CN102184328A - Method for optimizing land use evolution CA model transformation rules - Google Patents
Method for optimizing land use evolution CA model transformation rules Download PDFInfo
- Publication number
- CN102184328A CN102184328A CN2011101191680A CN201110119168A CN102184328A CN 102184328 A CN102184328 A CN 102184328A CN 2011101191680 A CN2011101191680 A CN 2011101191680A CN 201110119168 A CN201110119168 A CN 201110119168A CN 102184328 A CN102184328 A CN 102184328A
- Authority
- CN
- China
- Prior art keywords
- model
- cellular
- evolution
- soil utilization
- land use
- 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
Images
Abstract
The invention provides a method for optimizing land use evolution CA model transformation rules, and the method comprises the following steps: firstly, according to the multitemporal spatiotemporal land use data of a studied area, selecting factors influencing the land use change of the studied area as the spatial characteristic variables of land use evolution CA; establishing a Logistic regression method based land use evolution CA model, selecting sampling point data, and calculating the influence weight of each space variable; and optimizing the parameters of the land use evolution CA model and establishing an evolution programming algorithm based land use evolution CA model by using an evolution programming method, and finally, verifying the simulation accuracy and efficiency of the model. Compared with the existing commonly-used method for obtaining land use evolution CA model transformation rules, the method provided by the invention is simpler in operation, faster in convergence speed and higher in simulation precision; and compared with other methods for obtaining land use evolution CA model transformation rules, the method provided by the invention is more identical with the essential characteristics of spatiotemporal land use evolution.
Description
Technical field
The invention belongs to the geography information science and technology field, be specifically related to introduce the transformation rule that Evolutionary Programming Algorithm is optimized magnanimity space-time soil utilization evolution CA analogy model.
Background technology
Cellular automaton (Cellular Automata, CA) be the dynamical system of the individual interaction of a kind of microcosmic, time and spatial discretization, proposed the forties in 20th century by U.S. mathematician Ulam and Neumann the earliest, the back has been provided its definition and has been applied to complex system simulation in the eighties by Britain computational science man Wolfram.CA has powerful spatial operation ability, be usually used in the research of self-organizing system evolution process, it is all to disperse a kind of time, space, state, and steric interaction and time cause-effect relationship all are local grid kinetic model, has the ability of Simulation of Complex system time evolutionary process.Its research thinking of this " from bottom to top ", the individual behavior that has demonstrated fully the complication system part produces the theory of the overall situation, orderly pattern, is highly suitable for the simulation and the prediction of complicated geographical process.In recent years, more and more scholars utilizes cellular automaton to simulate soil utilization variation, and has obtained a lot of significant achievements in research.These studies show that, can simulate complicated city's spatial structure by simple local transitions rule, embodied the marrow of " complication system is from the interaction of simple subsystem " this complexity science, developing to study for the soil utilization provides reliable basis.
The key problem of soil utilization evolution CA is the definition of transformation rule, and so-called transformation rule is exactly to determine the next kinetic function of this cellular state constantly according to cellular current state and neighbours' situation thereof, simply say, and be exactly a state transition function.Transformation rule is described the logical relation of simulation system, relates to numerous space variables that have multicollinearity, and they determine the result of spatial variations jointly.So how to determine the weight and the parameter of various space variables in the transformation rule, become the emphasis and the difficult point problem of soil utilization evolution CA research.
The transformation rule of determining soil utilization evolution CA at present mainly contains following several method.
Adopt analytical hierarchy process (AHP) and multiple criteria to differentiate the optimized parameter assembled scheme that (MCE) determines soil utilization evolution CA, but this method can't be eliminated the negative effect of the multiple conllinear of space variable, therefore, difficult accurately simulation soil utilization evolution phenomenon.
Adopting traditional decision-tree is that transformation rule is determined in representative with the See5.0 decision-tree model, then is absorbed in the situation of local optimum easily.Adopt the method for nuclear learning machine to have the unintelligible and big problem of operand of transformation rule physical significance, the same neural network method that adopts is obtained transformation rule automatically, though can determine model parameter and model structure very easily, eliminate the drawback that conventional method is brought, the transformation rule physical significance is indeterminate to wait problem slowly with speed of convergence but exist equally.
