CN111209679B - Genetic algorithm-based spatial interpolation method for heavy metal content in soil - Google Patents
Genetic algorithm-based spatial interpolation method for heavy metal content in soil Download PDFInfo
- Publication number
- CN111209679B CN111209679B CN202010031083.6A CN202010031083A CN111209679B CN 111209679 B CN111209679 B CN 111209679B CN 202010031083 A CN202010031083 A CN 202010031083A CN 111209679 B CN111209679 B CN 111209679B
- Authority
- CN
- China
- Prior art keywords
- new
- population
- individuals
- soil
- heavy metal
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Biophysics (AREA)
- Evolutionary Biology (AREA)
- General Engineering & Computer Science (AREA)
- Evolutionary Computation (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Biomedical Technology (AREA)
- Genetics & Genomics (AREA)
- Computational Linguistics (AREA)
- Mathematical Physics (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Probability & Statistics with Applications (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a genetic algorithm-based spatial interpolation method for the heavy metal content of soil, which comprises the following steps: carrying out gene coding on the content of the heavy metal observation points of the soil, and acquiring an observation point clustering center and an initial population by adopting a k-means clustering algorithm; pairing individuals in the population pairwise, and determining paired individuals p x ,p y Generated new individuals p new Obtaining the soil-related attribute parameter value of the new individual; for matched individuals p x ,p y Performing gene crossover operation to generate new individual p new I.e. the determined geographical location heavy metal content value; for new individuals p new Performing genetic variation to obtain new populationAnd to a new populationCarrying out adaptability evaluation; and generating updating iteration in the new population, and carrying out population merging on the new population after iteration.
Description
Technical Field
The invention relates to the technical fields of computers, soil science and ecology, in particular to a method for carrying out spatial data interpolation analysis on soil heavy metal content.
Background
The method comprises the steps of carrying out point distribution sampling on the heavy metal content of soil, and carrying out data interpolation on interpolation points according to sampling data, so that an estimated value of the whole observation area is obtained, and the method is a common problem in the field of soil heavy metal research. At present, 3 types of methods mainly solve the problem of spatial interpolation analysis of the heavy metal content of soil. The class 1 method is an interpolation method represented by a common kriging method based on geostatistics, and is characterized by the correlation of geographic space, including kriging method, ubiquitin method and the like; the class 2 method is a non-geostatistical method represented by inverse distance weighted interpolation, and is characterized in that the influence of an observation point on an interpolation point gradually weakens along with the increase of the distance, including RBF function method and the like; class 3 is a combination of the two, and different methods are applied to solve the local problem of data interpolation from different sides, and finally form a surrounding to realize data interpolation.
The genetic algorithm simulates the natural evolution and biological genetic process of the biological world, carries out biological evolution such as selection, crossover, mutation and the like among biological individuals, carries out population reproduction operation, and searches for an optimal solution in a global scope. Genetic algorithms have been widely used in many research fields for numerical optimization. The observation points of the heavy metals in the soil are used as initial individuals of a biological community to form an initial biological population, the individuals reproduce information, excellent individuals are reserved, inferior individuals are eliminated, and the population scale is gradually enlarged. And (3) carrying out adaptability evaluation on the population at the end of the algorithm, wherein new individuals reserved in the population are new interpolation point data.
The invention provides a genetic algorithm-based spatial interpolation method for the heavy metal content of soil based on bionics in computational intelligence.
Disclosure of Invention
In order to solve the technical problems, the invention aims to provide a genetic algorithm-based spatial interpolation method for the heavy metal content of soil.
The aim of the invention is achieved by the following technical scheme:
carrying out gene coding on the content of the heavy metal observation points of the soil, and acquiring an observation point clustering center and an initial population by adopting a k-means clustering algorithm;
pairing individuals in the population pairwise, and determining paired individuals p x ,p y Generated new individuals p new Obtaining the soil-related attribute parameter value of the new individual; a kind of electronic device with high-pressure air-conditioning system
For matched individuals p x ,p y Performing gene crossover operation to generate new individual p new I.e. the determined geographical location heavy metal content value;
for new individuals p new Performing genetic variation to obtain new populationAnd->Carrying out adaptability evaluation;
and generating updating iteration in the new population, and carrying out population merging on the new population after iteration.
