CN111917785B - Industrial internet security situation prediction method based on DE-GWO-SVR - Google Patents
Industrial internet security situation prediction method based on DE-GWO-SVR Download PDFInfo
- Publication number
- CN111917785B CN111917785B CN202010783805.3A CN202010783805A CN111917785B CN 111917785 B CN111917785 B CN 111917785B CN 202010783805 A CN202010783805 A CN 202010783805A CN 111917785 B CN111917785 B CN 111917785B
- Authority
- CN
- China
- Prior art keywords
- industrial internet
- wolf
- security situation
- svr
- data set
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1433—Vulnerability analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/004—Artificial life, i.e. computing arrangements simulating life
- G06N3/006—Artificial life, i.e. computing arrangements simulating life based on simulated virtual individual or collective life forms, e.g. social simulations or particle swarm optimisation [PSO]
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L41/00—Arrangements for maintenance, administration or management of data switching networks, e.g. of packet switching networks
- H04L41/14—Network analysis or design
- H04L41/145—Network analysis or design involving simulating, designing, planning or modelling of a network
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Computer Security & Cryptography (AREA)
- Signal Processing (AREA)
- Computer Networks & Wireless Communication (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- General Health & Medical Sciences (AREA)
- Mathematical Physics (AREA)
- Data Mining & Analysis (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Biophysics (AREA)
- General Physics & Mathematics (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Biomedical Technology (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Health & Medical Sciences (AREA)
- Computer Hardware Design (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention relates to a DE-GWO-SVR-based industrial internet security situation prediction method, which belongs to the technical field of industrial internet security and comprises the following steps: s1: collecting industrial internet safety data information and safety asset information, preprocessing the information and establishing an industrial internet safety database; s2: processing the security data in the database to obtain an industrial internet security situation value data set; s3: constructing a training sample data set and a test sample data set from data in the industrial internet security situation value data set by adopting a sliding window method; s4: building an industrial internet security situation prediction model based on DE-GWO-SVR to predict future security situations; s5: and (5) checking the safety situation prediction model, and if the safety situation prediction model does not meet the requirements, returning to the step S4 until the prediction result meets the requirements. The method can accurately predict the industrial internet security situation and provide better guarantee for the industrial internet security.
Description
Technical Field
The invention belongs to the technical field of industrial internet security, and relates to a DE-GWO-SVR-based industrial internet security situation prediction method.
Background
The internet technology is widely applied to industrial enterprises for centralization, the industrial interconnection brought by high-speed industrialization and informatization promotion brings great convenience to production and life of people, but with the gradual deepening of industrial informatization, the enterprises face various network attack threats at any time in the transformation and upgrading process. With the continued use of IPV6 technology and 5G technology, industrial internet enterprises will now face more sophisticated and varied security threats. Aiming at the requirements of safety and reliability, mass coverage, low time delay and the like of the industrial Internet, the industrial information safety is enhanced, and an omnibearing industrial information safety guarantee system is constructed and is a basic guarantee for the development of intelligent manufacturing enterprises. Traditional network security protection measures such as IDS protection, firewall vulnerability check system protection, data encryption protection and the like are lack of certain autonomy and relevance, and a network situation awareness technology can acquire relevant information causing security situation change under a large-scale industrial internet environment, effectively analyze and evaluate internal security events, carry out sequential prediction on network security threats to be faced recently, and further help security management personnel to make management decisions and preventive actions.
At present, although a machine learning method is applied to the field of network security situation prediction, the machine learning method is applied to the field of general internet, a security situation prediction technology aiming at industrial internet does not exist, and most of the traditional network security situation prediction technologies are not suitable for being directly applied to the industrial internet. Therefore, the industrial network security in the industrial internet environment needs higher security guarantee, and it is very meaningful to research a security situation prediction method with higher accuracy in the industrial internet environment.
Disclosure of Invention
In view of the above, the invention aims to provide a DE-GWO-SVR-based industrial internet security situation prediction method, which solves the problem that the traditional network security situation prediction method cannot be directly applied to the industrial internet well, and provides the industrial internet security situation prediction method with high prediction accuracy and high convergence rate.
