CN113988305B - Machine learning-based penetration algorithm verification method and system - Google Patents
Machine learning-based penetration algorithm verification method and system Download PDFInfo
- Publication number
- CN113988305B CN113988305B CN202111109148.5A CN202111109148A CN113988305B CN 113988305 B CN113988305 B CN 113988305B CN 202111109148 A CN202111109148 A CN 202111109148A CN 113988305 B CN113988305 B CN 113988305B
- Authority
- CN
- China
- Prior art keywords
- penetration
- factors
- influence
- probability
- factor
- 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
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Pure & Applied Mathematics (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Computational Mathematics (AREA)
- Databases & Information Systems (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Operations Research (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Probability & Statistics with Applications (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Computing Systems (AREA)
- Complex Calculations (AREA)
Abstract
The invention discloses a machine learning-based penetration algorithm verification method and a machine learning-based penetration algorithm verification system, wherein the method comprises the following steps: acquiring a plurality of penetration impact factors related to both attacking and defending parties; setting a weight value for each penetration influence factor based on a machine learning regression model; determining the penetration probability based on the weight value of each penetration influence factor and the parameters of the penetration influence factors; and adjusting the parameters and the corresponding weight values of each penetration influence factor, and verifying the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold value according to different penetration probabilities corresponding to different set weight values. Various factors which may influence the calculation of the penetration probability are considered, and weights are set for different influence factors through a weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
Description
Technical Field
The invention relates to the technical field of verification, in particular to a machine learning-based penetration algorithm verification method and system.
Background
The missile defense process is a complex attack and defense countermeasure process, an attack missile has multiple defense measures such as baits, interference devices and multiple warheads, a defense system can realize successful interception of an incoming missile only depending on various links such as early warning, detection, identification and interception of the system, the defense elements are more, and factors which are changeable instantly exist widely and act simultaneously. Therefore, it is extremely difficult and the system will be very complex to build a mathematical analytical model describing the process of penetration.
In the actual missile penetration process, the attacking and defending process is complex, the confrontation factors are too many, the accuracy of the penetration probability calculation of the existing penetration algorithm is not high, in addition, the prior art can only carry out the penetration probability calculation based on the past data, the penetration algorithm cannot be optimized, the penetration probability is improved, and a more efficient penetration plan is given.
Disclosure of Invention
The invention provides a machine learning-based penetration algorithm verification method and system, which aim to solve the problems in the prior art.
The invention provides a machine learning-based penetration algorithm verification method, which comprises the following steps:
s100, acquiring a plurality of penetration impact factors related to both attacking and defending parties;
s200, setting a weight value for each penetration influence factor based on a machine learning regression model;
s300, determining the penetration probability based on the weight value of each penetration influence factor and the parameter of the penetration influence factor;
s400, adjusting the parameters and the corresponding weight values of each penetration influence factor, and verifying the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold value according to different penetration probabilities corresponding to different set weight values.
Preferably, the S100 includes:
s101, acquiring all factors related to known attack weapons and defense measures of both attacking and defending parties;
s102, setting all the acquired factors as penetration influence factors;
correspondingly, the S200 includes:
s201-1, acquiring penetration influence factors corresponding to known attack weapons and defense measures of both attacking parties and defending parties for a plurality of times, and recording all penetration influence factors as historical data in a historical database;
s201-2, inputting the penetration influence factors in the historical database into a machine learning regression model, and obtaining the weight value of each penetration influence factor based on the model.
Preferably, said S400 comprises, after:
s500, screening the penetration influence factors to screen the penetration influence factors which are beneficial to improving the penetration probability;
the S500 includes:
s501, screening the penetration influence factors based on the penetration probability corresponding to the parameter and the weight value of each penetration influence factor;
and S502, when the parameters of the penetration influence factors are not changed, increasing or reducing the corresponding weight values, and if the obtained penetration probability does not change beyond the first threshold value and is smaller than the second threshold value, rejecting the corresponding penetration influence factors.
Preferably, after S100, the method includes:
s600, performing data processing on the penetration protection influence factors, establishing a four-level index system, and forming parameters of the penetration protection influence factors with the system;
s700, carrying out dimensionless standardization processing on the complex penetration prevention influence factors to form parameters of the dimensionless penetration prevention influence factors.
Preferably, the S200 further includes:
s202-1, based on an analytic hierarchy process, judging the relative importance of each penetration influence factor of each level, wherein the judgment is expressed by numerical values to form a judgment matrix;
s202-2, generating a weight value corresponding to each penetration influence factor based on the judgment matrix;
s202-3, determining a random factor in the penetration process, and setting the random factor as a penetration influence factor with a variable;
s202-4, setting a corresponding random weight value for the penetration impact factor with the variable;
s202-5, adjusting the weight value of the penetration influence factor with the variable, and listing the conventional factors set by the penetration influence factor with the variable with high penetration probability value into the penetration influence factor according to different penetration probabilities corresponding to different set weight values, thereby realizing the screening of random factors.
The invention also provides a machine learning-based penetration algorithm verification system, which comprises:
the system comprises a penetration influence factor acquisition module, a transmission module and a processing module, wherein the penetration influence factor acquisition module is used for acquiring a plurality of penetration influence factors related to both attacking and defending parties;
the weight value setting module is used for setting a weight value for each penetration influence factor based on the machine learning regression model;
the system comprises a penetration probability determining module, a penetration probability determining module and a collision probability determining module, wherein the penetration probability determining module is used for determining penetration probability based on the weight value of each penetration influence factor and the parameter of the penetration influence factor;
and the verification module is used for adjusting the parameters and the corresponding weight values of each penetration influence factor, and verifying the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold value according to different penetration probabilities corresponding to different set weight values.