One or more embodiments of the present invention may have the following advantages over the prior art:
the method searches the data of the interpolation point in the global data space range, and evaluates and controls the quality of a new individual, namely the quality of the data of the interpolation point in each stage of population evolution.
Drawings
FIG. 1 is a flow chart of a spatial interpolation method of soil heavy metal content;
FIG. 2 is a schematic representation of the selection range of individuals of a population when performing selection, crossover, variation;
FIG. 3 is a schematic diagram of a new individual geographic location distribution area;
FIG. 4 is one embodiment of a method of spatial interpolation of soil heavy metal content;
FIG. 5 is a second embodiment of a spatial interpolation method for soil heavy metal content.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in further detail with reference to the following examples and the accompanying drawings.
As shown in FIG. 1, the method for spatial interpolation of soil heavy metal content comprises the following steps
Obtaining k clustering centers, k initial populations and member individuals thereof after gene coding and k-means cluster analysis of a certain heavy metal content observed value of soil and soil environment parameters thereof; selecting pairing, determining new individual positions, gene crossing and gene mutation operations in the population to obtain a new population, and carrying out adaptability evaluation on the new population; and carrying out population merging operation on the new population after iteration. The following strategy is adopted to end the algorithm.
Algorithm end policy one: the whole population iterates and accumulates to the appointed times;
algorithm ending strategy two: the total number of individuals of the new population reaches the expected number;
algorithm ending strategy three: there was no significant improvement in the fitness evaluation and even a decrease in population quality.
Carrying out gene coding on the content of the heavy metal observation points of the soil, and acquiring an observation point clustering center and an initial population by adopting a k-means clustering algorithm; dividing all observation point individuals into k initial populations according to two adjacent distances, wherein p i For the individual observation points, lon and lat are longitude and latitude of the observation points, n is the number of the individual observation points and P k For k initial populations and their member individuals,is a population->Is a number of individuals.
p i ＝＜lon，lat，...＞
P 0 ＝{p 1 ，p 2 ，...，p n }，1≤k≤n/2
P 1 ＝P 0
Dividing all individuals into k initial populations and meeting the condition (1) to obtain k clustering centers and k initial populations P k 。
The binary system is adopted to carry out gene coding on the heavy metal content of the soil at the observation point, and the gene coding comprises an integer part and a decimal part, and is shown as a formula (2). The heavy metal content of the soil of all observation points and the predicted value points codes a gene sequence with equal length (n+m), and the deficiency positions are filled with 0.
a n-1 a n-2 …a 0 ·a -1 a -2 …a -m a i ＝0or1-m≤i≤n-1 (2)
For any one populationTwo-to-two body pairing selection operations are performed. Population->The range of pairing selection is all individuals within the population, if the population +.>Is combined with other species->Is closer to (less than a valve)Value), the population ∈>Is included in the population +.>As shown in fig. 2. The individuals selected in the pairing are denoted < p x ，p y The policy of pairing selection may be the following principle:
the principle of approximation: preferentially selecting 2 individuals close to each other;
the random principle: randomly selecting 2 individuals;
the combination principle is as follows: mixed selection of the above 2 selection principles.
For paired individuals<p x ,p y >The new individual generated is determined to be the geographic location. Setting the influence range of parent individuals on new individuals as radius r,2 parent individuals<p x ,p y >The radius of the circumscribed circle of the influence range is R, and the geographical position range of the new individual is an area formed by 2 parent circular areas and 2 circumscribed circles, which is shown in fig. 3. Determining paired individuals with uniform distribution probability in the region<p x ,p y >New individual p of (2) new Geographic location. After determining the geographical position of the new individual, the soil-related attribute parameter values of the individual can be obtained, including soil type, elevation, organic matter content, soil pH value, soil cation exchange capacity, distance from the parent, pollution source and the like.