In order to achieve the purpose, the invention provides the following technical scheme:
a method for predicting the security situation of an industrial internet based on DE-GWO-SVR comprises the following steps:
s1: collecting industrial internet safety data information and safety asset information, preprocessing the information and establishing an industrial internet safety database;
s2: processing the safety data in the database to obtain an industrial internet safety situation value data set;
s3: constructing a training sample data set and a test sample data set from data in the industrial internet security situation value data set by adopting a sliding window method;
s4: building an industrial internet security situation prediction model based on DE-GWO-SVR to predict future security situations;
s5: and (5) checking the safety situation prediction model, and if the safety situation prediction model does not meet the requirements, returning to the step S4 until the prediction result meets the requirements.
Further, step S2 specifically includes the following steps:
s21: through the research on the situation influence index classification, the extracted data is preprocessed and quantized and graded;
s22: and (4) safety situation value calculation: calculating the security situation value of the industrial internet in one period according to the following formula:
in the formula, T represents the magnitude of the security situation value, N represents the total number of different types of attacks in one week, i represents the type, and omega represents the type1、ω2、ω3Represents a weight factor, Vi、Ti、AiRepresenting vulnerability degree values, threat degree values and asset values corresponding to attacks of the same type;
s23: normalization treatment: data were normalized to the [0,1] interval according to the following equation:
in the formula, XiAnd Xi' indicates the situation values before and after the normalization processing, respectively, and i is 1,2, …, 150; xmaxAnd XminWhich respectively represent the two maxima and minima in the raw data.
Further, in step S3, a sliding window method is used to determine 80% of data in the industrial internet security situation value sample set as a training sample set, 20% of the data is determined as a test sample set, a sliding window is selected as 5, a single-step prediction mode is used to predict the last 1 security situation value using the first 5 security situation values, and a sample training set D ═ is constructed (X)i,Yi) And sample test set T ═ (X)i,Yi)。
Further, in step S4, the differential evolution algorithm DE is first introduced into the grey wolf algorithm GWO to obtain an improved grey wolf optimization algorithm, the population scale, the maximum iteration number, and the spatial dimension in the improved grey wolf optimization algorithm are initialized, then the training situation prediction model is trained by using the training sample data set constructed in step S3, the residual between the predicted value and the true value obtained by training the sample data set is used as a fitness function to find out the optimal individual, and finally the obtained optimal individual is optimized for the SVR parameters of the support vector regression machine to construct the industrial internet security prediction model based on DE-GWO-SVR.
Further, step S4 specifically includes the following steps:
s41: initializing model parameters: setting N as the number of the wolf populations, G representing the maximum iteration number, a scaling factor F, a cross probability parameter CR and the value ranges of two coefficients C and G involved in the support vector regression, and randomly initializing individuals in the whole population in a search space;
s42: inputting a training sample data set into a DE improved GWO-SVR prediction model for training; randomly generating the position information of all father grey wolf individuals in the population, comparing and selecting the grey wolf with the best adaptability according to the fitness value of each father in the father grey wolf population, respectively using the grey wolf as the father alpha wolf, the grey wolf as the father beta wolf and the grey wolf as the father delta wolf, and updating the position information of other father wolfs in the wolf population by using the following formula:
A＝a·(2r-1)
wherein D (t) represents the distance between one of the three dominant subjects and the target, xp(t) selecting the current position of the target animal, wherein t represents the current iteration times; r belongs to rand (0,1), A is a synergistic factor; when A is more than or equal to 1, the predatory wolves perform global search at a place far away from the hunting target; when | A |<1, predatory wolves begin to gradually surround prey targets;
s43: differential evolution operation: performing mutation operation with the newly generated filial generation gray wolf individual by using the following formula, and performing cross operation with the target parent alpha wolf to generate an intermediate variant filial generation alpha wolf; comparing the adaptability of the two parent and child alpha wolves in the current iteration process, taking the gray wolves with the best adaptability as new parent alpha wolves, updating the position information of other gray wolves in the wolves, and obtaining new parent alpha wolves, beta wolves and delta wolves after sorting by depending on the individual adaptability values again:
Vi(g)＝xr3(g)+F·(xr1(g)-xr2(g))
in the formula, xr1(g),xr2(g),xr3(g) Is a randomly selected three parent individuals and r1≠r2≠r3≠i，Vi(g) G is the current iteration numerical value of the variant progeny individual; f0Is the initial value of the scaling factor, when F is epsilon (F)0,2F0) And F ∈ (0, 1); CR is cross probability used for controlling cross degree, j represents dimension to be crossed, jrandRepresent integer indices, chosen randomly from {1,2, …, n }.