The method that adopts Logistic to return is determined transformation rule, comparatively clear physical significance is arranged, but extract complicated physical phenomenon rule with linear method, seem too simple, therefore be necessary the parameter of obtaining based on the Logistic homing method is optimized processing,, can keep the physical significance of former transformation rule on the one hand such as adopting genetic algorithm optimization to obtain transformation rule, also can improve the precision of modeling on the other hand, but but face problems such as complicated operation, freight volume are big.Simultaneously, the space-time soil utilizes delta data to have characteristics such as magnanimity, higher-dimension, and the search volume that must increase algorithm has increased the blindness of searching for.
Therefore explore the transformation rule of new algorithm optimization soil utilization evolution CA, the physical significance of clear and definite transformation rule, improve the operational efficiency obtain soil utilization evolution CA and be necessary, this also is value of the present invention place, in view of the advantage of Evolutionary Programming Algorithm aspect following:
(1) from the modern molecular biology viewpoint, evolutional programming is based on a kind of neutral theory of biological evolution, and it mainly embodies is evolution on the population level, emphasizes the behavior contact between individuality, and genetic algorithm is the evolution on the gene level, emphasizes the gene contact between individuality.In general extreme adaptability selection can cause precocity, and evolutional programming does not then have this drawback, means that it has good robustness.
(2) sudden change is the unique method that evolutional programming produces new colony, and it does not adopt reorganization or commutating operator.
Therefore computation complexity has reduction significantly than genetic algorithm.Simultaneously, the mutation operator of sudden change adopts the mode of the stochastic variable of Normal Distribution, is specially adapted to be subjected to the model of multiple independent random factor affecting.
(3) fast convergence rate of evolutional programming, the computational accuracy height, and can change convergence of algorithm speed and computational accuracy, dirigibility and extremely well-adapted by the quantity of adjustment population and the weight factor of mutation operator.
Therefore we adopt Evolutionary Programming Algorithm to optimize the transformation rule of soil utilization evolution CA.
Summary of the invention
Technical matters to be solved of the present invention is to obtain the shortcoming of soil utilization evolution CA transformation rule in order to remedy conventional method, by introducing new algorithm, optimize the transformation rule of soil utilization evolution CA, and mechanism and physical significance that soil utilization evolution CA model more can the utilization of clear sign soil be developed.
The present invention adopts following technical scheme for achieving the above object:
A kind of soil utilization evolution CA model conversion rule optimization method comprises the steps:
Steps A according to being studied regional multidate space-time land use data, selects influence to be studied the space characteristics variable of the factor of regional soil utilization variation as soil utilization evolution CA;
Step B according to the space characteristics variable that steps A is selected, sets up the soil utilization evolution CA model based on the Logistic homing method, selects the sampling point data, and calculates the weighing factor of each space variable;
Step C adopts Evolutionary Programming Algorithm, optimizes soil utilization evolution CA model parameter;
Step D sets up the soil utilization evolution CA model based on Evolutionary Programming Algorithm;
Step e, based on the constructed soil utilization evolution CA model of step D, the soil utilization of simulation magnanimity space-time is developed, and the simulation precision of verification model and operational efficiency.
The present invention adopts technique scheme to have following beneficial effect:
The present invention is on classical Logistic CA model based, consider the characteristics of magnanimity space-time land use data, make full use of the advantage of Evolutionary Programming Algorithm, optimize the transformation rule of soil utilization evolution CA, and foundation model is being compared with conventional soil utilization evolution CA model aspect the efficient of operation and the accuracy of simulation at provincial regional scale, comparative result shows: the more conventional soil of institute's established model utilization evolution CA model, as genetic algorithm etc., operational efficiency and precision all are improved largely, and have proved the operational efficiency and the accuracy of simulation advantage of institute's established model.
Soil utilization evolution CA analogy model transformation rule acquisition methods (as analytical hierarchy process, neural network algorithm, the principal component analysis (PCA) etc.) operation that the present invention uses always more at present is more simple, speed of convergence is faster, simulation precision is higher, and this algorithm is based on the essential characteristic of evolutional basic thought than the more identical space-time of other soil utilization evolutions CA analogy model transformation rule acquisition methods soil utilization evolution.
Description of drawings
Fig. 1 is a technical scheme process flow diagram of the present invention.
Fig. 2 is the process flow diagram of Evolutionary Programming Algorithm.
Specific embodiments
Be described in further detail below in conjunction with the enforcement of accompanying drawing technical scheme.
