CN113204743B - Neutron-gamma discrimination method based on genetic algorithm - Google Patents
Neutron-gamma discrimination method based on genetic algorithm Download PDFInfo
- Publication number
- CN113204743B CN113204743B CN202110544100.0A CN202110544100A CN113204743B CN 113204743 B CN113204743 B CN 113204743B CN 202110544100 A CN202110544100 A CN 202110544100A CN 113204743 B CN113204743 B CN 113204743B
- Authority
- CN
- China
- Prior art keywords
- neutron
- gamma
- pulse
- fitness function
- genetic algorithm
- 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
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- 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)
- General Physics & Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Evolutionary Biology (AREA)
- Biophysics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Mathematical Physics (AREA)
- Health & Medical Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Optimization (AREA)
- Mathematical Analysis (AREA)
- Computational Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Software Systems (AREA)
- Physiology (AREA)
- Computing Systems (AREA)
- Molecular Biology (AREA)
- General Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- Computational Linguistics (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Operations Research (AREA)
- Probability & Statistics with Applications (AREA)
- Genetics & Genomics (AREA)
- Algebra (AREA)
- Databases & Information Systems (AREA)
- Measurement Of Radiation (AREA)
Abstract
The invention discloses a neutron-gamma discrimination method based on a genetic algorithm, which comprises the steps of S10, acquiring neutron-gamma pulse data; s20, preprocessing the acquired neutron-gamma pulse data; s30, averaging the pulse data extraction sample signals to construct neutron or gamma standard pulses; s40, fitting the standard pulse to obtain a fitness function; s50, carrying out iteration of a genetic algorithm on the preprocessed neutron-gamma pulse data based on a fitness function to obtain parameters of the obtained fitness function; and S60, obtaining a discrimination factor through the optimal parameters of the fitness function, and discriminating the neutron-gamma pulse data according to the discrimination factor. The invention has better discrimination performance, can show good noise immunity, has high accuracy and has good application value in the technical field of mixed radiation field measurement and data processing.
Description
Technical Field
The invention relates to the technical field of mixed radiation field measurement and data processing thereof, in particular to a neutron-gamma discrimination method based on a genetic algorithm.
Background
With the rapid development of nuclear science and technology around the world, research and application of neutrons are concerned by more and more researchers. In practical neutron measurement applications, due to interaction of neutrons with the surrounding environment such as inelastic scattering and radiation capture of slow neutrons, gamma rays always exist along with the neutrons, and a detector sensitive to neutron detection is also sensitive to gamma rays, so that neutrons and gamma rays are difficult to distinguish. Therefore, how to quickly and accurately realize neutron-gamma discrimination from a neutron-gamma mixed radiation field is a key problem in neutron detection. However, although the existing neutron-gamma discrimination methods are different day by day, the differences, accuracy, practicability and the like among different methods need to be examined and researched.
Genetic algorithms are one of many heuristics (metaprobabilistic), and belong to evolutionary algorithms in population-oriented heuristics, and another population-oriented heuristic is the population intelligence algorithm (Sourabh Katoch et al, 2020). Also belonging to the group heuristic algorithm are Particle Swarm Optimization (PSO) (Kennedy J et al, 1995), Ant Colony Optimization (ACO), etc. (Dorigo M et al, 2006). Inspired and influenced by Darwinian's theory of evolution and Mendelian's genetics, John Holland et al first proposed this concept in the early 20 actual 60 s (JH Holland 1992). The genetic algorithm well utilizes the basic concept of competitive breeding of the plants, and the population is continuously adapted to the evolution through the cross exchange and mutation of genetic materials, so that the optimal living space is achieved.
The genetic algorithm is applied to the neutron-gamma discrimination technology in the neutron detection, so that the problem that the accuracy of the conventional neutron-gamma discrimination technology is insufficient is solved, the neutron measurement level is improved, and the method has important significance to scientific research and engineering application.
Disclosure of Invention
Aiming at the technical problems, the invention provides a neutron-gamma discrimination method based on a genetic algorithm with higher accuracy.