Further, in step S5, a determination condition is set as whether the highest prediction precision condition is achieved or whether iteration has been performed to the G generation, if a given requirement for terminating the algorithm loop is achieved, the position information of the parent α wolf individual with the best adaptability at this time is output, so as to obtain the best SVR related penalty parameter C and RBF kernel function parameter G, thereby establishing the best industrial internet security situation prediction model, and finally, the test sample data set obtained in S3 is input, so as to obtain a predicted value of the industrial internet security situation.
The invention has the beneficial effects that: compared with the traditional network security situation prediction method, the gray wolf optimization algorithm is improved by using the differential evolution algorithm, the problem that the gray wolf optimization algorithm is not high in solving precision and falls into the local optimal solution is solved, then the punishment coefficient C and the kernel function parameter g of the support vector regression machine are selected by using the improved combined optimization algorithm aiming at the problems of high-dimensional complexity, nonlinearity and openness of the industrial internet security data, and finally the future security situation value is predicted by using the advantages of high training speed, good fitting effect, difficulty in falling into the local optimal solution and the like of the support vector regression algorithm. Therefore, the method and the device solve the problems of low prediction precision of the industrial internet security situation and non-ideal security data processing.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objectives and other advantages of the invention may be realized and attained by the means of the instrumentalities and combinations particularly pointed out hereinafter.
Drawings
For the purposes of promoting a better understanding of the objects, aspects and advantages of the invention, reference will now be made to the following detailed description taken in conjunction with the accompanying drawings in which:
FIG. 1 is a basic structure diagram of an industrial Internet security situation prediction method based on DE-GWO-SVR according to the present invention;
FIG. 2 is a diagram illustrating a security posture value quantification method according to the present invention;
FIG. 3 is a schematic diagram of the calceea priestor of the present invention;
FIG. 4 is a two-dimensional schematic diagram of a standard differential variation strategy according to the present invention;
FIG. 5 is a flowchart of an industrial Internet security situation prediction algorithm based on DE-GWO-SVR according to the present invention.
Detailed Description
The following embodiments of the present invention are provided by way of specific examples, and other advantages and effects of the present invention will be readily apparent to those skilled in the art from the disclosure herein. The invention is capable of other and different embodiments and of being practiced or of being carried out in various ways, and its several details are capable of modification in various respects, all without departing from the spirit and scope of the present invention. It should be noted that the drawings provided in the following embodiments are only for illustrating the basic idea of the present invention in a schematic way, and the features in the following embodiments and examples may be combined with each other without conflict.
Wherein the showings are for the purpose of illustrating the invention only and not for the purpose of limiting the same, and in which there is shown by way of illustration only and not in the drawings in which there is no intention to limit the invention thereto; to better illustrate the embodiments of the present invention, some parts of the drawings may be omitted, enlarged or reduced, and do not represent the size of an actual product; it will be understood by those skilled in the art that certain well-known structures in the drawings and descriptions thereof may be omitted.
The same or similar reference numerals in the drawings of the embodiments of the present invention correspond to the same or similar components; in the description of the present invention, it should be understood that if there is an orientation or positional relationship indicated by the terms "upper", "lower", "left", "right", "front", "rear", etc., based on the orientation or positional relationship shown in the drawings, it is only for convenience of description and simplification of description, but it is not intended to indicate or imply that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore the terms describing the positional relationship in the drawings are only used for illustrative purposes and are not to be construed as limiting the present invention, and the specific meaning of the terms described above will be understood by those skilled in the art according to the specific circumstances.
