CN113221447A - Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm - Google Patents
Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm Download PDFInfo
- Publication number
- CN113221447A CN113221447A CN202110435506.5A CN202110435506A CN113221447A CN 113221447 A CN113221447 A CN 113221447A CN 202110435506 A CN202110435506 A CN 202110435506A CN 113221447 A CN113221447 A CN 113221447A
- Authority
- CN
- China
- Prior art keywords
- neural network
- genetic algorithm
- data
- threshold
- soil humidity
- 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 72
- 239000002689 soil Substances 0.000 title claims abstract description 47
- 230000002068 genetic effect Effects 0.000 title claims abstract description 46
- 238000000034 method Methods 0.000 title claims abstract description 35
- 238000012549 training Methods 0.000 claims abstract description 25
- 230000035772 mutation Effects 0.000 claims abstract description 24
- 238000012360 testing method Methods 0.000 claims abstract description 18
- 210000002569 neuron Anatomy 0.000 claims abstract description 4
- 210000000349 chromosome Anatomy 0.000 claims description 16
- 238000005457 optimization Methods 0.000 claims description 8
- 230000003044 adaptive effect Effects 0.000 claims description 6
- 238000004364 calculation method Methods 0.000 claims description 4
- 238000005286 illumination Methods 0.000 claims description 4
- 238000003062 neural network model Methods 0.000 abstract description 2
- 230000006870 function Effects 0.000 description 17
- 230000008569 process Effects 0.000 description 13
- 238000012271 agricultural production Methods 0.000 description 6
- 230000006872 improvement Effects 0.000 description 4
- 238000012272 crop production Methods 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 3
- 238000012544 monitoring process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 238000011161 development Methods 0.000 description 2
- 230000000694 effects Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000012937 correction Methods 0.000 description 1
- 230000007613 environmental effect Effects 0.000 description 1
- 238000012804 iterative process Methods 0.000 description 1
- 238000004519 manufacturing process Methods 0.000 description 1
- 108090000623 proteins and genes Proteins 0.000 description 1
- 230000008707 rearrangement Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F30/00—Computer-aided design [CAD]
- G06F30/20—Design optimisation, verification or simulation
- G06F30/27—Design optimisation, verification or simulation using machine learning, e.g. artificial intelligence, neural networks, support vector machines [SVM] or training a model
-
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/12—Computing arrangements based on biological models using genetic models
- G06N3/126—Evolutionary algorithms, e.g. genetic algorithms or genetic programming
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F2111/00—Details relating to CAD techniques
- G06F2111/08—Probabilistic or stochastic CAD
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Biophysics (AREA)
- Artificial Intelligence (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- General Health & Medical Sciences (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Economics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Mathematical Physics (AREA)
- Tourism & Hospitality (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- Data Mining & Analysis (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Operations Research (AREA)
- Genetics & Genomics (AREA)
- Entrepreneurship & Innovation (AREA)
- Primary Health Care (AREA)
- Marine Sciences & Fisheries (AREA)
- Game Theory and Decision Science (AREA)
- Development Economics (AREA)
- Animal Husbandry (AREA)
- Physiology (AREA)
- Mining & Mineral Resources (AREA)
- Agronomy & Crop Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
Abstract
The invention discloses a soil humidity prediction method for optimizing a BP neural network based on an improved genetic algorithm. Step 1: inputting data, and dividing the collected data into two groups, wherein one group is used as training data, and the other group is used as test data; step 2: determining a topological structure of a neural network, and setting the number of neurons of each parameter of the neural network to include an input layer, a hidden layer and an output layer; and step 3: initializing a BP neural network, and obtaining an initial weight and a threshold of the neural network; and 4, step 4: initializing a genetic algorithm, and encoding an initial weight and a threshold; and 5: setting a fitness function of a genetic algorithm; step 6: carrying out selection, crossing and mutation operations; and 7: calculating a fitness value, and judging whether a termination condition is met; and 8: and determining to obtain the optimal weight and threshold value, and completing the prediction of the soil humidity. The method is used for solving the problems that a simple BP neural network model has large error when predicting the soil humidity and cannot predict the soil humidity accurately.