In order to achieve the purpose, the technical scheme adopted by the invention is as follows:
a neutron-gamma screening method based on a genetic algorithm comprises the following steps:
s10, acquiring neutron-gamma pulse data;
s20, preprocessing the obtained neutron-gamma pulse data to inhibit noise;
s30, extracting neutron or gamma sample signals from the preprocessed neutron-gamma pulse data, and carrying out averaging processing to construct a standard pulse of the neutron or gamma;
s40, fitting the constructed standard pulse to obtain a fitness function for genetic algorithm processing;
s50, performing genetic algorithm iteration by using the preprocessed neutron-gamma pulse data based on the fitness function, and obtaining the optimal parameters of the used fitness function after selection, intersection and variation operations;
s60, calculating a discrimination factor R according to the optimal parameters of the fitness function obtained in the step S50 PSD And using the discrimination factor R PSD And screening the neutron-gamma pulse data.
Specifically, the acquiring neutron-gamma pulse data in step S10 includes:
by using 252 Cf and 60 co performs experiments respectively to obtain a plurality of gamma and neutron pulse signals originData, and the data length is n.
Specifically, the preprocessing of the neutron-gamma pulse data in the step S20 includes:
s21, performing normalization processing on the obtained neutron-gamma pulse data, so that the result falls in the [0,1] interval, that is:
s22, smoothing the neutron-gamma pulse data after normalization processing by adopting a least square method, and removing random noise in the data, namely:
where pulse (x) is smoothed data, a k Are curve fitting coefficients.
Specifically, the constructing of the standard pulses of neutrons and gammas in the step S30 includes:
s31, extracting a specified number of neutron pulse sample signals or gamma pulse sample signals from the preprocessed neutron-gamma pulse data respectively;
s32, according to the pulse duration, the neutron pulse sample signals are respectively and correspondingly summed and then averaged to obtain neutron standard pulses, or the gamma pulse sample signals are respectively and correspondingly summed and then averaged to obtain gamma standard pulses, which are expressed as:
wherein, s (x) is the neutron standard pulse or the gamma standard pulse after the averaging, I is the number of the sample signals, and pulse (x) represents the neutron pulse sample signal or the gamma pulse sample signal.
Specifically, the process of fitting the standard pulse to obtain the fitness function in step S40 includes:
s41, eliminating the rising edge part of the signal in the standard pulse;
and S42, performing nonlinear least square fitting on the falling edge part of the signal in the reserved standard pulse to obtain a fitness function.
Specifically, in step S42, the following formula is used to perform non-linear least squares fitting:
in the formula, P is a parameter vector, n is the length of a standard pulse signal, Q is the error of nonlinear least square fitting, s (x) is a standard pulse, and f (x, P) represents a fitness function to be fitted.
Specifically, the fitness function obtained in step S42 is represented as:
In the formula, p 1 ,p 2 ,p 3 ,p 4 As the parameter elements in the parameter vector P, equation (5) represents a fitness function obtained based on the neutron standard pulse, and equation (6) represents a fitness function obtained based on the gamma standard pulse.
Specifically, the process of performing genetic algorithm iteration based on the fitness function in step S50 includes:
s51, taking the parameter P of the fitness function as an individual in the population, and randomly generating an initial population with a specified number of individuals;
s52, calculating the fitness of each individual in the population according to the fitness function obtained in the step S40;
s53, judging whether the individual fitness in the population reaches the set iteration times or the optimization criterion;
and S54, if not, carrying out selection, encoding, crossing, mutation, decoding and population updating operations, repeating the steps S52 to S54, and if so, outputting the optimal parameters of the fitness function.
The iteration number set in the step S53 is 200, and the optimization criterion is that the algorithm error is smaller than 1 e-6. In step S54, the selecting operation is to resample the population according to the fitness, the encoding operation is to encode each individual in the population, the crossing operation is to randomly select two individuals in the population to cross, the variation operation is to randomly select one individual in the population to vary, and the decoding operation is to decode each individual in the population and combine them to obtain a new population.
Specifically, in step S60, the obtained optimal parameter of the fitness function is the individual with the highest fitness in the current population, and the parameters P of the individual are recorded and summed to obtain the discrimination factor R PSD =sum(P)。
Compared with the prior art, the invention has the following beneficial effects:
(1) the method skillfully utilizes the original data to construct the standard pulse of the neutron and the gamma, and obtains the fitness function through fitting, converts the discrimination problem of the neutron-gamma discrimination into a data optimization problem, and then adopts a genetic algorithm to optimize the data solution, thereby effectively improving the accuracy in the neutron-gamma discrimination.