Referring to fig. 1 to 5, fig. 1 is a basic structure diagram of a method for predicting a security situation of an industrial internet based on DE-GWO-SVR, which is suitable for predicting a network security situation under an industrial internet environment, and includes the following steps:
101: data preprocessing: constructing an industrial internet security database according to the industrial enterprise network security data information and the asset value information;
102: evaluation and quantification: and carrying out weighted average on the obtained data, and carrying out normalization processing on the data to obtain a sample data set of the industrial internet security situation value.
103: determining 80% of data of an industrial internet security situation value sample data set as a training sample data set and 20% of data as a test sample data set by adopting a sliding window method, selecting the size of a sliding window as 5, outputting as 1, and constructing a training sample set D ═ X (X)i,Yi) And test sample set T ═ (X)i,Yi)。
104: the method comprises the steps of constructing an industrial internet security situation prediction model based on DE-GWO-SVR to predict the future security situation of the industrial internet;
105: if the prediction model satisfies the requirement, the process is stopped, and if the prediction model does not satisfy the requirement, the process returns to step S4, and the process is repeated until the prediction result satisfies the requirement.
Optionally, in the step 102, the data processing process includes the following steps:
1021: through research on classification of situation influence indexes, extracted data are quantized and graded, and the industrial internet security situation value in a period is calculated according to the following formula:
in the formula, T represents the magnitude of the security situation value, N represents the total number of different types of attacks in one week, i represents the type, and omega represents the number of attacks in one week1、ω2、ω3Representing a weight factor, Vi、Ti、AiVulnerability value, threat degree value and asset corresponding to attack representing same typeAnd (4) value.
1023: normalization processing: data were normalized to the [0,1] interval according to the following equation:
in the formula, XiAnd X'iEach indicates a situation value before and after normalization processing, i is 1,2, …, 150; xmaxAnd XminRespectively, as the two most significant values in the original data.
In step 104, referring to fig. 5, training to obtain optimal parameters C and g of the SVR according to the data sets D and T obtained in step 103 specifically includes the following steps:
1041: initializing model parameters: setting N as the number of the wolf population, G as the maximum iteration number, the scaling factor F, the cross probability parameter CR and the value range of two coefficients C and G involved in the support vector regression, and randomly initializing individuals in the whole population in a search space.
1042: after model parameters are initialized, a training sample data set is input into a DE improved GWO-SVR prediction model for training. Randomly generating the position information of all father grey wolfs in the population, referring to fig. 3, selecting the best grey wolf as the father alpha wolf, beta wolf and delta wolf according to the fitness value of each father in the father grey wolf group, and updating the position information of other father wolfs in the wolf group by the following formula:
A＝a·(2r-1)
wherein D (t) represents the distance between the current Hui wolf individual (one of the three dominant Hui wolfs) and the target, xp(t) selecting the current position of the target animal, wherein t represents the current iteration times; r belongs to rand (0,1), and A is a synergistic factor. When the absolute value A is more than or equal to 1, the predatory wolves perform global search at a place far away from the hunting target; when | A |<1, predatory wolves start to gradually surround prey targets, which is equivalent to the algorithm entering a local optimization stage.
1043: differential evolution operation: referring to fig. 4, the following formula is used to perform mutation operation with the newly generated offspring wolf individuals, and then the mutation operation is performed with the target parent alpha wolf to generate the intermediate variant offspring alpha wolf. And comparing the adaptability of the two parent-child alpha wolves in the current iteration process, taking the gray wolves with the best adaptability as new parent alpha wolves, updating the position information of other gray wolves in the wolves, and sequencing by depending on the individual adaptability values again to obtain new parent alpha wolves, beta wolves and delta wolves.