For paired individuals<p x ,p y >Performing gene crossover operation to generate new individual p new I.e. the heavy metal content value of the determined geographical location. Is provided with<p x ,p y >And (3) respectively, calculating the gene crossing position N and meeting the condition (4), and determining dominant precursors.
n-1≤N≤0 (4)
Soil type: if a new individual p new Soil type and 2 precursors of (2)<p x ,p y >The 2 parents participate in the crossover with equal probability; if the soil type of the new individual is equal to that of 1 parent (e.g., p x ) The same, the parent participates in crossover with a higher probability, i.e., retains more genes of the parent; if the new individual is of a different soil type than 2 parents, 2 parents participate in the crossover with equal probability, or the new individual is abandoned and the parents are reselected. Finally, the contribution degree of 2 parent soil types to new individuals is determined and respectively calculated asAnd->Expressed as 2 percentages, the sum of 2 being 1.
Elevation: under the influence of gravity and precipitation, the heavy metal in the soil has the characteristic of migrating along with the water flow direction from high to low places. If 2 parents have the same elevation, the parents participate in the intersection with equal probability; if parent p x With high topography, the crossing is participated with higher probability; if the new individual has a higher topography than 2 parents, then the elevation factor is ignored or the new individual is abandoned and the parents are reselected. Finally, the contribution degree of the elevation of 2 parents to the new individual is determined asAnd->
Soil organic matter content: the soil with high organic matter content has stronger adsorption capacity to certain heavy metals, thereby improving the fixation and accumulation of the heavy metals in the soil. If 2 parents have the same soil organic matter contentThen the intersection is participated in with equal probability; if the parent px has higher soil organic matter content, the parent px participates in the crossing with higher probability; if a new individual has a higher soil organic matter content than 2 parents, the organic matter content factor is ignored or the new individual is abandoned and the parents are reselected. Finally determining the contribution degree of the soil organic matter content of 2 parents to new individuals, which are respectively calculated asAnd->
Soil pH value: the heavy metal release potential increases as the pH of the soil decreases. If 2 precursors have the same pH value, the crossover is participated in with equal probability; if parent px has a low pH, then the crossover is participated with a higher probability; if a new individual has a lower pH than 2 parents, the pH factor is ignored or the new individual is discarded and the parents are reselected. Finally determining the contribution degree of the soil pH values of 2 parents to new individuals, which are respectively calculated asAnd->
Soil cation exchange amount (CEC): the higher the CEC value of the soil, the higher the net negative charge of the soil particles, so that the more the adsorption points of cations are, in particular the stronger the specific adsorption of heavy metal elements are, and if 2 parents have the same CEC value, the equal probability of participating in the crossing is adopted; if parent px has a larger CEC value, participate in the crossover with a higher probability; if the new individual has a greater CEC value than 2 parents, the CEC influencing factors are ignored or the new individual is abandoned and the parents are reselected. Finally, the contribution degree of CEC of 2 parents to new individuals is determined asAnd->
Distance from parent: the new individuals are distributed in the blocks shown in fig. 3, and the closely-spaced parents have large influence on the new individuals and high correlation, and participate in gene crossover with higher probability. Finally determining the contribution degree of the distance between the parent and the new individual to the new individual, which are respectively calculated asAnd->
According to the influence factors, calculating the comprehensive contribution degree of 2 parents to the heavy metal content of a new individual, which is expressed as w x And w y Dominant precursors are determined, see formulas (5) and (6).
Let dominant parent be p x Calculating the gene crossing position N to generate a new individual p new See equations (7), (8), where rand produces random perturbations.
N＝[n×(1-w x )×rand] (7)
For new individuals p new Genetic variation was performed. The mutation operation may employ the following strategy.
Low probability policy: the new individuals are similar to 2 parents in soil-related attribute parameter values;
medium probability policy: the new individuals are similar to 1 parent in the soil-related attribute parameter values;
high probability policy: the 3 individuals differ significantly in the soil-related attribute parameter values.
The probability of gene mutation determined according to the mutation strategy is p var The number of mutated genes is p var X (n+m) ×rand, and uniformly occurs in new individuals p new Is a sequence of a gene of (a). New individual p finally produced new Adding to a populationIs a kind of medium.
For new individuals p new The genetic variation can be performed by using a pollution source strategy.