As shown in Figure 1, idiographic flow of the present invention is as follows:
The first step is analyzed not the spatial data of phase simultaneously, and in conjunction with these regional actual conditions, selects influence the factor of this soil, zone utilization variation, such as from intown distance, from distance of main roads or the like.
Second step, set up the Logistic-CA model, its function of state is
I in the formula, j are respectively the ranks number at cellular place,
With
Be respectively cellular (i, j) constantly and the state in the t moment at t+1,
For the neighborhood cellular at t function of state constantly, N is the quantity of cellular in the neighborhood, comprises the center cellular.
In the formula
Expression neighborhood cellular to cellular (i, influence j).
Suppose that any one cellular is that the local probability of city state is from non-city state exchange
, this probability is subjected to the variable influence that the first step is chosen, when then determining probability with the Logistic homing method,
Form be:
In the formula
Be that cellular is the local transitions probability of city state from non-city state exchange under the space variable effect,
(P=1,2 ..., m), be the space variable of selecting,
(P=0,1,2 ..., m) be the weight of space variable.
According to formula 1 and analyze restrictive factors such as local economy situation, macro policy, simultaneously,, add random entry for the randomness of outstanding urban development, then cellular is that the final transition probability of city state can be expressed as from non-city state exchange:
In the formula
Be the restrictive condition whether cellular can transform, γ is the random number between 0 ~ 1, and α is a constant of expression annoyance level size,
Factor immediately for urban development.
Then cellular at next state constantly is
In the formula
The expression cellular (i, j) at t+1 state constantly,
The expression cellular (i, j) at t transition probability constantly,
The probability threshold value that the representation element dysuria with lower abdominal colic is changed, when
Greater than
The time, this cellular then is converted to urban land, otherwise then keeps original state.
According to above-mentioned formula, select the spatial data of two periods, from the cellular that is converted to urban land and the cellular that is not converted to urban land, select a certain proportion of sampling point respectively, the ratio height can improve the precision of inverted parameters, but need the plenty of time, travelling speed can be improved and ratio is low, but inversion accuracy can be reduced.Therefore need to select rational proportion,, be finally inversed by the weight parameter of each space variable in conjunction with the space variable parameter according to regional actual conditions.
The 3rd step, utilize Evolutionary Programming Algorithm, optimize soil utilization evolution CA model parameter; As shown in Figure 2, specific practice is as follows:
(1) expression way of problem identificatioin, the i.e. objective function of model
And model parameter vector (
), need to suppose to optimize
Individual parameter.
(2) produce initial population at random
, comprise
Individuality
, promptly population scale is
, wherein 1 individuality is exactly 1 model parameter vector, and calculates each individual adaptive value (target function value):
(3) produce new colony with following operation:
2) intersect: to M the individuality of selecting
Implement certain interlace operation, intersect such as on 2 individualities, implementing single-point: given parent individuality
With
, at random from
The individual position that is arranged in adjacent element is selected one as the point of crossing, such as the
Individual element and
Position between the individual element exchanges two parent individualities then and is produced descendants's individuality by the separated part in point of crossing, promptly
With
3) variation: the individuality after intersecting is implemented certain mutation operation, make a variation such as single-point: given parent individuality
, evenly element of selection at random is as change point, and promptly each is put selecteed probability and is
, such as
Individual element increases the random quantity of a Normal Distribution then to the element of selecting
Thereby, produce descendants's individuality, promptly
4) calculate the fitness of descendants's individuality of generation newly;
5) select: select defect individual according to certain strategy in descendants's individuality of individuality from current population and generation and form population of future generation, such as blocking selection: descendants's individuality of individuality in the current population and generation is arranged (supposing that fitness is the bigger the better) from high in the end according to their fitness, get top
Individuality is as population of future generation.
(4) carry out (3) repeatedly,, select the optimum solution of optimized individual as evolutional programming until satisfying end condition (restriction of computational resource or found optimum solution).
In the 4th step, simulate provincial yardstick soil utilization evolution situation; Specific practice is as follows:
Parameter substitution CA model after will optimizing with Evolutionary Programming Algorithm is set certain iterations (100-200 time) then, and simulation soil utilization is developed.