Description
Technical Field
The invention belongs to the technical field of soil humidity prediction, and particularly relates to a soil humidity prediction method based on an improved genetic algorithm optimized BP neural network.
Background
With the continuous development of sensor technology, the growth information of crops is accurately predicted by means of the sensor, and therefore the intelligent agriculture operation of all things interconnection in agricultural production is achieved. Wisdom agricultural mainly gathers the environmental parameter in the crop production through the sensor, later transmits data to network terminal through the internet, thereby analyzes data and formulates reasonable crop production plan finally. In various data for monitoring the crop production environment, the prediction of soil humidity is extremely important, the dryness and the humidity of soil are related to the production condition of crops, and the crops can grow normally only by reasonable soil humidity.
At present, the measurement to soil moisture mainly relies on soil moisture sensor, and a large amount of sensors can destroy the structure of soil, has also caused huge waste to resource and energy, consequently relies on neural network to predict soil moisture effectual the drawback of having avoided the sensor in the measurement process, also makes soil moisture's prediction more reliable, makes the agricultural production technique have had very big improvement. With the continuous development of artificial intelligence, a neural network prediction model is widely applied, as the most successful neural network model, a BP neural network is widely applied in the field of data prediction, and a soil humidity prediction method for optimizing the BP neural network by applying an improved genetic algorithm is provided for solving the problem of large prediction error of a single BP neural network prediction model.
Disclosure of Invention
The invention is used for solving the problem of soil humidity prediction, and the single BP neural network has larger error when prediction is carried out, so the soil humidity prediction method based on the BP neural network optimized by the improved genetic algorithm is provided.
The soil humidity prediction method for optimizing the BP neural network based on the improved genetic algorithm is realized according to the following steps: step 1: inputting data, and dividing the collected data into two groups, wherein one group is used as training data, and the other group is used as test data; step 2: determining a topological structure of a neural network, and setting the number of neurons of each parameter of the neural network to include an input layer, a hidden layer and an output layer; and step 3: initializing a BP neural network, and obtaining an initial weight and a threshold of the neural network; and 4, step 4: initializing a genetic algorithm, and encoding an initial weight and a threshold; and 5: setting a fitness function of a genetic algorithm, and taking an error square root reciprocal obtained by training a BP neural network as a fitness function value; step 6: carrying out selection, crossing and mutation operations; and 7: calculating a fitness value, judging whether a termination condition is met, if so, determining an optimal weight and a threshold, and if not, executing the step 6; and 8: and after the optimal weight and the threshold are determined to be obtained, assigning the optimal weight and the threshold to the BP neural network, and training the BP neural network through training data to obtain an accurate data prediction model and finish accurate prediction of soil humidity.
Further, the step 1 specifically includes dividing the data into a training set and a testing set, where the training set and the testing set include input data and target data, the input data includes air temperature, air humidity and illumination intensity, and the target data is soil humidity.
Further, in the step 3, the BP neural network is initialized, and the initial weight and the threshold of the neural network are obtained as chromosome codes, the number of chromosomes and the length of chromosomes of the set genetic algorithm; setting selection operation, mutation operation and crossover operation of chromosomes.
Further, the step 6 comprises the following steps: step 6.1: during selection operation, the population individuals are rearranged by using a sorting method, and then selection is carried out according to the probability of the self-adaptive function; step 6.2: during cross operation, the calculation mode of the cross probability utilizes a self-adaptive function to calculate; step 6.3: during mutation operation, the mutation probability is calculated by using an adaptive function.
Further, the step 7 comprises the following steps: step 7.1: calculating the fitness value of each group of chromosomes, and judging whether the optimal weight and threshold are obtained or not according to the fitness value; step 7.2: by introducing the self-adaptive selection probability, the mutation probability and the cross probability, the optimal weight and threshold are obtained.
The invention has the beneficial effects.