High-order gene mutation: new individuals p new The neighborhood has a pollution source and the elevation is lower than the pollution source, so that variation occurs in a high-order gene region of a new individual according to a certain probability;
median genetic variation: new individuals p new The pollution source exists in the nearby area, and the elevation is not higher than the pollution source, so that the median gene area of the new individual is mutated according to a certain probability;
low-level genetic variation: new individuals p new Far from the pollution source, the low-level gene region of the new individual is mutated with a certain probability.
After the selection, crossing and mutation operation, a new population is obtainedThe population was assessed for fitness. New populationRepresented by formula (9), wherein>Representing population->Is->Representing population->Is a new subject.
In the whole populationIs a data of (1) by inverse distance weighting (or kriging) pair ++>Interpolation is carried out to obtain +.>Estimate of +.>The new population adaptation employs a decision coefficient (R 2 ) Root Mean Square Error (RMSE) and relative analysis error (RPD) as evaluation indices, R 2 And the larger the RPD and the smaller the RMSE, the stronger the adaptability of the new population, the receiving the population and replacing the original population, otherwise, the new individual is abandoned +.>The population is returned to the original state->And re-evolved.
The merging between populations is checked and performed after an update iteration occurs inside the populations.
One of the conditions for population merger is that the number of adjacent individuals in adjacent populations reaches a certain level.
The second condition of the group merging is that adopting the k-means clustering algorithm to respectively set 2 and 1 clustering centers, and settingEvaluation index in case of 1 cluster centerWithout significant increase.
The third condition for population combination is that after combination, fitness evaluation and evaluation index (R 2 RMSE, RPD) meets the requirements of reception. After the populations are combined, a new population is formed.
One implementation of this embodiment is implemented in parallel in a multi-threaded manner, as shown in fig. 4.
Firstly, normalizing the observed value of the heavy metal content in soil and the soil environment parameters thereof into database records, wherein each record corresponds to 1 observation point, namely 1 original individual.
And (3) finishing gene coding in the main thread, performing k-means cluster analysis, and dividing all database records into k initial populations.
And respectively starting k working threads for k initial populations, performing selection, crossing and mutation operations in the populations and the adjacent domains thereof, determining the geographic position of a new individual, and performing adaptability evaluation on the new populations.
Two-by-two combinations are implemented between populations. After the working thread completes one round of iterative updating of the group, whether the condition of group merging is met is checked. And when the population merging condition is met, waiting for the other population to finish the iterative updating of the current round, and then implementing the population merging. After merging, terminating 1 working thread, and continuing population evolution iteration by the other 1 working thread.
And when all the populations iterate to the appointed times, the algorithm is ended, and finally all the individual data are output.
The second embodiment of the present invention is serial implementation with the third party tool and custom plug-in.
Firstly, normalizing soil heavy metal content observation values and environmental background data thereof into ArcGis data format, and establishing raster images.
And (3) carrying out cluster analysis on the raster images according to geographic positions in ArcGis by adopting a Pyclumter tool to obtain k cluster centers and k initial populations.
An interpolation point grid, i.e., the geographical location of the new individual, is established for the entire interpolation area in ArGis, and a configuration parent is selected for each interpolation point and satisfies the conditions shown in fig. 3. At the beginning of population iteration, part of interpolation points may not be configured to the parent body meeting the condition, but are successfully configured in the middle and later stages of the iteration.
1 custom plug-in was created with Python in ArcGis and population iterations were performed in a serial fashion, i.e., only 1 population was performing the iteration at a particular time, as shown in fig. 5.
When new individuals of all interpolation point grids are completed, or when all populations iterate to the designated times, the algorithm is ended, and finally all individual data are output.
Although the embodiments of the present invention are described above, the embodiments are only used for facilitating understanding of the present invention, and are not intended to limit the present invention. Any person skilled in the art can make any modification and variation in form and detail without departing from the spirit and scope of the present disclosure, but the scope of the present disclosure is still subject to the scope of the appended claims.