Preferably, the penetration factor acquiring module includes:
the factor acquisition submodule is used for acquiring all factors related to known attack weapons and defense measures of both attacking and defending parties;
the setting submodule is used for setting all the acquired factors as the penetration influence factors;
the weight value setting module includes:
the historical database forming submodule is used for acquiring the penetration influence factors corresponding to the known attack weapons and the defense measures of the attacking and defending parties for a plurality of times, and recording all the penetration influence factors as historical data in the historical database;
and the model learning submodule is used for inputting the penetration protection influence factors in the historical database into a machine learning regression model and obtaining the weight value of each penetration protection influence factor based on the model.
Preferably, the screening module is configured to screen the penetration impact factors after the verification module verifies that the penetration probability is higher than the preset threshold and the parameters and the corresponding weight values of the penetration impact factors, so as to screen the penetration impact factors which are beneficial to improving the penetration probability;
the screening module includes:
the screening submodule is used for screening the penetration influence factors based on the penetration probability corresponding to the parameters and the weight values of each penetration influence factor;
and the eliminating submodule is used for increasing or decreasing the corresponding weight value when the parameter of the penetration prevention influence factor is not changed, and eliminating the corresponding penetration prevention influence factor if the obtained change of the penetration prevention probability does not exceed the first threshold value and the penetration prevention probability is smaller than the second threshold value.
Preferably, the method further comprises the following steps:
the data processing module is used for carrying out data processing on the penetration influence factors after the penetration influence factor acquisition module acquires a plurality of penetration influence factors related to both attacking parties and defending parties, and establishing a four-level index system to form parameters of the penetration influence factors with the system;
and the standardization processing module is used for carrying out dimensionless standardization processing on the complex penetration prevention influence factors to form parameters of the dimensionless penetration prevention influence factors.
Preferably, the weight value setting module further includes:
the judgment matrix forming submodule is used for judging the relative importance of each sudden defense influence factor of each level based on an analytic hierarchy process, and the judgment adopts numerical value representation to form a judgment matrix;
the weight value generation submodule is used for generating a weight value corresponding to each penetration influence factor based on the judgment matrix;
the random factor determining submodule is used for determining the random factors in the penetration process and setting the random factors as penetration influence factors with variables;
a random weight value setting submodule for setting a corresponding random weight value for the penetration influence factor with the variable;
and the random factor screening submodule is used for adjusting the weight value of the penetration factor with the variable, corresponding to different penetration probabilities according to different set weight values, and listing the conventional factors with the variable and high penetration probability value set by the penetration factor into the penetration factor to realize the screening of the random factors.
Compared with the prior art, the invention has the following advantages:
the invention provides a machine learning-based penetration algorithm verification method and system, wherein various factors which possibly influence penetration probability calculation are fully considered by adopting the scheme provided by the application, and weights are set for different influence factors through a weight calculation method, so that the accuracy of penetration probability calculation is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
Additional features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or may be learned by practice of the invention. The objectives and other advantages of the invention will be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
The accompanying drawings, which are included to provide a further understanding of the invention and are incorporated in and constitute a part of this specification, illustrate embodiments of the invention and together with the description serve to explain the principles of the invention and not to limit the invention. In the drawings:
FIG. 1 is a flowchart of a machine learning-based penetration algorithm verification method according to an embodiment of the present invention;
FIG. 2 is a flowchart illustrating a method for setting weight values for the penetration impact factors according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a machine learning-based defense algorithm verification system according to an embodiment of the present invention.
Detailed Description
The preferred embodiments of the present invention will be described in conjunction with the accompanying drawings, and it will be understood that they are described herein for the purpose of illustration and explanation and not limitation.
The embodiment of the invention provides a machine learning-based penetration algorithm verification method, and fig. 1 is a flow chart of the machine learning-based penetration algorithm verification method in the embodiment of the invention; referring to fig. 1, the verification method includes the following steps:
s100, acquiring a plurality of penetration impact factors related to both attacking and defending parties;
s200, setting a weight value for each penetration influence factor based on a machine learning regression model;
s300, determining the penetration probability based on the weight value of each penetration influence factor and the parameter of the penetration influence factor;
s400, adjusting the parameters and the corresponding weight values of each penetration influence factor, and verifying the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold value according to different penetration probabilities corresponding to different set weight values.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is to obtain a plurality of penetration impact factors related to both attacking and defending parties; setting a weight value for each penetration influence factor based on a machine learning regression model; determining the penetration probability based on the weight value of each penetration influence factor and the parameters of the penetration influence factors; and adjusting the parameters and the corresponding weight values of each penetration influence factor, and verifying the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold value according to different penetration probabilities corresponding to different set weight values.
Specifically, the invention comprehensively considers various influence factors of both aspects of the defense outburst, sets different weights for various complicated influence factors, and designs the defense outburst probability verification method based on machine learning.
According to known attack weapons and defense measures of both attacking and defending parties, various factors influencing the penetration probability are subjected to datamation, a four-level index system is established, and different weights are set for different influencing factors. And performing dimensionless quantization processing on the complex data, setting a weight calculation method of each influence factor, and obtaining a penetration probability calculation system through a penetration comprehensive evaluation judgment matrix. The data processing process is carried out by reading the sample data file, so that the data volume of the current processing is reduced, and the requirement on the computing memory is reduced. Based on the machine learning regression model, a large amount of sample data is calculated, a penetration probability system is continuously optimized, and the accuracy and the authenticity of the penetration probability calculation are improved. In application, the penetration probability calculation system can calculate penetration probability under the condition of existing data samples, and can improve the penetration probability by changing different influence factors, thereby being beneficial to optimizing missile penetration plans.