Vi(g)＝xr3(g)+F·(xr1(g)-xr2(g))
In the formula, xr1(g),xr2(g),xr3(g) Is a randomly selected three parent individuals and r1≠r2≠r3≠i，Vi(g) G is the current iteration numerical value of the variant offspring individuals; f0Is the initial value of the scaling factor, when F is the same as (F)0,2F0) And F ∈ (0, 1); CR is the crossover probability and is used for controlling the crossover degree, j represents the dimension to be crossed, jrandRepresent integer indices, chosen randomly from {1,2, …, n }.
In step 105, a determination condition is set as to whether the highest prediction accuracy condition is reached or whether iteration has been performed to the G generation. If the requirement of the given termination algorithm cycle is met, outputting the position information of the parent alpha wolf individual with the best adaptability at the moment, so as to obtain the optimal SVR (support vector regression) related penalty parameter C and RBF (radial basis function) parameter g, and establishing the optimal industrial internet security situation prediction model. And finally, processing the test sample data set, and outputting a situation prediction result to be presented to safety management personnel.
The method is suitable for predicting the security situation of the industrial Internet, and based on a machine learning method, the data set can be subjected to normalization processing, dimensionality reduction, abnormal data detection and correction and the like, so that the prediction precision is improved. The difference evolution algorithm is adopted to avoid the gray wolf algorithm from being easily trapped into a local optimal solution, the optimal support vector regression related parameters are selected by utilizing the improved gray wolf optimization algorithm, and finally the support vector regression is adopted to predict the industrial internet security situation, so that the effects of high prediction precision and strong convergence capability can be achieved.
Finally, although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that various changes and modifications may be made therein without departing from the spirit and scope of the invention as defined by the appended claims.
Claims (5)
1. A method for predicting industrial internet security situation based on DE-GWO-SVR is characterized by comprising the following steps: the method comprises the following steps:
s1: collecting industrial internet safety data information and safety asset information, preprocessing the information and establishing an industrial internet safety database;
s2: processing the security data in the database to obtain an industrial internet security situation value data set;
s3: constructing a training sample data set and a test sample data set from data in the industrial internet security situation value data set by adopting a sliding window method;
s4: building an industrial internet security situation prediction model based on DE-GWO-SVR to predict future security situations; introducing a differential evolution algorithm DE into a gray wolf algorithm GWO to obtain an improved gray wolf optimization algorithm, initializing the population scale, the maximum iteration times and the spatial dimension in the improved gray wolf optimization algorithm, training a situation prediction model by using a training sample data set constructed in the step S3, finding out an optimal individual by using a residual error between a predicted value and a true value obtained by training the sample data set as a fitness function, and optimizing a support vector regression SVR parameter by using the obtained optimal individual to construct an industrial internet security prediction model based on DE-GWO-SVR;
s5: and (5) checking the safety situation prediction model, and if the safety situation prediction model does not meet the requirements, returning to the step S4 until the prediction result meets the requirements.
2. The DE-GWO-SVR-based industrial internet security situation prediction method according to claim 1, wherein: step S2 specifically includes the following steps:
s21: through the research on the situation influence index classification, the extracted data is preprocessed and quantized and graded;
s22: and (3) safety situation value calculation: calculating the security situation value of the industrial internet in one period according to the following formula:
in the formula, T represents the magnitude of the security situation value, N represents the total number of different types of attacks in one week, i represents the type, and omega represents the type1、ω2、ω3Representing a weight factor, Vi、Ti、AiRepresenting vulnerability degree values, threat degree values and asset values corresponding to attacks of the same type;
s23: normalization processing: data were normalized to the [0,1] interval according to the following equation:
in the formula, XiAnd X'iThe security situation values before and after the normalization processing are respectively represented, i is 1,2, … and 150; xmaxAnd XminRepresenting two maxima and minima in the raw data, respectively.