Claims (1)
1. A genetic algorithm-based spatial interpolation method for soil heavy metal content, which is characterized by comprising the following steps:
carrying out gene coding on the content of the heavy metal observation points of the soil, and acquiring an observation point clustering center and an initial population by adopting a k-means clustering algorithm;
pairing individuals in the population pairwise, and determining paired individuals p x ,p y Generated new individuals p new Obtaining the soil-related attribute parameter value of the new individual; a kind of electronic device with high-pressure air-conditioning system
For matched individuals p x ,p y Performing gene crossover operation to generate new individual p new Determining a heavy metal content value of the geographic location;
for new individuals p new Performing genetic variation to obtain new populationAnd->Carrying out adaptability evaluation;
generating update iteration in the new population, and carrying out population merging on the new population after iteration;
carrying out gene coding on soil heavy metal content data by adopting binary coding;
the k-means clustering algorithm performs clustering analysis according to the distance between observation points, and takes the minimum average value of the distance between the observation points as an optimal cluster;
the pairing selection range is a position range of a new individual, wherein the position range is formed by all individuals in the population and individuals in other populations with adjacent boundaries, and the circular area of the paired individuals and the area formed by the circumscribed circles of the paired individuals are used as the position range of the new individual, and the positions of the new individual are determined according to uniform distribution probability;
the policy rules for pairing selection are: a nearest neighbor principle, a random principle and a combination principle;
the soil related attribute parameter values comprise soil type, elevation, soil organic matter content, soil pH value, soil cation exchange capacity, distance between the soil cation exchange capacity and a parent body and pollution sources;
the genetic variation operation is to perform genetic variation operation on the interpolation point data according to the soil type, elevation, soil organic matter content, soil pH value, soil cation exchange capacity, parent distance and pollution source of the paired individuals and the new individuals to generate new interpolation point data;
for new individuals p new The implementation of the genetic variation operation adopts the following strategies: a low probability policy, a medium probability policy, and a high probability policy; or (b)
For new individuals p new Carrying out genetic variation operation by adopting pollution source strategies, including higher genetic variation, median genetic variation and lower genetic variation;
the population adaptability evaluation is to interpolate the observation point data by using the observation point and interpolation point data in the population, and to evaluate the population adaptability by using the original value and the predicted value of the observation point;
the condition of the population combination is that the number of adjacent individuals of adjacent populations on the boundary reaches a certain degree, and the cluster analysis and the population adaptability evaluation are carried out.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010031083.6A CN111209679B (en) | 2020-01-13 | 2020-01-13 | Genetic algorithm-based spatial interpolation method for heavy metal content in soil |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010031083.6A CN111209679B (en) | 2020-01-13 | 2020-01-13 | Genetic algorithm-based spatial interpolation method for heavy metal content in soil |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111209679A CN111209679A (en) | 2020-05-29 |
| CN111209679B true CN111209679B (en) | 2023-09-29 |
Family
ID=70790089
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010031083.6A Active CN111209679B (en) | 2020-01-13 | 2020-01-13 | Genetic algorithm-based spatial interpolation method for heavy metal content in soil |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111209679B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN113159219B (en) * | 2021-05-14 | 2022-04-08 | 广东工业大学 | Soil pollutant content interpolation method coupling genetic algorithm and neural network |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102158799A (en) * | 2011-01-24 | 2011-08-17 | 东软集团股份有限公司 | Method and system for determining recommended passage place sequence |
| CN102855392A (en) * | 2012-08-10 | 2013-01-02 | 河海大学 | Ground settlement space monitoring method through Kriging interpolation based on genetic algorithm |
| CN103745258A (en) * | 2013-09-12 | 2014-04-23 | 北京工业大学 | Minimal spanning tree-based clustering genetic algorithm complex web community mining method |