The penetration impact factors include: attack density, direction number (unidirectional attack and multidirectional attack), attack height, attack speed, attack time and radar reflection sectional area factors.
Height: in a certain combat airspace, the lower the height, the greater the defense probability. When the missile flies by sea and the height is reduced to a certain value, the carrier-borne defense weapon cannot intercept the missile, and the penetration probability of the missile is maximum.
Speed: under given conditions, the law of the change of the penetration probability along with the flying speed of the missile can be calculated, and the penetration probability of the anti-ship missile is basically in a linear relation with the speed of the missile below the hypersonic speed. In addition, reducing the radar reflection cross-sectional area of a ballistic missile can increase the penetration probability.
It should be noted that, the penetration probability is the probability that the missile warhead breaks through the enemy defense system to reach the predetermined target. It depends on the maneuverability and enemy defense of the warhead of the own party. Generally expressed in percent.
The existing penetration technologies include the following:
1, a fast burning engine technology, a boosting section infrared stealth technology and a laser resisting technology play an important role in ballistic missile boosting section defense outburst.
Bait technology is an important defense approach, including inert bait, anti-mock bait technology, and spoof (jamming) bait technology, in addition to intelligent bait technology.
And 3, radar stealth and infrared stealth technologies.
Multi-warhead technology, which has become one of the key penetration technologies.
And 5, folding the maneuvering warhead, wherein the maneuvering warhead can avoid interception of anti-guided interception bullets and is considered as one of the most important anti-interception technologies of ballistic missiles, namely, the maneuvering flight of the warhead is realized by generating control moment of maneuvering flight by changing the mass center of the warhead.
And 6, the technology of folding the gliding type maneuvering warhead can enhance the penetration capacity of the ballistic missile by adopting the gliding type maneuvering warhead technology, and is a new direction for the future development of warhead technology.
7, the folding jump technology is a new ground missile outburst prevention technology.
In addition, for the calculation of the penetration probability, generally, the following methods and principles can be adopted: missile penetration probability calculation based on a Monte Carlo method, missile penetration distributed simulation technology, ant colony algorithm, penetration probability calculation based on multi-wave homogeneous interception and the like.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In another embodiment, the S100 includes:
s101, acquiring all factors related to known attack weapons and defense measures of both attacking and defending parties;
s102, setting all the acquired factors as penetration influence factors;
correspondingly, the S200 includes:
s201-1, acquiring penetration influence factors corresponding to known attack weapons and defense measures of both attacking parties and defending parties for a plurality of times, and recording all penetration influence factors as historical data in a historical database;
s201-2, inputting the penetration influence factors in the historical database into a machine learning regression model, and obtaining the weight value of each penetration influence factor based on the model.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is to acquire all factors related to known attack weapons and defense measures of both attacking and defending parties; setting all the acquired factors as penetration influence factors; further acquiring the penetration influence factors corresponding to the known attack weapons and defense measures of the attacking and defending parties for a plurality of times, and recording all the penetration influence factors as historical data in a historical database; and inputting the penetration protection influence factors in the historical database into a machine learning regression model, and obtaining the weight value of each penetration protection influence factor based on the model.
It should be noted that, according to known attack weapons and defense measures of both attacking and defending parties, various factors influencing the penetration probability are digitized, a four-level index system is established, and different weights are set for different influencing factors. And performing dimensionless quantization processing on the complex data, setting a weight calculation method of each influence factor, and obtaining a penetration probability calculation system through a penetration comprehensive evaluation judgment matrix. Any system analysis is based on certain information, the information base of the Analytic Hierarchy Process (AHP) is mainly the judgment given by people to the relative importance of each factor of each layer, the judgment is expressed by numerical values, and the judgment matrix is written into a matrix form. The judgment matrix is the starting point of the AHP work, and the construction of the judgment matrix is the key step of the AHP.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors through the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In another embodiment, the S400 is followed by:
s500, screening the penetration influence factors to screen the penetration influence factors which are beneficial to improving the penetration probability;
the S500 includes:
s501, screening the penetration influence factors based on the penetration probability corresponding to the parameter and the weight value of each penetration influence factor;
and S502, when the parameters of the penetration influence factors are not changed, increasing or reducing the corresponding weight values, and if the obtained penetration probability changes and does not exceed the first threshold value and is smaller than the second threshold value, removing the corresponding penetration influence factors.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that the penetration influence factors are screened, and the penetration influence factors which are beneficial to improving the penetration probability are screened out; specifically, screening the penetration influence factors based on the penetration probability corresponding to the parameter and the weight value of each penetration influence factor; and when the parameters of the penetration influence factors are not changed, increasing or reducing the corresponding weight values, and if the obtained variation of the penetration probability does not exceed the first threshold and the penetration probability is smaller than the second threshold, removing the corresponding penetration influence factors.
According to the scheme, the sudden protection influence factors which have little influence on the sudden protection probability are removed in the screening process of the sudden protection influence factors, so that the calculation workload is reduced, other sudden protection influence factors can be added subsequently, the sudden protection probability is calculated according to the real-time condition, and the accuracy of the sudden protection probability is improved.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In another embodiment, after S100, the method includes:
s600, performing data processing on the penetration protection influence factors, establishing a four-level index system, and forming parameters of the penetration protection influence factors with the system;
s700, carrying out dimensionless standardization processing on the complex penetration prevention influence factors to form parameters of the dimensionless penetration prevention influence factors.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is to carry out data processing on the penetration protection influence factors, establish a four-level index system and form parameters of the penetration protection influence factors with the system; and carrying out dimensionless standardization processing on the complex penetration prevention influence factors to form parameters of the dimensionless penetration prevention influence factors.