3. The DE-GWO-SVR-based industrial internet security situation prediction method as claimed in claim 1, wherein: in step S3, a sliding window method is used to determine 80% of data in the industrial internet security situation value sample data set as a training sample data set, 20% of the data is determined as a test sample data set, a sliding window is selected as 5, a single step prediction method is used to predict the last 1 security situation value using the first 5 security situation values, and a sample training set D (X) is constructedi,Yi) And sample test set T ═ (X)i,Yi)。
4. The DE-GWO-SVR-based industrial internet security situation prediction method as claimed in claim 1, wherein: step S4 specifically includes the following steps:
s41: initializing model parameters: setting N as the number of the wolf populations, G as the maximum iteration number, a scaling factor F, a cross probability parameter CR and the value ranges of two coefficients C and G related in the support vector regression, and randomly initializing individuals in the whole population in a search space;
s42: inputting a training sample data set into a DE improved GWO-SVR prediction model for training; randomly generating the position information of all father grey wolf individuals in the population, comparing and selecting the grey wolf with the best adaptability according to the fitness value of each father in the father grey wolf population, respectively using the grey wolf as the father alpha wolf, the grey wolf as the father beta wolf and the grey wolf as the father delta wolf, and updating the position information of other father wolfs in the wolf population by using the following formula:
x(t+1)＝xp(t)-A·D(t)
A＝a·(2r-1)
wherein D (t) represents the distance between one of the three dominant subjects and the target, xp(t) selecting the current position of the target animal, wherein t represents the current iteration times; r belongs to rand (0,1), A is a synergistic factor; when A is more than or equal to 1, the predatory wolves perform global search at a place far away from the hunting target; when | A |<1, predatory wolves begin to gradually surround prey targets;
s43: differential evolution operation: performing mutation operation with the newly generated filial generation gray wolf individual by using the following formula, and performing cross operation with the target parent alpha wolf to generate an intermediate variant filial generation alpha wolf; comparing the adaptability of the two parent-child alpha wolves in the current iteration process, taking the gray wolves with the best adaptability as new parent alpha wolves, updating the position information of other gray wolves in the wolves, and obtaining new parent alpha wolves, beta wolves and delta wolves after sequencing by depending on the individual adaptability values again:
Vi(g)＝xr3(g)+F·(xr1(g)-xr2(g))
in the formula, xr1(g),xr2(g),xr3(g) Is a randomly selected three parent individuals and r1≠r2≠r3≠i，Vi(g) G is the current iteration numerical value of the variant progeny individual; f0Is the initial value of the scaling factor, when F is the same as (F)0,2F0) And F ∈ (0, 1); CR is cross probability used for controlling cross degree, j represents dimension to be crossed, jrandRepresent integer indices, chosen randomly from {1,2, …, n }.
5. The DE-GWO-SVR-based industrial internet security situation prediction method according to claim 4, wherein: in step S5, a determination condition is set as whether the condition reaches the highest prediction precision condition or whether the iteration reaches the G generation, if the requirement of the given termination algorithm loop is reached, the position information of the parent α wolf individual with the best adaptability at this time is output, so as to obtain the best SVR related penalty parameter C and RBF kernel function parameter G, thereby establishing the best industrial internet security situation prediction model, and finally, the test sample data set obtained in step S3 is input, so as to obtain the predicted value of the industrial internet security situation.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010783805.3A CN111917785B (en) | 2020-08-06 | 2020-08-06 | Industrial internet security situation prediction method based on DE-GWO-SVR |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010783805.3A CN111917785B (en) | 2020-08-06 | 2020-08-06 | Industrial internet security situation prediction method based on DE-GWO-SVR |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111917785A CN111917785A (en) | 2020-11-10 |