The 5th step, obtain the simulation precision of model from changing overall accuracy and two angles of space layout, use the operational effect that Kappa coefficient and Moran ' I index come discrimination model respectively, and compare with other models, the simulation precision of verification model, the working time of computation model, and compare the operational efficiency of verification model with other models.Wherein overall accuracy is by pointwise method relatively, also be about to (the i of analog result, j) (the i of cellular and actual conditions, j) cellular is compared, if both land use pattern is identical, then simulation is correct, otherwise then simulates mistake, and the ratio of simulating correct cellular number and all cellular numbers is overall accuracy.Moran ' s I then can utilize Spatial Autocorrelation in the Spatial Statistic Tools module of ArcMap software (Moran ' s I) to calculate, the result of calculation that compares the two then, numerical value is close represents that then the space distribution of the two is close, analog result is more accurate, otherwise then analog result is relatively poor.
Claims (5)
1. a soil utilization evolution CA model conversion rule optimization method is characterized in that, comprises the steps:
Steps A according to being studied regional multidate space-time land use data, selects influence to be studied the space characteristics variable of the factor of regional soil utilization variation as soil utilization evolution CA;
Step B according to the space characteristics variable that steps A is selected, sets up the soil utilization evolution CA model based on the Logistic homing method, selects the sampling point data, and calculates the weighing factor of each space variable;
Step C adopts Evolutionary Programming Algorithm, optimizes soil utilization evolution CA model parameter;
Step D sets up the soil utilization evolution CA model based on Evolutionary Programming Algorithm;
Step e, based on the constructed soil utilization evolution CA model of step D, the soil utilization of simulation magnanimity space-time is developed, and the simulation precision of verification model and operational efficiency.
2. soil utilization evolution CA model conversion rule optimization method according to claim 1, it is characterized in that: the detailed process of described step B is as follows:
B-1 sets up the Logistic-CA model, and its function of state is
I in the formula, j are respectively the ranks number at cellular place,
With
Be respectively cellular (i, j) constantly and the state in the t moment at t+1,
For the neighborhood cellular at t function of state constantly, N is the quantity of cellular in the neighborhood, comprises the center cellular;
B-2 supposes that any one cellular is that the local probability of city state is from non-city state exchange
, this probability is subjected to the variable influence that the first step is chosen, when then determining probability with the Logistic homing method,
Form be:
In the formula
Be that cellular is the local transitions probability of city state from non-city state exchange under the space variable effect,
(P=1,2 ..., m), be the space variable of selecting,
(P=0,1,2 ..., m) be the weight of space variable;
B-3 according to formula (1) and analyze restrictive factors such as local economy situation, macro policy, adds random entry simultaneously, and then cellular is that the final transition probability of city state can be expressed as from non-city state exchange:
In the formula
Be the restrictive condition whether cellular can transform, γ is the random number between 0 ~ 1, and α is a constant of expression annoyance level size,
Factor immediately for urban development;
Then cellular at next state constantly is
(5)
In the formula
The expression cellular (i, j) at t+1 state constantly,
The expression cellular (i, j) at t transition probability constantly,
The probability threshold value that the representation element dysuria with lower abdominal colic is changed, when
Greater than
The time, this cellular then is converted to urban land, otherwise then keeps original state;
B-4, according to above-mentioned formula, select the spatial data of two periods, from the cellular that is converted to urban land and the cellular that is not converted to urban land, select a certain proportion of sampling point respectively, described certain proportion is to carry out choose reasonable according to regional actual conditions, in conjunction with the space variable parameter, be finally inversed by the weight parameter of each space variable then.
3. soil utilization evolution CA model conversion rule optimization method according to claim 1, it is characterized in that: the detailed process of described step C is as follows:
C-1 determines the objective function of model
And model parameter vector (
), need to suppose to optimize
Individual parameter;
C-2 produces initial population at random
, comprise
Individuality
, promptly population scale is
, wherein 1 individuality is exactly 1 model parameter vector, and calculates each individual adaptive value:
C-3 produces new colony with following operation:
C-31 selects: select M individuality from current population
C-32 intersects: to M the individuality of selecting
Implement interlace operation;
C-33, variation: the individuality after intersecting is implemented mutation operation;
C-34 calculates the fitness of descendants's individuality of generation newly;
C-35 selects: select defect individual in descendants's individuality of individuality from current population and generation and form population of future generation;
C-4, execution in step C-33 repeatedly, until satisfying end condition, i.e. the optimum solution of optimized individual as evolutional programming selected in computational resource restriction or found optimum solution, and the M in the above-mentioned steps, N, n are natural number.