Specifically, according to known attack weapons and defense measures of both attacking and defending parties, various factors influencing the penetration probability are subjected to datamation, a four-level index system is established, and different weights are set for different influencing factors. And performing dimensionless quantization processing on the complex data, setting a weight calculation method of each influence factor, and obtaining a penetration probability calculation system through a penetration comprehensive evaluation judgment matrix. Any system analysis is based on certain information, the information base of the Analytic Hierarchy Process (AHP) is mainly the judgment given by people to the relative importance of each factor of each layer, the judgment is expressed by numerical values, and the judgment matrix is written into a matrix form. The judgment matrix is the starting point of the AHP work, and the construction of the judgment matrix is the key step of the AHP. The data processing process is carried out by reading the sample data file, so that the data volume of the current processing is reduced, and the requirement on the computing memory is reduced.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In another embodiment, a method for setting a weight value by a penetration factor is provided, fig. 2 is a flowchart of the method for setting a weight value by a penetration factor in the embodiment of the present invention, please refer to fig. 2, where the S200 further includes:
s202-1, based on an analytic hierarchy process, judging the relative importance of each penetration influence factor of each level, wherein the judgment is expressed by numerical values to form a judgment matrix;
s202-2, generating a weight value corresponding to each penetration influence factor based on the judgment matrix;
s202-3, determining a random factor in the penetration process, and setting the random factor as a penetration influence factor with a variable;
s202-4, setting a corresponding random weight value for the penetration influence factor with the variable;
s202-5, adjusting the weight value of the penetration influence factor with the variable, and listing the conventional factors set by the penetration influence factor with the variable with high penetration probability value into the penetration influence factor according to different penetration probabilities corresponding to different set weight values, thereby realizing the screening of random factors.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is based on an analytic hierarchy process, judgment is given to the relative importance of each sudden protection influence factor of each level, numerical representation is adopted for the judgment to form a judgment matrix, and a weight value corresponding to each sudden protection influence factor is generated based on the judgment matrix; determining a random factor in a penetration process, and setting the random factor as a penetration influence factor with a variable; setting a corresponding random weight value for the penetration influence factor with the variable; the method comprises the steps of adjusting the weight value of the penetration influence factor with the variable, setting the conventional factors with the high penetration probability value and the variable corresponding to different penetration probabilities according to different set weight values, and listing the conventional factors into the penetration influence factor to realize the screening of random factors.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In addition, in the process of data transmission of the penetration probability, the parameters of the penetration influence factors and the weight values of the penetration influence factors, the information is encrypted, an encryption transmission channel is adopted for data transmission, and meanwhile, the encryption safety and stability are evaluated, so that the safety of the process of information and data transmission is ensured to reach the preset standard.
The evaluating the stability of the encrypted data transmission comprises:
carrying out blocking processing on the encrypted data to form a plurality of encrypted data blocks;
and evaluating the stability of the data in each encrypted data block, wherein the stability is calculated according to the following formula:
wherein, gamma is a stability index of the encrypted data, xi,jThe data which represents the jth encrypted data block in the ith encrypted data block and needs to be encrypted is obtained by conversion processing through a set conversion mechanismThe feature data is data obtained by extracting features of data to be encrypted and performing data standardization processing on the extracted features; n, j 1,2.. m, where n is the number of encrypted data blocks and m is the number of characteristic data in the encrypted data blocks.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that the stability of data encryption is evaluated by setting a stability evaluation mechanism of the data encryption, so that the problem of data leakage caused by insecurity of an encryption mode due to the change of the data encryption mechanism along with the improvement of science and technology is solved. The scheme adopted by this embodiment is to perform calculation of the stability index by using the above formula for stability, and the stability index of the current encrypted data can be determined by using the above formula, it should be noted that no matter what form of information or data is encrypted, for example, information or data to be encrypted in the form of picture, video, audio, etc., after the information or data to be encrypted is subjected to encryption conversion, a series of feature data with a sequence formed according to encryption rules will be formed, the set of feature data can be subjected to any form of calculation and processing, and the confidential stability problem can be finally determined by using the above formula calculation. In addition, when the stability index of the current encrypted data is equal to or less than the set value, it is described that the current encrypted data is not a stable encryption method, and therefore, in such a case, it is necessary to set the encryption level of the current encrypted data to the lower level, and for the encrypted data of the lower level, it is necessary to encrypt the data by an upgraded encryption method. On the contrary, if the stability index of the current encrypted data is greater than the set value, the current encrypted data is safe, and the current encryption technology can be continuously adopted to encrypt the data so as to ensure the safety and stability of data storage and data transmission.
Fig. 3 is a schematic structural diagram of a machine learning-based defense algorithm verification system according to an embodiment of the present invention, and please refer to fig. 3, the verification system includes the following components:
a penetration impact factor obtaining module 301, configured to obtain a plurality of penetration impact factors related to both attacking and defending parties;
a weight value setting module 302, configured to set a weight value for each penetration impact factor based on a machine learning regression model;
a penetration probability determining module 303, configured to determine a penetration probability based on a weight value of each penetration influence factor and a parameter of the penetration influence factor;
the verification module 304 is configured to adjust parameters and corresponding weight values of each penetration influence factor, and verify the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold according to different penetration probabilities corresponding to different set weight values.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that various influence factors of both aspects of the defense outburst are comprehensively considered, different weights are set for various complicated influence factors, and the machine learning-based defense outburst probability verification method is designed.