| CN111917785B true CN111917785B (en) | 2022-07-15 |
Family
ID=73287274
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010783805.3A Active CN111917785B (en) | 2020-08-06 | 2020-08-06 | Industrial internet security situation prediction method based on DE-GWO-SVR |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111917785B (en) |
Families Citing this family (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112801359A (en) * | 2021-01-25 | 2021-05-14 | 海尔数字科技(青岛)有限公司 | Industrial internet security situation prediction method and device, electronic equipment and medium |
| CN113141272B (en) * | 2021-04-20 | 2022-03-15 | 浙江大学 | Network security situation analysis method based on iteration optimization RBF neural network |
| CN113222273B (en) * | 2021-05-26 | 2022-06-07 | 中铁十八局集团有限公司 | TBM tunneling rate prediction method based on GWO-FW-MKL-SVR algorithm |
| CN113358840A (en) * | 2021-06-07 | 2021-09-07 | 西安邮电大学 | Water quality early warning method and system |
| CN115242428B (en) * | 2022-06-08 | 2024-05-31 | 大连大学 | Network security situation prediction method based on optimized CW-RNN |
| CN115277159B (en) * | 2022-07-22 | 2023-05-23 | 重庆邮电大学 | Industrial Internet security situation assessment method based on improved random forest |
| CN115996135B (en) * | 2022-09-09 | 2024-03-12 | 重庆邮电大学 | Industrial Internet malicious behavior real-time detection method based on feature combination optimization |
Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101867498A (en) * | 2009-04-17 | 2010-10-20 | 中国科学院软件研究所 | Network security situation evaluating method |
| CN102098180A (en) * | 2011-02-17 | 2011-06-15 | 华北电力大学 | Network security situational awareness method |
| CN102148820A (en) * | 2011-01-14 | 2011-08-10 | 中国科学技术大学 | System and method for estimating network security situation based on index logarithm analysis |
| CN102694800A (en) * | 2012-05-18 | 2012-09-26 | 华北电力大学 | Gaussian process regression method for predicting network security situation |
| CN106453293A (en) * | 2016-09-30 | 2017-02-22 | 重庆邮电大学 | Network security situation prediction method based on improved BPNN (back propagation neural network) |
| CN109598120A (en) * | 2018-11-15 | 2019-04-09 | 中国科学院计算机网络信息中心 | Security postures intelligent analysis method, device and the storage medium of mobile terminal |
| CN109816204A (en) * | 2018-12-25 | 2019-05-28 | 南京理工大学 | A kind of safety of subway operation Tendency Prediction method based on GA-SVM |
| CN110378526A (en) * | 2019-07-15 | 2019-10-25 | 安徽理工大学 | The mobile method for predicting of bus station based on GW and SVR, system and storage medium |
| CN110392048A (en) * | 2019-07-04 | 2019-10-29 | 湖北央中巨石信息技术有限公司 | Network security situation awareness model and method based on CE-RBF |
| CN111178578A (en) * | 2019-11-26 | 2020-05-19 | 湖南大学 | Financial stock prediction method integrating clustering and ensemble learning |
Family Cites Families (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120068611A (en) * | 2010-12-17 | 2012-06-27 | 한국전자통신연구원 | Apparatus and method for security situation awareness and situation information generation based on spatial linkage of physical and it security |
| US20130318609A1 (en) * | 2012-05-25 | 2013-11-28 | Electronics And Telecommunications Research Institute | Method and apparatus for quantifying threat situations to recognize network threat in advance |
| CN104486141B (en) * | 2014-11-26 | 2018-10-23 | 国家电网公司 | A kind of network security situation prediction method that wrong report is adaptive |
| CN108520272B (en) * | 2018-03-22 | 2020-09-04 | 江南大学 | Semi-supervised intrusion detection method for improving Cantonese algorithm |
| CN111476263B (en) * | 2019-12-27 | 2024-02-09 | 江苏科技大学 | Bearing defect identification method based on SDAE and improved GWO-SVM |
-
2020
- 2020-08-06 CN CN202010783805.3A patent/CN111917785B/en active Active
Patent Citations (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101867498A (en) * | 2009-04-17 | 2010-10-20 | 中国科学院软件研究所 | Network security situation evaluating method |