In the agricultural production process, the quantity of the soil humidity sensors is greatly reduced by applying the neural network to predict the soil humidity, the soil structure is prevented from being damaged, the agricultural production technology is improved, and the prediction of the soil humidity is more convenient. The prediction model based on the BP neural network can effectively predict the soil humidity, provides convenience for monitoring data of the crop growth environment, and the prediction error of the BP neural network is large in the prediction process. The soil humidity prediction method based on the improved genetic algorithm for optimizing the BP neural network can effectively reduce prediction errors, the genetic algorithm has strong global optimization capability, the generation of local optimization is avoided, the prediction capability of the BP neural network is greatly improved, and therefore the prediction of the soil humidity is more accurate.
Drawings
FIG. 1 is a schematic flow chart of the present invention.
FIG. 2 is a system framework of the present invention.
FIG. 3 is a comparison of predicted values and true values for the present invention.
Detailed Description
The technical process of the invention in the implementation process will be shown in detail and completely. The implementation described below contains some experimental examples, not all examples of the present invention. Based on the examples of the present invention, those skilled in the art can use the examples of the present invention without any creative effort, and all of them belong to the protection scope of the present invention.
Example 1.
Step 1: and inputting data, and dividing the collected data into two groups, wherein one group is used as training data, and the other group is used as test data.
Step 2: determining the topological structure of the neural network, and setting the number of neurons of each item of the neural network to include an input layer, a hidden layer and an output layer.
And step 3: initializing the BP neural network, and obtaining an initial weight and a threshold of the neural network.
And 4, step 4: initializing the genetic algorithm, and encoding the initial weight and threshold.
And 5: and setting a fitness function of the genetic algorithm, and taking the inverse square root error obtained by training the BP neural network as the fitness function value.
Step 6: selection, crossover and mutation operations are performed.
And 7: calculating the fitness value, judging whether a termination condition is met, if so, determining the optimal weight and the threshold, and if not, executing the step 6.
And 8: and after the optimal weight and the threshold are determined to be obtained, assigning the optimal weight and the threshold to the BP neural network, and training the BP neural network through training data to obtain an accurate data prediction model and finish accurate prediction of soil humidity.
Further, the step 1 specifically includes dividing the data into a training set and a testing set, where the training set and the testing set include input data and target data, the input data includes air temperature, air humidity and illumination intensity, and the target data is soil humidity.
Further, in the step 3, the BP neural network is initialized, and the initial weight and the threshold of the neural network are obtained as chromosome codes, the number of chromosomes and the length of chromosomes of the set genetic algorithm; setting selection operation, mutation operation and crossover operation of chromosomes.
Further, the step 6 includes the following steps.
Step 6.1: during selection, the population individuals are rearranged by using a sorting method, and then are selected according to the probability of the adaptive function.
Step 6.2: in the crossing operation, the calculation mode of the crossing probability utilizes an adaptive function to calculate.
Step 6.3: during mutation operation, the mutation probability is calculated by using an adaptive function.
Further, the step 7 includes the following steps.
Step 7.1: and calculating the fitness value of each group of chromosomes, and judging whether the optimal weight and threshold are obtained or not according to the fitness value.
Step 7.2: by introducing the self-adaptive selection probability, the mutation probability and the cross probability, the optimal weight and threshold are obtained.
The invention has the beneficial effects.
In the agricultural production process, the quantity of the soil humidity sensors is greatly reduced by applying the neural network to predict the soil humidity, the soil structure is prevented from being damaged, the agricultural production technology is improved, and the prediction of the soil humidity is more convenient. The prediction model based on the BP neural network can effectively predict the soil humidity, provides convenience for monitoring data of the crop growth environment, and the prediction error of the BP neural network is large in the prediction process. The soil humidity prediction method based on the improved genetic algorithm for optimizing the BP neural network can effectively reduce prediction errors, the genetic algorithm has strong global optimization capability, the generation of local optimization is avoided, the prediction capability of the BP neural network is greatly improved, and therefore the prediction of the soil humidity is more accurate.
Example 2.
And (4) analyzing by experimental theory.