According to known attack weapons and defense measures of both attacking and defending parties, various factors influencing the penetration probability are subjected to datamation, a four-level index system is established, and different weights are set for different influencing factors. And performing dimensionless quantization processing on the complex data, setting a weight calculation method of each influence factor, and obtaining a penetration probability calculation system through a penetration comprehensive evaluation judgment matrix. The data processing process is carried out by reading the sample data file, so that the data volume of the current processing is reduced, and the requirement on the calculation memory is reduced. Based on the machine learning regression model, a large amount of sample data is calculated, a penetration probability system is continuously optimized, and the accuracy and the authenticity of the penetration probability calculation are improved. In application, the penetration probability calculation system can calculate penetration probability under the condition of existing data samples, and can improve the penetration probability by changing different influence factors, thereby being beneficial to optimizing missile penetration plans.
The penetration impact factors include: attack density, direction number (unidirectional attack and multidirectional attack), attack height, attack speed, attack time and radar reflection sectional area factors.
Height: in a certain combat airspace, the lower the height, the greater the defense probability. When the missile flies by sea and the height is reduced to a certain value, the carrier-borne defense weapon cannot intercept the missile, and the penetration probability of the missile is maximum.
Speed: under given conditions, the law of the change of the penetration probability along with the flying speed of the missile can be calculated, and the penetration probability of the anti-ship missile and the speed of the missile are basically in a linear relation below the hypersonic speed. In addition, reducing the radar reflection cross-sectional area of a ballistic missile can increase the penetration probability.
It should be noted that, the penetration probability is the probability that the missile warhead breaks through the enemy defense system to reach the predetermined target. It depends on the maneuverability and enemy defense of the warhead of the own party. Generally expressed in percent.
The existing penetration technologies include the following:
1, a fast burning engine technology, a boosting section infrared stealth technology and a laser resisting technology play an important role in ballistic missile boosting section defense outburst.
Bait technology is an important defense approach, including inert bait, anti-mock bait technology, and spoof (jamming) bait technology, in addition to intelligent bait technology.
And 3, radar stealth and infrared stealth technologies.
4, multiple warhead technology, which has become one of the key defense technologies.
And 5, folding the maneuvering warhead, wherein the maneuvering warhead can avoid interception of anti-guided interception bullets and is considered as one of the most important anti-interception technologies of ballistic missiles, namely, the maneuvering flight of the warhead is realized by generating control moment of maneuvering flight by changing the mass center of the warhead.
And 6, the technology of folding the gliding type maneuvering warhead can enhance the penetration capacity of the ballistic missile by adopting the gliding type maneuvering warhead technology, and is a new direction for the future development of warhead technology.
7, the folding jump technology is a new ground missile outburst prevention technology.
In addition, for the calculation of the penetration probability, generally, the following methods and principles can be adopted: missile penetration probability calculation based on a Monte Carlo method, missile penetration distributed simulation technology, ant colony algorithm, penetration probability calculation based on multi-wave homogeneous interception and the like.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In another embodiment, the penetration impact factor obtaining module includes:
the factor acquisition submodule is used for acquiring all factors related to known attack weapons and defense measures of both attacking and defending parties;
the setting submodule is used for setting all the acquired factors as penetration influence factors;
the weight value setting module includes:
the historical database forming submodule is used for acquiring the penetration influence factors corresponding to the known attack weapons and the defense measures of the attacking and defending parties for a plurality of times, and recording all the penetration influence factors as historical data in the historical database;
and the model learning submodule is used for inputting the penetration protection influence factors in the historical database into a machine learning regression model and obtaining the weight value of each penetration protection influence factor based on the model.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is characterized in that various factors influencing the penetration probability are subjected to datamation according to known attack weapons and defense measures of both attacking parties and defending parties, a four-level index system is established, and different weights are set for different influencing factors. And performing dimensionless quantization processing on the complex data, setting a weight calculation method of each influence factor, and obtaining a penetration probability calculation system through a penetration comprehensive evaluation judgment matrix. Any system analysis is based on certain information, the information base of the Analytic Hierarchy Process (AHP) is mainly the judgment given by people to the relative importance of each factor of each layer, the judgment is expressed by numerical values, and the judgment matrix is written into a matrix form. The judgment matrix is the starting point of the AHP work, and the construction of the judgment matrix is the key step of the AHP.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In another embodiment, further comprising:
the screening module is used for screening the penetration influence factors after the verification module verifies that the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than the preset threshold value, so as to screen out the penetration influence factors which are beneficial to improving the penetration probability;
the screening module includes:
the screening submodule is used for screening the penetration influence factors based on the penetration probability corresponding to the parameters and the weight values of each penetration influence factor;
and the eliminating submodule is used for increasing or decreasing the corresponding weight value when the parameter of the penetration prevention influence factor is not changed, and eliminating the corresponding penetration prevention influence factor if the obtained change of the penetration prevention probability does not exceed the first threshold value and the penetration prevention probability is smaller than the second threshold value.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that the sudden protection influence factors which have little influence on the sudden protection probability are removed in the screening process of the sudden protection influence factors so as to reduce the calculation workload, and other sudden protection influence factors can be added subsequently so as to calculate the sudden protection probability according to the real-time condition and improve the accuracy of the sudden protection probability.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In another embodiment, further comprising:
the data processing module is used for carrying out data processing on the penetration influence factors after the penetration influence factor acquisition module acquires a plurality of penetration influence factors related to both attacking parties and defending parties, and establishing a four-level index system to form parameters of the penetration influence factors with the system;
and the standardization processing module is used for carrying out dimensionless standardization processing on the complex penetration prevention influence factors to form parameters of the dimensionless penetration prevention influence factors.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is characterized in that various factors influencing the penetration probability are subjected to datamation according to known attack weapons and defense measures of both attacking parties and defending parties, a four-level index system is established, and different weights are set for different influencing factors. And performing dimensionless quantization processing on the complex data, setting a weight calculation method of each influence factor, and obtaining a penetration probability calculation system through a penetration comprehensive evaluation judgment matrix. Any system analysis is based on certain information, the information base of the Analytic Hierarchy Process (AHP) is mainly the judgment given by people to the relative importance of each factor of each layer, the judgment is expressed by numerical values, and the judgment matrix is written into a matrix form. The judgment matrix is the starting point of the AHP work, and the construction of the judgment matrix is the key step of the AHP. The data processing process is carried out by reading the sample data file, so that the data volume of the current processing is reduced, and the requirement on the computing memory is reduced.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors through the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the penetration probability calculation system can optimize and improve the penetration probability by changing different influence factors.