| CN102148820A (en) * | 2011-01-14 | 2011-08-10 | 中国科学技术大学 | System and method for estimating network security situation based on index logarithm analysis |
| CN102098180A (en) * | 2011-02-17 | 2011-06-15 | 华北电力大学 | Network security situational awareness method |
| CN102694800A (en) * | 2012-05-18 | 2012-09-26 | 华北电力大学 | Gaussian process regression method for predicting network security situation |
| CN106453293A (en) * | 2016-09-30 | 2017-02-22 | 重庆邮电大学 | Network security situation prediction method based on improved BPNN (back propagation neural network) |
| CN109598120A (en) * | 2018-11-15 | 2019-04-09 | 中国科学院计算机网络信息中心 | Security postures intelligent analysis method, device and the storage medium of mobile terminal |
| CN109816204A (en) * | 2018-12-25 | 2019-05-28 | 南京理工大学 | A kind of safety of subway operation Tendency Prediction method based on GA-SVM |
| CN110392048A (en) * | 2019-07-04 | 2019-10-29 | 湖北央中巨石信息技术有限公司 | Network security situation awareness model and method based on CE-RBF |
| CN110378526A (en) * | 2019-07-15 | 2019-10-25 | 安徽理工大学 | The mobile method for predicting of bus station based on GW and SVR, system and storage medium |
| CN111178578A (en) * | 2019-11-26 | 2020-05-19 | 湖南大学 | Financial stock prediction method integrating clustering and ensemble learning |
Non-Patent Citations (3)
| Title |
|---|
| A framework for network security situation awareness based on knowledge discovery;Fang Lan et al.;《2010 2nd International Conference on Computer Engineering and Technology》;20100617;全文 * |
| 基于差分WGAN的网络安全态势预测;王婷婷 等;《计算机科学》;20191115;全文 * |
| 基于改进灰狼优化算法的网络流量预测模型;龙震岳 等;《计算机应用研究》;20170614;全文 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111917785A (en) | 2020-11-10 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN111917785B (en) | Industrial internet security situation prediction method based on DE-GWO-SVR | |
| Li et al. | Applying various algorithms for species distribution modelling | |
| CN106453293B (en) | A kind of network security situation prediction method based on improved BPNN | |
| Chen et al. | Improved XGBoost model based on genetic algorithm | |
| CN110705692B (en) | Nonlinear dynamic industrial process product prediction method of space-time attention network | |
| CN110085327A (en) | Multichannel LSTM neural network Influenza epidemic situation prediction technique based on attention mechanism | |
| CN112581263A (en) | Credit evaluation method for optimizing generalized regression neural network based on wolf algorithm | |
| CN112966714B (en) | Edge time sequence data anomaly detection and network programmable control method | |
| CN106682502A (en) | Intrusion intension recognition system and method based on hidden markov and probability inference | |
| Xie et al. | Unsupervised user identity linkage via factoid embedding | |
| CN110990718B (en) | Social network model building module of company image lifting system | |
| CN109523021A (en) | A kind of dynamic network Structure Prediction Methods based on long memory network in short-term | |
| CN110619540A (en) | Click stream estimation method of neural network | |
| Gandy et al. | MMCTest—a safe algorithm for implementing multiple Monte Carlo tests | |
| CN118151020B (en) | Method and system for detecting safety performance of battery | |
| CN116151485A (en) | Method and system for predicting inverse facts and evaluating effects | |
| CN115051929A (en) | Network fault prediction method and device based on self-supervision target perception neural network | |
| Hu et al. | An efficient Long Short-Term Memory model based on Laplacian Eigenmap in artificial neural networks | |
| CN116340936A (en) | ICS intrusion detection system and method integrating reinforcement learning and feature selection optimization | |
| Jain et al. | Increasing fairness in predictions using bias parity score based loss function regularization | |
| CN106778252B (en) | Intrusion detection method based on rough set theory and WAODE algorithm | |
| Sergeev et al. | Genome-wide analysis of MDR and XDR Tuberculosis from Belarus: Machine-learning approach | |
| CN112528554A (en) | Data fusion method and system suitable for multi-launch multi-source rocket test data | |
| Shi et al. | A genetic algorithm-based approach for classification rule discovery | |
| JP5401885B2 (en) | Model construction method, construction system, and construction program |
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 |