The BP neural network algorithm (Back Propagation) is a typical multilayer feedforward neural network, and learning and training are carried out through an error Back Propagation algorithm, and the operation characteristics of the neural network are data forward Propagation and error Back Propagation. The BP neural network mainly comprises an input layer, a hidden layer and an output layer, in the training process, the neural network continuously adjusts the weight and the threshold value between the input layer and the hidden layer and between the hidden layer and the output layer, and the training is stopped when the output value of the neural network is consistent with a target value, so that the neural network has good generalization capability.
The calculation formula of the BP neural network is as follows.
The working process of the BP neural network comprises the steps of firstly carrying out weighted summation on input data from an input layer to a hidden layer and then subtracting the threshold value, then carrying out mapping through a Sigmoid function to obtain output data of the hidden layer, finally carrying out weighted summation on the output data of the hidden layer from the hidden layer to the output layer and then subtracting the threshold value, and then carrying out mapping through the Sigmoid function to obtain the data of an output layer. The conventional BP neural network mainly adopts a data forward propagation and error backward propagation mode, and corrects the weight value and the threshold value of the network by adopting a gradient reduction method according to an error value, so that the error is continuously reduced to an expected value, and a correction formula of the weight value and the threshold value is shown as follows.
And (4) improving a genetic algorithm.
Genetic Algorithm (GA), which was originally proposed by John holland in the united states in the 70's 20 th century, was designed according to the rules of organism evolution in nature. The working principle of the traditional genetic algorithm is that input data is coded firstly, then selective crossing and mutation operation is carried out through certain probability until an individual with the maximum fitness is selected as a target value to be output, and then operation is stopped.
And (4) selecting a fitness function.
The fitness function is a standard for measuring the individual capacity in the population, and generally, a target function is selected as the fitness function of the genetic algorithm, the inverse of the square of the error is adopted as the fitness function in the algorithm, and the formula is shown as follows.
Improvement of the selection operator.
The traditional genetic algorithm often adopts a 'roulette' mode in the working process, the probability that individuals in a population are selected is random, the optimal individuals are probably lost through the selection mode, and a large error is generated in the actual operation process. Therefore, the selection operator is improved by first rearranging the population of individuals by using a ranking method, and a probability formula for each individual to be selected after the rearrangement is shown as follows.
And (5) improvement of a crossover operator.
Conventional genetic algorithms typically set the crossover probability to a constant between 0.3 and 0.8 during operation. In the operation process, the overall searching capability of the genetic algorithm is improved due to too high cross probability setting, but the adaptive capacity of the chromosome is reduced, and the overall searching capability and the convergence speed of the genetic algorithm are reduced due to too low cross probability setting. The crossover operator is improved, the change of the crossover probability can be adjusted according to the change of the fitness in the iterative process of the algorithm, and the improved crossover probability formula is shown as follows.
And (5) improvement of mutation operators.
Conventional genetic algorithms typically set the mutation probability to a constant between 0.001 and 0.1 during operation. In the initial stage of genetic algorithm operation, the fitness of population individuals is relatively low compared to the average fitness, so that the probability of mutation needs to be set to a small value, thereby retaining individuals with excellent genes in chromosomes. In the later stage of the genetic algorithm, the fitness of the population individuals is relatively higher than the average fitness, so that the probability of variation needs to be set to a larger value to improve the local search capability of the genetic algorithm. The mutation operator is improved, the variation of the mutation probability can be adjusted according to the variation of the fitness in the algorithm iteration process, and an improved mutation probability formula is shown as follows.
And (5) analyzing test results.
In the test, three data of air temperature, air humidity and illumination intensity are collected through a sensor, 1000 groups of data are collected, and the data are divided into a training group and a testing group testing model for training and testing.
And randomly dividing the data into two groups, selecting 980 groups of data as training data, selecting 20 groups of data as test data, inputting 980 groups of data into the prediction model to train the model, inputting the test data into the prediction model to detect the model, and evaluating the prediction model according to an error result.
Table 1 model prediction error.