4. soil utilization evolution CA model conversion rule optimization method according to claim 1, it is characterized in that: the soil utilization evolution CA model that described step D sets up based on Evolutionary Programming Algorithm is the soil utilization evolution CA model parameter substitution CA model that adopts after step C optimizes, carry out iteration then, simulation soil utilization is developed and is drawn, and the scope of iterations is 100-200 time.
5. soil utilization evolution CA model conversion rule optimization method according to claim 1 is characterized in that: described step e is used the simulation precision that Kappa coefficient and Moran ' s I index come verification model respectively;
Wherein, Moran ' s I index utilizes the Spatial Autocorrelation in the Spatial Statistic Tools module of ArcMap software to calculate, the result of calculation that compares the two then, numerical value is close represents that then the space distribution of the two is close, analog result is more accurate, otherwise then analog result is relatively poor;
The overall accuracy of model draws by the method for pointwise comparison, be about to (the i of analog result, j) (the i of cellular and actual conditions, j) cellular is compared, if both land use pattern is identical, then simulation is correct, otherwise then simulates mistake, and overall accuracy is for simulating the correct cellular number and the ratio of all cellular numbers;
Described step e compares the operational efficiency of verification model by the working time of computation model with its working time and other models.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011101191680A CN102184328A (en) | 2011-05-10 | 2011-05-10 | Method for optimizing land use evolution CA model transformation rules |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN2011101191680A CN102184328A (en) | 2011-05-10 | 2011-05-10 | Method for optimizing land use evolution CA model transformation rules |
Publications (1)
Publication Number | Publication Date |
---|---|
CN102184328A true CN102184328A (en) | 2011-09-14 |
Family
ID=44570504
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN2011101191680A Pending CN102184328A (en) | 2011-05-10 | 2011-05-10 | Method for optimizing land use evolution CA model transformation rules |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN102184328A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164554A (en) * | 2011-12-14 | 2013-06-19 | 深圳光启高等理工研究院 | Method for determining metamaterial unit structure |
CN105243503A (en) * | 2015-10-19 | 2016-01-13 | 上海海洋大学 | Coastal zone ecological safety assessment method based on space variables and logistic regression |
CN106021751A (en) * | 2016-05-26 | 2016-10-12 | 上海海洋大学 | Land utilization change simulation method for coastal zone based on CA and SAR |
CN109063388A (en) * | 2018-09-28 | 2018-12-21 | 同济大学 | The micro climate architecture design addressing design method of wind environment simulation |
CN109508360A (en) * | 2018-11-07 | 2019-03-22 | 武汉大学 | A kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata |
CN109815885A (en) * | 2019-01-21 | 2019-05-28 | 南京国准数据有限责任公司 | GDP evaluation method and device based on MODIS satellite data |
CN110069885A (en) * | 2019-05-05 | 2019-07-30 | 重庆师范大学 | A kind of " three lives " space optimization method based on external ecology functional localization |
CN114818517A (en) * | 2022-06-28 | 2022-07-29 | 南京北斗创新应用科技研究院有限公司 | Land use change simulation method based on NSGA-II self-correcting cellular automaton |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1987906A (en) * | 2005-12-22 | 2007-06-27 | 中国煤炭地质总局航测遥感局 | Method for dynamicaly predicting land use change |
CN101419623A (en) * | 2008-12-09 | 2009-04-29 | 中山大学 | Geographical simulation optimizing system |
-
2011
- 2011-05-10 CN CN2011101191680A patent/CN102184328A/en active Pending
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN1987906A (en) * | 2005-12-22 | 2007-06-27 | 中国煤炭地质总局航测遥感局 | Method for dynamicaly predicting land use change |
CN101419623A (en) * | 2008-12-09 | 2009-04-29 | 中山大学 | Geographical simulation optimizing system |
Non-Patent Citations (3)
Title |
---|
《地理研究》 20070331 杨青生等 基于遗传算法自动获取CA模型的参数--以东莞市城市发展模拟为例 第229-237页 1-5 第26卷, 第2期 * |
杨青生等: "基于遗传算法自动获取CA模型的参数——以东莞市城市发展模拟为例", 《地理研究》 * |
王丽萍等: "基于灰色模型-元胞自动机模型的佛山市土地利用情景模拟分析", 《农业工程学报》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103164554A (en) * | 2011-12-14 | 2013-06-19 | 深圳光启高等理工研究院 | Method for determining metamaterial unit structure |