| CN106651100A (en) * | 2016-10-12 | 2017-05-10 | 华南理工大学 | Internet-of-Vehicles optimal vehicle-mounted monitoring point-based air quality evaluation system and method |
| CN107038479A (en) * | 2017-05-08 | 2017-08-11 | 湖北科技学院 | A kind of hybrid parallel genetic algorithm for clustering of variable length chromosome coding |
| CN109633748A (en) * | 2018-11-12 | 2019-04-16 | 中国石油大学(华东) | A kind of seismic properties preferred method based on improved adaptive GA-IAGA |
| CN110188785A (en) * | 2019-03-28 | 2019-08-30 | 山东浪潮云信息技术有限公司 | A kind of data clusters analysis method based on genetic algorithm |
-
2020
- 2020-01-13 CN CN202010031083.6A patent/CN111209679B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102158799A (en) * | 2011-01-24 | 2011-08-17 | 东软集团股份有限公司 | Method and system for determining recommended passage place sequence |
| CN102855392A (en) * | 2012-08-10 | 2013-01-02 | 河海大学 | Ground settlement space monitoring method through Kriging interpolation based on genetic algorithm |
| CN103745258A (en) * | 2013-09-12 | 2014-04-23 | 北京工业大学 | Minimal spanning tree-based clustering genetic algorithm complex web community mining method |
| CN106651100A (en) * | 2016-10-12 | 2017-05-10 | 华南理工大学 | Internet-of-Vehicles optimal vehicle-mounted monitoring point-based air quality evaluation system and method |
| CN107038479A (en) * | 2017-05-08 | 2017-08-11 | 湖北科技学院 | A kind of hybrid parallel genetic algorithm for clustering of variable length chromosome coding |
| CN109633748A (en) * | 2018-11-12 | 2019-04-16 | 中国石油大学(华东) | A kind of seismic properties preferred method based on improved adaptive GA-IAGA |
| CN110188785A (en) * | 2019-03-28 | 2019-08-30 | 山东浪潮云信息技术有限公司 | A kind of data clusters analysis method based on genetic algorithm |
Non-Patent Citations (1)
| Title |
|---|
| Ping Zhou 等.Source mapping and determining of soil contamination by heavy metals using statistical analysis, artificial neural network, and adaptive genetic algorithm.《Journal of Environmental Chemical Engineering》.2015,第2569-2579页. * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111209679A (en) | 2020-05-29 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109359162B (en) | GIS-based school site selection method | |
| Salcedo-Sanz et al. | New coral reefs-based approaches for the model type selection problem: a novel method to predict a nation's future energy demand | |
| CN106778826A (en) | Based on the hereditary Hybrid Clustering Algorithm with preferred Fuzzy C average of self adaptation cellular | |
| CN109902808B (en) | Method for optimizing convolutional neural network based on floating point digital variation genetic algorithm | |
| CN107977711B (en) | Multi-agent genetic method oriented to 'three-line' cooperative optimization | |
| CN109872330A (en) | A kind of two-dimentional Otsu Fast image segmentation method for improving lion group's optimization | |
| CN113627479B (en) | Graph data anomaly detection method based on semi-supervised learning | |
| CN111985623A (en) | Attribute graph group discovery method based on maximized mutual information and graph neural network | |
| CN111209679B (en) | Genetic algorithm-based spatial interpolation method for heavy metal content in soil | |
| Zhang et al. | Basic farmland zoning and protection under spatial constraints with a particle swarm optimisation multiobjective decision model: a case study of Yicheng, China | |
| CN115051925B (en) | Time-space sequence prediction method based on transfer learning | |
| CN115249054A (en) | Improved hybrid multi-target particle swarm optimization feature selection algorithm | |
| CN112381284B (en) | Improved genetic algorithm for multi-station path optimization of unmanned connection vehicle | |
| CN114329941A (en) | Optical transport network transmission planning optimization method and system | |
| CN117078312B (en) | Advertisement putting management method and system based on artificial intelligence | |
| CN116756207A (en) | Network key node mining method based on discount strategy and improved discrete crow search algorithm | |
| CN113328466B (en) | Electric vehicle charging scene generation method | |
| CN113722853B (en) | Group intelligent evolutionary engineering design constraint optimization method for intelligent computation | |
| CN115544869A (en) | Multi-target optimization method, system, equipment and medium for high-power microwave source | |
| CN113343565A (en) | Neighborhood effect mode construction and CA simulation method and system considering spatial heterogeneity | |
| CN114581470A (en) | Image edge detection method based on plant community behaviors | |
| KR102103578B1 (en) | Method for Selecting Asset Portfolio | |
| CN111754533A (en) | Image segmentation method based on improved genetic algorithm and K-mean algorithm | |
| CN113159219B (en) | Soil pollutant content interpolation method coupling genetic algorithm and neural network | |
| Wang et al. | Application of travel management system based on route inquiry |
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 |