As can be seen from the data in table 1, the average absolute error, the average absolute percentage error, and the root mean square error of the IGA-BP model are 0.0142, 0.0004, and 0.0634, respectively, and the indexes are improved by 0.0313, 0.0011, and 0.1402, respectively, compared to the BP model, and are improved by 0.0255, 0.0009, and 0.114, respectively, compared to the GA-BP model. The analysis data shows that the prediction effect of the IGA-BP model is better.
The invention discloses a soil humidity prediction method for optimizing a BP neural network based on an improved genetic algorithm.
The genetic algorithm is optimized, and the probabilities of a selection operator, a crossover operator and a mutation operator of the genetic algorithm are optimized, so that the optimization performance of the genetic algorithm is improved; the improved genetic algorithm is used for optimizing the BP neural network, and a soil humidity prediction model based on the BP neural network optimized by the improved genetic algorithm is established; analysis of test data shows that the improved genetic algorithm has better prediction effect in optimizing the BP neural network.
Claims (5)
1. A soil humidity prediction method for optimizing a BP neural network based on an improved genetic algorithm is characterized by comprising the following steps:
step 1: inputting data, and dividing the collected data into two groups, wherein one group is used as training data, and the other group is used as test data;
step 2: determining a topological structure of a neural network, and setting the number of neurons of each parameter of the neural network to include an input layer, a hidden layer and an output layer;
and step 3: initializing a BP neural network, and obtaining an initial weight and a threshold of the neural network;
and 4, step 4: initializing a genetic algorithm, and encoding an initial weight and a threshold;
and 5: setting a fitness function of a genetic algorithm, and taking an error square root reciprocal obtained by training a BP neural network as a fitness function value;
step 6: carrying out selection, crossing and mutation operations;
and 7: calculating a fitness value, judging whether a termination condition is met, if so, determining an optimal weight and a threshold, and if not, executing the step 6;
and 8: and after the optimal weight and the threshold are determined to be obtained, assigning the optimal weight and the threshold to the BP neural network, and training the BP neural network through training data to obtain an accurate data prediction model and finish accurate prediction of soil humidity.
2. The method for predicting soil moisture based on BP neural network optimization by improved genetic algorithm as claimed in claim 1, wherein the step 1 specifically comprises dividing data into training set and testing set, the training set and testing set further comprising input data and target data, wherein the input data comprises air temperature, air humidity, illumination intensity, and the target data is soil moisture.
3. The method for predicting soil moisture based on the improved genetic algorithm optimized BP neural network as claimed in claim 1, wherein in step 3, the BP neural network is initialized, and the initial weight and the threshold of the neural network are obtained as chromosome codes and chromosome number and length of the genetic algorithm; setting selection operation, mutation operation and crossover operation of chromosomes.
4. The method for predicting soil moisture based on the BP neural network optimization by the improved genetic algorithm as claimed in claim 1, wherein the step 6 comprises the following steps:
step 6.1: during selection operation, the population individuals are rearranged by using a sorting method, and then selection is carried out according to the probability of the self-adaptive function;
step 6.2: during cross operation, the calculation mode of the cross probability utilizes a self-adaptive function to calculate;
step 6.3: during mutation operation, the mutation probability is calculated by using an adaptive function.