(2) The invention adopts the advantages of the genetic algorithm, continuously updates and optimizes the characteristic subsets by simulating the competitive selection rule of the nature and the cross exchange and mutation phenomena of genetic materials, skillfully utilizes the potential solution of the individual representation optimization problem, and the operator for updating the characteristic subsets directly acts on the individual, so that the algorithm can be efficiently and parallelly executed.
Drawings
FIG. 1 is a schematic flow chart of an embodiment of the present invention.
FIG. 2 is a diagram of the pulse effect of a fitness function fit in an embodiment of the present invention.
Fig. 3 is a neutron-gamma screening FoM graph obtained by using a fitness function according to an embodiment of the present invention.
Fig. 4 is a neutron-gamma screening FoM graph obtained by using another fitness function in the embodiment of the invention.
Fig. 5 is a diagram illustrating neutron-gamma discrimination in an embodiment of the present invention.
Detailed Description
The present invention is further illustrated by the following figures and examples, which include, but are not limited to, the following examples.
Examples
As shown in fig. 1 to 5, the neutron-gamma screening method based on the genetic algorithm includes the following steps:
s10, acquiring neutron-gamma pulse data: by using 252 Cf and 60 co performs experiments respectively to obtain a plurality of gamma and neutron pulse signals originData, and the data length is n.
S20, preprocessing the obtained neutron-gamma pulse data, and suppressing noise:
s21, performing normalization processing on the obtained neutron-gamma pulse data, so that the result falls in the [0,1] interval, that is:
s22, smoothing the neutron-gamma pulse data after normalization processing by adopting a least square method, and removing random noise in the data, namely:
where pulse (x) is smoothed data, a k Are curve fitting coefficients.
S30, extracting a sample signal from the preprocessed neutron-gamma pulse data, averaging, and constructing standard pulses of neutrons and gamma, respectively, where the two standard pulses are constructed in the same manner, and in this embodiment, the method is described in a unified manner, and any one of the standard pulses may be used in practical applications:
respectively extracting 100 sample signals of neutron and gamma pulse data, respectively and correspondingly summing and averaging the neutron pulse sample signals according to pulse duration to obtain neutron standard pulses, respectively and correspondingly summing and averaging the gamma pulse sample signals to obtain gamma standard pulses, wherein the gamma standard pulses can be represented as follows:
wherein, s (x) is the neutron standard pulse or the gamma standard pulse after the averaging, I is the number of the sample signals, and pulse (x) represents the neutron pulse sample signal or the gamma pulse sample signal.
And S40, fitting the constructed standard pulse to obtain a fitness function for genetic algorithm processing, wherein the fitness function is fitted in the same way, so that the embodiment is described in a unified way, and any one of the standard pulse and the fitness function in the step S30 can be used in practical application:
s41, eliminating the rising edge part of the signal in the standard pulse;
s42, performing nonlinear least square fitting on the falling edge part of the signal in the reserved standard pulse, namely
In the formula, P is a parameter vector, n is the length of a standard pulse signal, Q is the error of nonlinear least square fitting, s (x) is a standard pulse, and f (x, P) represents a fitness function to be fitted.
Two fitness functions with higher fitting degree respectively corresponding to the neutron pulse data and the gamma pulse data are obtained and are expressed as follows:
in the formula, p 1 ,p 2 ,p 3 ,p 4 As the parameter elements in the parameter vector P, equation (5) represents a fitness function obtained based on the neutron standard pulse, and equation (6) represents a fitness function obtained based on the gamma standard pulse. It is worth pointing out that, based on the characteristic that the graphs of the neutron and gamma pulse data are similar, only one fitness function can be used when processing the neutron-gamma pulse data, and for the neutron and gamma pulse data, only the parameters of the fitness function are different.