In another embodiment, the weight value setting module further includes:
the judgment matrix forming submodule is used for giving judgment to the relative importance of each penetration influence factor of each level based on an analytic hierarchy process, and the judgment adopts numerical value expression to form a judgment matrix;
the weight value generation submodule is used for generating a weight value corresponding to each penetration influence factor based on the judgment matrix;
the random factor determining submodule is used for determining the random factors in the penetration process and setting the random factors as penetration influence factors with variables;
a random weight value setting submodule for setting a corresponding random weight value for the penetration influence factor with the variable;
and the random factor screening submodule is used for adjusting the weight value of the penetration factor with the variable, corresponding to different penetration probabilities according to different set weight values, and listing the conventional factors with the variable and high penetration probability value set by the penetration factor into the penetration factor to realize the screening of the random factors.
The working principle of the technical scheme is as follows: the present embodiment adopts a scheme that the weight value setting module further includes: the judgment matrix forming submodule is used for judging the relative importance of each sudden defense influence factor of each level based on an analytic hierarchy process, and the judgment adopts numerical value representation to form a judgment matrix; the weight value generation submodule is used for generating a weight value corresponding to each penetration influence factor based on the judgment matrix; the random factor determining submodule is used for determining the random factors in the penetration process and setting the random factors as penetration influence factors with variables; a random weight value setting submodule for setting a corresponding random weight value for the penetration influence factor with the variable; and the random factor screening submodule is used for adjusting the weight value of the penetration factor with the variable, corresponding to different penetration probabilities according to different set weight values, and listing the conventional factors with the variable and high penetration probability value set by the penetration factor into the penetration factor to realize the screening of the random factors.
The beneficial effects of the above technical scheme are: by adopting the scheme provided by the embodiment, various factors which can influence the calculation of the penetration probability are fully considered, and the weights are set for different influence factors by the weight calculation method, so that the accuracy of the calculation of the penetration probability is improved. In addition, the defense probability calculation system can optimize and improve the defense probability by changing different influence factors.
In addition, in the process of data transmission of the penetration probability, the parameters of the penetration influence factors and the weight values of the penetration influence factors, the information is encrypted, an encryption transmission channel is adopted for data transmission, and meanwhile, the encryption safety and stability are evaluated, so that the safety of the process of information and data transmission is ensured to reach the preset standard.
The authentication system further comprises: encryption module and stability evaluation module, encryption module carries out encryption processing to the weight value of the parameter of the probability of suddenly preventing, the factor of suddenly preventing influence and the factor of suddenly preventing influence to form encrypted data and transmit, stability evaluation module is used for assessing the stability of encrypted data transmission, includes:
the blocking submodule is used for carrying out blocking processing on the encrypted data to form a plurality of encrypted data blocks;
and the evaluation submodule is used for evaluating the stability of the data in each encrypted data block, and the stability calculation formula is as follows:
wherein, gamma is a stability index of the encrypted data, xi,jRepresenting characteristic data obtained by converting the jth data to be encrypted through a set conversion mechanism in the ith encrypted data block, wherein the characteristic data is obtained by extracting the characteristics of the data to be encrypted and performing data standardization processing on the extracted characteristics; n, j 1,2.. m, where n is the number of encrypted data blocks and m is the number of characteristic data in the encrypted data blocks.
The working principle of the technical scheme is as follows: the scheme adopted by the embodiment is that the stability of data encryption is evaluated by setting a stability evaluation mechanism of the data encryption, so that the problem of data leakage caused by unsafe encryption mode due to the change of the data encryption mechanism along with the improvement of science and technology is solved. The scheme adopted by this embodiment is to perform calculation of the stability index by using the above formula for stability, and the stability index of the current encrypted data can be determined by using the above formula, it should be noted that no matter what form of information or data is encrypted, for example, information or data to be encrypted in the form of picture, video, audio, etc., after the information or data to be encrypted is subjected to encryption conversion, a series of feature data with a sequence formed according to encryption rules will be formed, the set of feature data can be subjected to any form of calculation and processing, and the confidential stability problem can be finally determined by using the above formula calculation. In addition, when the stability index of the current encrypted data is equal to or less than the set value, it indicates that the current encrypted data is not a stable encryption method, and therefore, in this case, it is necessary to set the encryption level of the current encrypted data to the lower level, and in the case of the lower level encrypted data, it is necessary to encrypt the data by the upgraded encryption processing method. On the contrary, if the stability index of the current encrypted data is greater than the set value, the current encrypted data is safe, and the current encryption technology can be continuously adopted to encrypt the data so as to ensure the safety and stability of data storage and data transmission.