5. The method for predicting soil moisture based on the BP neural network optimization by the improved genetic algorithm as claimed in claim 2, wherein the step 7 comprises the following steps:
step 7.1: calculating the fitness value of each group of chromosomes, and judging whether the optimal weight and threshold are obtained or not according to the fitness value;
step 7.2: by introducing the self-adaptive selection probability, the mutation probability and the cross probability, the optimal weight and threshold are obtained.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110435506.5A CN113221447A (en) | 2021-04-22 | 2021-04-22 | Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110435506.5A CN113221447A (en) | 2021-04-22 | 2021-04-22 | Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN113221447A true CN113221447A (en) | 2021-08-06 |
Family
ID=77088388
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110435506.5A Pending CN113221447A (en) | 2021-04-22 | 2021-04-22 | Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113221447A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113971517A (en) * | 2021-10-25 | 2022-01-25 | 中国计量大学 | GA-LM-BP neural network-based water quality evaluation method |
| CN114694766A (en) * | 2022-03-28 | 2022-07-01 | 武汉理工大学 | Red mud heavy metal content online prediction method, system, device and storage medium |
| CN117706282A (en) * | 2024-02-06 | 2024-03-15 | 国网安徽省电力有限公司营销服务中心 | Method and system for monitoring phase line loss in station division |
| CN118014009A (en) * | 2024-02-26 | 2024-05-10 | 广芯微电子（广州）股份有限公司 | Neural network initial value optimizing method based on genetic algorithm |
-
2021
- 2021-04-22 CN CN202110435506.5A patent/CN113221447A/en active Pending
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113971517A (en) * | 2021-10-25 | 2022-01-25 | 中国计量大学 | GA-LM-BP neural network-based water quality evaluation method |
| CN114694766A (en) * | 2022-03-28 | 2022-07-01 | 武汉理工大学 | Red mud heavy metal content online prediction method, system, device and storage medium |
| CN117706282A (en) * | 2024-02-06 | 2024-03-15 | 国网安徽省电力有限公司营销服务中心 | Method and system for monitoring phase line loss in station division |
| CN118014009A (en) * | 2024-02-26 | 2024-05-10 | 广芯微电子（广州）股份有限公司 | Neural network initial value optimizing method based on genetic algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN113221447A (en) | Soil humidity prediction method for optimizing BP neural network based on improved genetic algorithm | |
| CN113282122B (en) | Commercial building energy consumption prediction optimization method and system | |
| CN105488528B (en) | Neural network image classification method based on improving expert inquiry method | |
| CN106373022B (en) | BP-GA-based greenhouse crop planting efficiency condition optimization method and system | |
| CN110020712B (en) | Optimized particle swarm BP network prediction method and system based on clustering | |
| CN115099500B (en) | Water level prediction method based on weight correction and DRSN-LSTM model | |
| CN106650784A (en) | Feature clustering comparison-based power prediction method and device for photovoltaic power station | |
| CN113722980B (en) | Ocean wave height prediction method, ocean wave height prediction system, computer equipment, storage medium and terminal | |
| CN107169621A (en) | A kind of Dissolved Oxygen in Water Forecasting Methodology and device | |
| CN116542382A (en) | Sewage treatment dissolved oxygen concentration prediction method based on mixed optimization algorithm | |
| Priya et al. | An IoT based gradient descent approach for precision crop suggestion using MLP | |
| CN110109193A (en) | A kind of eggplant greenhouse temperature intellectualized detection device based on DRNN neural network | |
| KR102585381B1 (en) | The method, system and equipment for vegetation restoration or rehabilitation of simulating natural ecosystem based on machine learnig | |
| CN117575094B (en) | Crop yield prediction and optimization method and device based on digital twin | |
| CN109214503A (en) | Project of transmitting and converting electricity cost forecasting method based on KPCA-LA-RBM | |
| CN114580762A (en) | Hydrological forecast error correction method based on XGboost | |
| Shang et al. | Research on intelligent pest prediction of based on improved artificial neural network | |
| CN113379116A (en) | Cluster and convolutional neural network-based line loss prediction method for transformer area | |
| CN114897204A (en) | Method and device for predicting short-term wind speed of offshore wind farm | |
| CN110414115A (en) | A kind of wavelet neural network tomato yield prediction technique based on genetic algorithm | |
| Chen et al. | A water-saving irrigation decision-making model for greenhouse tomatoes based on genetic optimization TS fuzzy neural network | |
| CN114282702A (en) | Soil conditioning time sequence prediction method and system based on IGA-BP neural network | |
| CN110334869A (en) | A kind of mangrove forest ecological health forecast training method based on dynamic colony optimization algorithm | |
| CN116957164A (en) | Pesticide residue measurement method based on LightGBM-XGBoost integrated learning | |
| CN109472320A (en) | Crop growing stage model Cultivar parameter automatically corrects frame under condition of uncertainty |
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 |