S50, performing genetic algorithm iteration by using the preprocessed neutron-gamma pulse data based on the fitness function, and obtaining the best parameters of the fitted fitness function after selection, intersection and variation operations, wherein the specific process is as follows:
taking the parameter P of the fitness function as an individual in the population, and randomly generating a population of 100 individuals;
respectively calculating the fitness of each individual in the population according to the formula (5) or the formula (6);
judging whether the individual fitness in the population reaches the set iteration times or the optimization criterion, wherein the set iteration times are 200 times, and when the set optimization criterion is that the error of the genetic algorithm is less than 1e-6, the error z of the genetic algorithm is expressed by the following formula:
in the formula, n is the length of the signal, y' (x) is an iterative fitness function, and pulse (x) is preprocessed pulse data;
if so, stopping iteration and outputting the individual with the highest fitness in the population;
if not, sequentially carrying out selection, encoding, crossing, mutation, decoding and population updating operations, resampling the population according to the fitness by the selection operation, and setting the selection probability of resampling to be 0.5; the encoding operation is to encode each individual in the population; the cross operation is to randomly select two individuals in the population to cross, and the cross rate is set to be 0.9; the mutation operation is to randomly select one individual in the population for mutation, and the mutation probability is set to be 0.1; the decoding operation is to decode each individual in the population and combine to obtain a new population; and repeating the above process to calculate the fitness of each individual according to formula (5) or formula (6) and making a judgment. S60, obtaining a discrimination factor R by summing the parameters P of the individuals with the highest fitness in the output population PSD ,
R PSD =sum(P) (8)
And using the discrimination factor R PSD And screening the neutron-gamma pulse data.
The screening method was verified by the following experiment:
experimental data Using an EJ-276 probe at an average energy of 4.5MeV 241 6000 pulses are obtained on the Am-Be neutron source through a 10Gs/s digital oscilloscope.
Fig. 2 is a fitting result graph obtained by nonlinear least square fitting after eliminating the pulse rising edge part, and the abscissa pulse time and the ordinate are normalized pulse amplitude.
To verify the feasibility of the screening method, the following table 1 lists the parameter values of the optimal neutron and gamma pulses iteratively calculated by the genetic algorithm based on the fitness function represented by formula (5), and it can be seen that the neutron and gamma pulses are p 2 The difference between the parameter values is large, and for each parameter element P of the parameter P 1 ,p 2 ,p 3 ,p 4 Summing to obtain discrimination factor R PSD And screening the neutron gamma pulse. Table 2 below lists the parameter values for the optimal neutron and gamma pulses calculated iteratively by the genetic algorithm based on the fitness function represented by equation (6), which shows that the neutrons and gamma pulses are p 1 The difference between the parameter values is large, and for each parameter element P of the parameter P 1 ,p 2 ,p 3 Summing to obtain discrimination factor R PSD And screening the neutron gamma pulse.
p 1 | p 2 | p 3 | p 4 | |
Gamma ray | 1.58 | 212.52 | 2.046 | 17.024 |
Neutron (neutron) | 1.63 | 52.43 | 6.501 | 16.918 |
TABLE 1
p 1 | p 2 | p 3 | |
Gamma ray | 150.86 | 6.53 | 12.92 |
Neutron (neutron) | 37.44 | 10.43 | 10.94 |
TABLE 2
Fig. 3 and 4 show neutron-gamma screening FoM graphs based on a genetic algorithm, and fig. 3 and 4 correspond to fitness function formula (5) and fitness function formula (6), respectively. The abscissa represents a discrimination factor, the ordinate represents pulse count in the discrimination factor interval, and a total pulse count value (i.e., the total number of pulses) can be obtained by calculating two peak areas. FoM values of the neutron gamma detection method are respectively 1.498 and 1.5933, which are calculated to be higher than a theoretical FoM value (the theoretical FoM value is 1.27), and the method is characterized by being capable of realizing better neutron-gamma discrimination. Fig. 5 is a diagram of the discrimination effect combining pulse amplitudes, and it can be seen from the diagram that a better discrimination effect is obtained.
The above embodiments are only preferred embodiments of the present invention, and are not intended to limit the scope of the present invention, but all changes that can be made by applying the principles of the present invention and performing non-inventive work on the basis of the principles shall fall within the scope of the present invention.