It will be apparent to those skilled in the art that various changes and modifications may be made in the present invention without departing from the spirit and scope of the invention. Thus, if such modifications and variations of the present invention fall within the scope of the claims of the present invention and their equivalents, the present invention is also intended to include such modifications and variations.
Claims (8)
1. A machine learning-based penetration algorithm verification method is characterized by comprising the following steps:
s100, acquiring a plurality of penetration impact factors related to both attacking and defending parties;
s200, setting a weight value for each penetration influence factor based on a machine learning regression model;
s300, determining the penetration probability based on the weight value of each penetration influence factor and the parameters of the penetration influence factor;
s400, adjusting parameters and corresponding weight values of each penetration influence factor, and verifying the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold value according to different penetration probabilities corresponding to different set weight values;
the S200 includes:
s202-1, based on an analytic hierarchy process, judging the relative importance of each penetration influence factor of each level, wherein the judgment is expressed by numerical values to form a judgment matrix;
s202-2, generating a weight value corresponding to each penetration influence factor based on the judgment matrix;
s202-3, determining a random factor in the penetration process, and setting the random factor as a penetration influence factor with a variable;
s202-4, setting a corresponding random weight value for the penetration impact factor with the variable;
s202-5, adjusting the weight value of the penetration influence factor with the variable, and listing the conventional factors set by the penetration influence factor with the variable with high penetration probability value into the penetration influence factor according to different penetration probabilities corresponding to different set weight values, thereby realizing the screening of random factors.
2. The machine learning-based penetration algorithm verification method according to claim 1, wherein the S100 comprises:
s101, acquiring all factors related to known attack weapons and defense measures of both attacking and defending parties;
s102, setting all the acquired factors as penetration influence factors;
correspondingly, the S200 includes:
s201-1, acquiring penetration influence factors corresponding to known attack weapons and defense measures of both attacking parties and defending parties for a plurality of times, and recording all penetration influence factors as historical data in a historical database;
s201-2, inputting the penetration influence factors in the historical database into a machine learning regression model, and obtaining the weight value of each penetration influence factor based on the model.
3. The machine learning-based penetration algorithm verification method according to claim 1, wherein the S400 is followed by:
s500, screening the penetration influence factors to screen the penetration influence factors which are beneficial to improving the penetration probability;
the S500 includes:
s501, screening the penetration influence factors based on the penetration probability corresponding to the parameter and the weight value of each penetration influence factor;
and S502, when the parameters of the penetration influence factors are not changed, increasing or reducing the corresponding weight values, and if the obtained penetration probability changes and does not exceed the first threshold value and is smaller than the second threshold value, removing the corresponding penetration influence factors.
4. The machine learning-based penetration algorithm verification method according to claim 1, wherein after S100, the method comprises:
s600, performing data processing on the penetration protection influence factors, establishing a four-level index system, and forming parameters of the penetration protection influence factors with the system;
s700, carrying out dimensionless standardization processing on the complex penetration prevention influence factors to form parameters of the dimensionless penetration prevention influence factors.
5. A machine learning-based penetration algorithm verification system, comprising:
the system comprises a penetration influence factor acquisition module, a transmission module and a processing module, wherein the penetration influence factor acquisition module is used for acquiring a plurality of penetration influence factors related to both attacking and defending parties;
the weight value setting module is used for setting a weight value for each penetration influence factor based on the machine learning regression model;
the system comprises a penetration probability determining module, a penetration probability determining module and a collision probability determining module, wherein the penetration probability determining module is used for determining penetration probability based on the weight value of each penetration influence factor and the parameter of the penetration influence factor;
the verification module is used for adjusting the parameters and the corresponding weight values of each penetration influence factor, and verifying the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than a preset threshold value according to different penetration probabilities corresponding to different set weight values;
the weight value setting module includes:
the judgment matrix forming submodule is used for judging the relative importance of each sudden defense influence factor of each level based on an analytic hierarchy process, and the judgment adopts numerical value representation to form a judgment matrix;
the weight value generation submodule is used for generating a weight value corresponding to each penetration influence factor based on the judgment matrix;
the random factor determining submodule is used for determining the random factors in the penetration process and setting the random factors as penetration influence factors with variables;
a random weight value setting submodule for setting a corresponding random weight value for the penetration influence factor with the variable;
and the random factor screening submodule is used for adjusting the weight value of the penetration factor with the variable, corresponding to different penetration probabilities according to different set weight values, and listing the conventional factors with the variable and high penetration probability value set by the penetration factor into the penetration factor to realize the screening of the random factors.
6. The machine-learning-based penetration algorithm verification system according to claim 5, wherein the penetration impact factor obtaining module comprises:
the factor acquisition submodule is used for acquiring all factors related to known attack weapons and defense measures of both attacking and defending parties;
the setting submodule is used for setting all the acquired factors as the penetration influence factors;
the weight value setting module includes:
the historical database forming submodule is used for acquiring the penetration influence factors corresponding to the known attack weapons and the defense measures of the attacking and defending parties for a plurality of times, and recording all the penetration influence factors as historical data in the historical database;
and the model learning submodule is used for inputting the penetration protection influence factors in the historical database into a machine learning regression model and obtaining the weight value of each penetration protection influence factor based on the model.
