP neural network |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010245280.8A CN111489021A (en) | 2020-03-31 | 2020-03-31 | Beet yield prediction method based on particle swarm optimization BP neural network |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN111489021A true CN111489021A (en) | 2020-08-04 |
Family
ID=71794559
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010245280.8A Pending CN111489021A (en) | 2020-03-31 | 2020-03-31 | Beet yield prediction method based on particle swarm optimization BP neural network |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111489021A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117575094A (en) * | 2023-11-27 | 2024-02-20 | 浪潮智慧科技有限公司 | Crop yield prediction and optimization method and device based on digital twin |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106920008A (en) * | 2017-02-28 | 2017-07-04 | 山东大学 | A kind of wind power forecasting method based on Modified particle swarm optimization BP neural network |
| CN110909773A (en) * | 2019-11-08 | 2020-03-24 | 中国农业大学 | Client classification method and system based on adaptive particle swarm |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
-
2020
- 2020-03-31 CN CN202010245280.8A patent/CN111489021A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106920008A (en) * | 2017-02-28 | 2017-07-04 | 山东大学 | A kind of wind power forecasting method based on Modified particle swarm optimization BP neural network |
| CN110909773A (en) * | 2019-11-08 | 2020-03-24 | 中国农业大学 | Client classification method and system based on adaptive particle swarm |
| CN110930182A (en) * | 2019-11-08 | 2020-03-27 | 中国农业大学 | Improved particle swarm optimization algorithm-based client classification method and device |
Non-Patent Citations (3)
| Title |
|---|
| GU LILI: "Optimization of PSO Algorithm Based on Adaptive", 《OURNAL OF PHYSICS: CONFERENCE SERIES》 * |
| 纪雪玲: "改进粒子群优化算法及其在人工神经网络中的应用研究", 《中国优秀硕士学位论文全文数据库 (信息科技辑)》 * |
| 顾丽丽: "基于改进粒子群算法优化BP神经网络的甜菜产量预测方法", 《新疆大学学报(自然科学版)》 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN117575094A (en) * | 2023-11-27 | 2024-02-20 | 浪潮智慧科技有限公司 | Crop yield prediction and optimization method and device based on digital twin |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113705478B (en) | Mangrove single wood target detection method based on improved YOLOv5 | |
| CN112270129B (en) | Plant growth prediction method based on big data analysis | |
| CN111401565A (en) | DOA estimation method based on machine learning algorithm XGboost | |
| CN113076969B (en) | Image target detection method based on Gaussian mixture loss function | |
| CN115277354B (en) | Fault detection method for command control network management system | |
| CN113221447A (en) | Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm | |
| CN112504682A (en) | Chassis engine fault diagnosis method and system based on particle swarm optimization algorithm | |
| CN114897204A (en) | Method and device for predicting short-term wind speed of offshore wind farm | |
| CN117370766A (en) | Satellite mission planning scheme evaluation method based on deep learning | |
| CN114611804A (en) | Maize yield prediction method based on TSO-GRNN combined model | |
| CN115984650A (en) | Deep learning-based synthetic aperture radar image identification method | |
| CN118332521A (en) | Crust deformation time sequence simulation method based on particle swarm optimization random forest | |
| CN111489021A (en) | Beet yield prediction method based on particle swarm optimization BP neural network | |
| CN114357870A (en) | Metering equipment operation performance prediction analysis method based on local weighted partial least squares | |
| CN114330815A (en) | Ultra-short-term wind power prediction method and system based on improved GOA (generic object oriented architecture) optimized LSTM (least Square TM) | |
| CN112288744A (en) | SAR image change detection method based on integer reasoning quantification CNN | |
| CN109187898B (en) | Soft measurement method and device for ammonia nitrogen content of water in aquaculture environment | |
| CN112149870A (en) | Pig house ammonia concentration combined prediction method based on ISODATA clustering and Elman neural network | |
| CN116757545A (en) | Multi-stage manufacturing system quality prediction method based on multi-task deep learning | |
| CN115907178A (en) | Clean ecosystem CO 2 Method for predicting exchange amount | |
| CN110728292A (en) | Self-adaptive feature selection algorithm under multi-task joint optimization | |
| CN114818945A (en) | Small sample image classification method and device integrating category adaptive metric learning | |
| CN114444654A (en) | NAS-oriented training-free neural network performance evaluation method, device and equipment | |
| CN111382147A (en) | Meteorological data missing interpolation method and system | |
| CN118252056B (en) | Grape disease control method and system combining boundary layer humidity |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20200804 |