Claims (7)
1. A neutron-gamma discrimination method based on a genetic algorithm is characterized by comprising the following steps:
s10, acquiring neutron-gamma pulse data;
s20, preprocessing the acquired neutron-gamma pulse data to inhibit noise;
s30, extracting neutron or gamma sample signals from the preprocessed neutron-gamma pulse data, and carrying out averaging processing to construct a standard pulse of the neutron or gamma;
s40, fitting the constructed standard pulse to obtain a fitness function for genetic algorithm processing:
s41, eliminating the rising edge part of the signal in the standard pulse;
s42, performing nonlinear least square fitting on the falling edge part of the signal in the reserved standard pulse to obtain a fitness function;
wherein the following formula is used for non-linear least squares fitting:
in the formula, P is a parameter vector, n is the length of a standard pulse signal, Q is the error of nonlinear least square fitting, S (x) is a standard pulse, and f (x, P) represents a fitness function to be fitted;
the resulting fitness function is expressed as:
In the formula, p 1 ,p 2 ,p 3 ,p 4 Is a parameter element in the parameter vector P;
s50, performing genetic algorithm iteration by using the preprocessed neutron-gamma pulse data based on the fitness function, and obtaining the optimal parameters of the used fitness function after selection, intersection and variation operations;
s60, calculating a discrimination factor R according to the optimal parameters of the fitness function obtained in the step S50 PSD And using the discrimination factor R PSD And screening the neutron-gamma pulse data.
2. The genetic algorithm-based neutron-gamma screening method according to claim 1, wherein the acquiring neutron-gamma pulse data in step S10 includes:
by using 252 Cf and 60 co performs experiments respectively to obtain a plurality of gamma and neutron pulse signals originData, and the data length is n.
3. The genetic algorithm-based neutron-gamma screening method of claim 1, wherein the preprocessing of the neutron-gamma pulse data in step S20 comprises:
s21, performing normalization processing on the obtained neutron-gamma pulse data to enable the result to fall in a [0,1] interval;
and S22, smoothing the neutron-gamma pulse data after the normalization processing by adopting a least square method, and removing random noise in the data.
4. The genetic algorithm-based neutron-gamma screening method according to claim 1, wherein the constructing of the standard pulse in step S30 includes:
s31, extracting a specified number of neutron pulse sample signals or gamma pulse sample signals from the preprocessed neutron-gamma pulse data respectively;
s32, according to the pulse duration, the neutron pulse sample signals are respectively and correspondingly summed and then averaged to obtain neutron standard pulses, or the gamma pulse sample signals are respectively and correspondingly summed and then averaged to obtain gamma standard pulses, which are expressed as:
wherein, s (x) is the neutron standard pulse or the gamma standard pulse after the averaging, I is the number of the sample signals, and pulse (x) represents the neutron pulse sample signal or the gamma pulse sample signal.
5. The genetic algorithm-based neutron-gamma screening method according to claim 1, wherein the process of performing genetic algorithm iteration based on the fitness function in step S50 includes:
s51, randomly generating an initial population with a specified number of individuals by taking the parameters of the fitness function as the individuals in the population;
s52, calculating the fitness of each individual in the population according to the fitness function obtained in the step S40;
s53, judging whether the individual fitness in the population reaches the set iteration times or the optimization criterion;
and S54, if not, carrying out selection, encoding, crossing, mutation, decoding and population updating operations, repeating the steps S52 to S54, and if so, outputting the optimal parameters of the fitness function.
6. The neutron-gamma screening method based on genetic algorithm of claim 5, wherein the selecting operation in step S54 is to resample the population according to fitness, the crossing operation is to randomly select two individuals in the population to cross, and the mutation operation is to randomly select one individual in the population to mutate.