CN103164554B (en) * | 2011-12-14 | 2016-03-02 | 深圳光启高等理工研究院 | A kind of method determining metamaterial modular construction |
CN105243503A (en) * | 2015-10-19 | 2016-01-13 | 上海海洋大学 | Coastal zone ecological safety assessment method based on space variables and logistic regression |
CN106021751A (en) * | 2016-05-26 | 2016-10-12 | 上海海洋大学 | Land utilization change simulation method for coastal zone based on CA and SAR |
CN106021751B (en) * | 2016-05-26 | 2019-04-05 | 上海海洋大学 | Littoral zone simulation of land use changes method based on CA and SAR |
CN109063388A (en) * | 2018-09-28 | 2018-12-21 | 同济大学 | The micro climate architecture design addressing design method of wind environment simulation |
CN109508360A (en) * | 2018-11-07 | 2019-03-22 | 武汉大学 | A kind of polynary flow data space-time autocorrelation analysis method of geography based on cellular automata |
CN109508360B (en) * | 2018-11-07 | 2021-03-16 | 武汉大学 | Geographical multivariate stream data space-time autocorrelation analysis method based on cellular automaton |
CN109815885A (en) * | 2019-01-21 | 2019-05-28 | 南京国准数据有限责任公司 | GDP evaluation method and device based on MODIS satellite data |
CN110069885A (en) * | 2019-05-05 | 2019-07-30 | 重庆师范大学 | A kind of " three lives " space optimization method based on external ecology functional localization |
CN114818517A (en) * | 2022-06-28 | 2022-07-29 | 南京北斗创新应用科技研究院有限公司 | Land use change simulation method based on NSGA-II self-correcting cellular automaton |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Yu et al. | LSTM-EFG for wind power forecasting based on sequential correlation features | |
Feng et al. | Operation rule derivation of hydropower reservoir by k-means clustering method and extreme learning machine based on particle swarm optimization | |
CN102184328A (en) | Method for optimizing land use evolution CA model transformation rules | |
CN106446540B (en) | A kind of Wind turbines health status real time evaluating method | |
Wang et al. | Hour-ahead photovoltaic generation forecasting method based on machine learning and multi objective optimization algorithm | |
CN102831474B (en) | Improved fuzzy C-mean clustering method based on quantum particle swarm optimization | |
CN109214449A (en) | A kind of electric grid investment needing forecasting method | |
CN107977734A (en) | A kind of Forecasting Methodology based on mobile Markov model under space-time big data | |
CN103150614B (en) | A kind of Automatic configuration method for land utilization space | |
CN108427845A (en) | A kind of Pb-Zn deposits mining process carbon emission short term prediction method | |
CN103455612B (en) | Based on two-stage policy non-overlapped with overlapping network community detection method | |
CN101908213A (en) | SAR image change detection method based on quantum-inspired immune clone | |
CN109492748A (en) | A kind of Mid-long term load forecasting method for establishing model of the electric system based on convolutional neural networks | |
CN104732091A (en) | Cellular automaton river bed evolution prediction method based on natural selection ant colony algorithm | |
CN105868906A (en) | Optimized method for analyzing maturity of regional development | |
CN109858665A (en) | Photovoltaic short term power prediction technique based on Feature Selection and ANFIS-PSO | |
CN105844334B (en) | A kind of temperature interpolation method based on radial base neural net | |
Fei et al. | Research on data mining algorithm based on neural network and particle swarm optimization | |
Jingming et al. | Research on credit risk measurement of small and micro enterprises based on the integrated algorithm of improved GSO and ELM | |
Guo et al. | Harris hawks optimization algorithm based on elite fractional mutation for data clustering | |
Zeng et al. | Short-term load forecasting of smart grid systems by combination of general regression neural network and least squares-support vector machine algorithm optimized by harmony search algorithm method | |
Xiaoxun et al. | Research on wind speed behavior prediction method based on multi-feature and multi-scale integrated learning | |
CN105046057A (en) | LSSVM (Least Square Support Vector Machine) pulsation wind speed prediction method based on Morlet wavelet kernel | |
CN104537108A (en) | High-dimensional data feature selecting method | |
CN113902270A (en) | Method and system for safety rating of urban gas area |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
C02 | Deemed withdrawal of patent application after publication (patent law 2001) | ||
WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20110914 |