7. The machine-learning-based penetration algorithm verification system of claim 5, further comprising:
the screening module is used for screening the penetration influence factors after the verification module verifies that the parameters and the corresponding weight values of the penetration influence factors when the penetration probability is higher than the preset threshold value, so as to screen out the penetration influence factors which are beneficial to improving the penetration probability;
the screening module includes:
the screening submodule is used for screening the penetration influence factors based on the penetration probability corresponding to the parameters and the weight values of each penetration influence factor;
and the eliminating submodule is used for increasing or decreasing the corresponding weight value when the parameter of the penetration prevention influence factor is not changed, and eliminating the corresponding penetration prevention influence factor if the obtained change of the penetration prevention probability does not exceed the first threshold value and the penetration prevention probability is smaller than the second threshold value.
8. The machine-learning-based penetration algorithm verification system of claim 5, further comprising:
the data processing module is used for carrying out data processing on the penetration influence factors after the penetration influence factor acquisition module acquires a plurality of penetration influence factors related to both attacking parties and defending parties, and establishing a four-level index system to form parameters of the penetration influence factors with the system;
and the standardization processing module is used for carrying out dimensionless standardization processing on the complex penetration prevention influence factors to form parameters of the dimensionless penetration prevention influence factors.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111109148.5A CN113988305B (en) | 2021-09-22 | 2021-09-22 | Machine learning-based penetration algorithm verification method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202111109148.5A CN113988305B (en) | 2021-09-22 | 2021-09-22 | Machine learning-based penetration algorithm verification method and system |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN113988305A CN113988305A (en) | 2022-01-28 |
| CN113988305B true CN113988305B (en) | 2022-06-14 |
Family
ID=79736276
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202111109148.5A Active CN113988305B (en) | 2021-09-22 | 2021-09-22 | Machine learning-based penetration algorithm verification method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN113988305B (en) |
Families Citing this family (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN115439021B (en) * | 2022-10-26 | 2023-03-24 | 江苏新恒基特种装备股份有限公司 | Metal strengthening treatment quality analysis method and system |
Family Cites Families (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103077193A (en) * | 2012-12-24 | 2013-05-01 | 人民搜索网络股份公司 | Related event generating method based on user reading interest |
| CN108846232A (en) * | 2018-06-28 | 2018-11-20 | 上海交通大学 | A kind of urban water supply booster confining method |
| CN109241591B (en) * | 2018-08-21 | 2022-05-17 | 哈尔滨工业大学 | Anti-ship missile combat effectiveness evaluation and decision-making assistance method |
| CN111507552A (en) * | 2019-01-31 | 2020-08-07 | 深圳富桂精密工业有限公司 | Deep learning method, system, server and readable storage medium |
| US11727328B2 (en) * | 2019-10-04 | 2023-08-15 | Magnit Jmm, Llc | Machine learning systems and methods for predictive engagement |
| CN112966913A (en) * | 2021-02-25 | 2021-06-15 | 重庆维知达科技有限公司 | Enterprise quality credit data analysis method and system |
-
2021
- 2021-09-22 CN CN202111109148.5A patent/CN113988305B/en active Active
Also Published As
| Publication number | Publication date |
|---|---|
| CN113988305A (en) | 2022-01-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Przemieniecki | Mathematical methods in defense analyses | |
| CN112131749A (en) | Damage assessment method for tank target | |
| CN113988305B (en) | Machine learning-based penetration algorithm verification method and system | |
| CN113395280A (en) | Anti-confusion network intrusion detection method based on generation of countermeasure network | |
| CN110163519B (en) | UUV red and blue threat assessment method for base attack and defense tasks | |
| CN117272306A (en) | Federal learning half-target poisoning attack method and system based on alternate minimization | |
| CN113553777A (en) | Anti-unmanned aerial vehicle swarm air defense deployment method, device, equipment and medium | |
| CN113132398A (en) | Array honeypot system defense strategy prediction method based on Q learning | |
| Qiu et al. | Mt-mtd: muti-training based moving target defense trojaning attack in edged-AI network | |
| Khan et al. | Offensive ai: unification of email generation through GPT-2 model with a game-theoretic approach for spear-phishing attacks | |
| Cheng et al. | Weapon-target assignment of ballistic missiles based on Q-learning and genetic algorithm | |
| Trad | Entity transformation projects-military technology strategy (DMTS) | |
| CN108734334B (en) | Bullet and cannon combined firepower distribution method based on D number and threat priority | |
| CN114818471A (en) | Damage probability calculation method based on machine learning neural network | |
| CN115187789A (en) | Confrontation image detection method and device based on convolutional layer activation difference | |
| Zhang | Research on Weighted Model of Air Defense Weapon-Target Assignment Based on AHP and Entropy Method | |
| Atia et al. | EMDG-FL: Enhanced Malicious Model Detection based on Genetic Algorithm for Federated Learning | |
| Abdulla et al. | Detect Denial of Service Attack using Hybrid Deep Neural Network | |
| Kebir et al. | Conceptual terrorist attacks classification: Pre-processing for artificial intelligence-based classification | |
| CN114880857B (en) | Weapon resource multi-stage optimization distribution method based on hybrid intelligent search | |
| Jia et al. | Heterogeneous Interception Equipment Deployment Method Based on Heuristic Optimization Algorithm | |
| CN117892637A (en) | Target plate breakdown thickness prediction method and device based on joint network model | |
| Juříček et al. | Methods of Indirect Identification in the Hand of a Crisis Manager in the Context of Sociological Aspects. | |
| Suyun et al. | On-line distribution of coordinated attack targets for multi-anti-ship missiles based on genetic simulated annealing algorithm | |
| Feaver et al. | “When the Urgency of Time and Circumstances Clearly Does Not Permit...”: Predelegation in Nuclear and Cyber Scenarios |
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 |