7. The genetic algorithm-based neutron-gamma screening method according to claim 5, wherein the iteration number set in the step S53 is 200, and the optimization criterion is that the algorithm error is less than 1 e-6.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110544100.0A CN113204743B (en) | 2021-05-19 | 2021-05-19 | Neutron-gamma discrimination method based on genetic algorithm |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202110544100.0A CN113204743B (en) | 2021-05-19 | 2021-05-19 | Neutron-gamma discrimination method based on genetic algorithm |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113204743A CN113204743A (en) | 2021-08-03 |
CN113204743B true CN113204743B (en) | 2022-09-02 |
Family
ID=77031732
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202110544100.0A Active CN113204743B (en) | 2021-05-19 | 2021-05-19 | Neutron-gamma discrimination method based on genetic algorithm |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113204743B (en) |
Families Citing this family (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN115359337B (en) * | 2022-08-23 | 2023-04-18 | 四川大学 | Searching method, system and application of pulse neural network for image recognition |
CN115345208B (en) * | 2022-10-19 | 2023-02-03 | 成都理工大学 | Neutron-gamma pulse accumulation discrimination method based on top-hat conversion |
CN115796095B (en) * | 2023-02-07 | 2023-04-21 | 中国科学技术大学 | Pulse interpolation timing parameter optimization method based on genetic algorithm |
Family Cites Families (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US6150655A (en) * | 1998-03-06 | 2000-11-21 | Computalog Research, Inc. | Inferential measurement of photoelectric absorption cross-section of geologic formations from neutron-induced, gamma-ray spectroscopy |
EP2260334A4 (en) * | 2008-03-31 | 2015-03-11 | Southern Innovation Internat Pty Ltd | Method and apparatus for borehole logging |
CN105068108B (en) * | 2015-07-22 | 2018-04-03 | 成都理工大学 | It is a kind of based on the multi-functional neutron and gamma detector singly popped one's head in |
CN108680943B (en) * | 2018-05-11 | 2021-10-19 | 南京航空航天大学 | Neutron energy spectrum measuring device and method based on prompt gamma ray neutron activation analysis technology |
CN110907996B (en) * | 2019-12-11 | 2020-07-14 | 青岛理工大学 | Automatic dense gas reservoir identification method |
CN112258432B (en) * | 2020-10-23 | 2021-09-21 | 成都大学 | Neutron-gamma discrimination method based on composite structural element mathematical morphology |
CN112505742B (en) * | 2020-11-07 | 2022-08-26 | 成都理工大学工程技术学院 | Digital n-gamma discrimination method based on falling edge integration |
-
2021
- 2021-05-19 CN CN202110544100.0A patent/CN113204743B/en active Active
Also Published As
Publication number | Publication date |
---|---|
CN113204743A (en) | 2021-08-03 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN113204743B (en) | Neutron-gamma discrimination method based on genetic algorithm | |
Excoffier et al. | Robust demographic inference from genomic and SNP data | |
Wagner et al. | Forward-weighted CADIS method for variance reduction of Monte Carlo calculations of distributions and multiple localized quantities | |
CN112633427B (en) | Ultrahigh-order harmonic emission signal detection method based on outlier detection | |
CN111639838B (en) | Water quality monitoring point layout optimization method suitable for water supply pipe network | |
CN116383743A (en) | Photovoltaic operation abnormality detection method and system based on machine learning | |
CN114792020B (en) | Quick evaluation method and system for building anti-seismic toughness based on machine learning | |
Li et al. | Many-objective rapid optimization of reactor shielding design based on NSGA-III | |
SAURETTE et al. | Determining minimum sample size for the conditioned Latin hypercube sampling algorithm | |
Alzabidi et al. | Automatic Software structural testing by using Evolutionary Algorithms for test data generations | |
CN111398928B (en) | Method for calculating detection threshold of synthetic ultra-narrow pulse radar based on resampling algorithm | |
Morgan et al. | Experimental evidence that rill-bed morphology is governed by emergent nonlinear spatial dynamics | |
CN109035258B (en) | Image segmentation method based on directed cross genetic algorithm and two-dimensional maximum entropy threshold segmentation algorithm | |
CN111553111A (en) | Digital imitation nuclear signal generator based on MCNP | |
Zhang et al. | A Semantic-Based Hoist Mutation Operator for Evolutionary Feature Construction in Regression | |
CN111125822B (en) | Design method and optimization method of drilling arrangement scheme based on Voronoi diagram | |
CN114265764A (en) | Deep learning operator test data generation method based on weighted sampling | |
CN109902007B (en) | Test case generation method based on point dyeing model | |
KR102103578B1 (en) | Method for Selecting Asset Portfolio | |
Rupšys et al. | Symmetric and Asymmetric Diffusions through Age-Varying Mixed-Species Stand Parameters. Symmetry 2021, 13, 1457 | |
CN105718609B (en) | Radiation detector response compensation sheet design method based on genetic algorithm | |
CN111274867B (en) | Method for simulating field gust | |
CN116819599B (en) | Neutron-gamma ray screening method, system, equipment and medium | |
CN110794469A (en) | Gravity inversion method based on minimum geological feature unit constraint | |
Kim | Effects of spatial growth on gene expression dynamics and on regulatory network reconstruction |
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 |