Unlock instant, AI-driven research and patent intelligence for your innovation.

Network security prediction method based on dynamic fuzzy clustering and gray neural network

A gray neural network, dynamic fuzzy technology, applied in the computer field, can solve the problems of local minimization, slow convergence speed, etc.

Active Publication Date: 2021-01-22
CHONGQING UNIV OF POSTS & TELECOMM
View PDF4 Cites 1 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

BP neural network is a multi-layer feed-forward neural network trained according to the error backpropagation algorithm, which has good nonlinear mapping ability, self-learning and self-adaptive ability, generalization ability and fault tolerance ability, but there are still local minima and slow convergence

Method used

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
View more

Image

Smart Image Click on the blue labels to locate them in the text.
Viewing Examples
Smart Image
  • Network security prediction method based on dynamic fuzzy clustering and gray neural network
  • Network security prediction method based on dynamic fuzzy clustering and gray neural network
  • Network security prediction method based on dynamic fuzzy clustering and gray neural network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment 1

[0066] This embodiment further describes step S4, including the following steps:

[0067] S41. Perform normalization processing on the real number genetic coding system of the individual, wherein, x pj represents the individual x p The genetic coding system of the jth position of the individual x after normalization p The gene code system of the jth position of is expressed as:

[0068]

[0069] S42. According to the normalized operation, by The formula constructs the fuzzy similarity matrix R among individuals;

[0070] S43. By looking for the minimum transitive closure of the fuzzy matrix R, transform it into a fuzzy equivalent matrix T according to the fuzzy similarity matrix R established in the upper layer, that is, obtain the corresponding fuzzy equivalent matrix T, and use T to cluster the population, Compare the similarity coefficient β with the equivalence coefficient between each pair of individuals, if β≤T pq , then the individual x p and x q Divided into...

Embodiment 2

[0084] BP neural network structure such as figure 2 , to establish a three-layer BP network, where l i is the output of the i-th node in the input layer, H i is the output of the i-th node in the hidden layer, O i is the output of the i-th node in the output layer, WIH ij Connect the weights between the i-th node in the input layer and the j-th node in the hidden layer, WHO ji is the connection weight between the jth node in the hidden layer and the ith node in the output layer.

[0085] S51. Initialize population P, including crossover scale, crossover probability, and mutation probability P m and for any WIH ij and WHO ji For initialization, real numbers are used for encoding, and the initialization population is 30.

[0086] S52. Calculate each individual evaluation function and sort it, according to The probability value selects network individuals, where f i is the fitness value of individual i, which can be measured by the sum of squared errors E, namely:

[00...

Embodiment 3

[0095] This embodiment further describes step S8, including the following steps:

[0096] S81. Data preprocessing, determining the number of samples required for building a model, namely:

[0097]

[0098] Finds the first-order cumulative sequence.

[0099] S82. Determine the system behavior sequence, from Choose one of the following bounded sequences

[0100] S83, determine the relevant factor sequence, select the lower bound sequence (or intermediate value sequence or upper bound sequence) of all relevant factor sequences as the relevant factor sequence, such as

[0101] S84. Use the gray relational analysis method to determine the influence of relevant factors on the development of system behavior sequence variables, and determine N v value, build GM(0,N v ) model and solve it, and the corresponding predicted value is:

[0102] S85, re-select relevant factors, repeat steps S82, S83, and record the corresponding predicted value as:

[0103]

[0104] in, ...

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

PUM

No PUM Login to View More

Abstract

The invention relates to the field of computers, in particular to a network security prediction method based on dynamic fuzzy clustering and a gray neural network. The method comprises the following steps: regarding each data type of a network intrusion attack type as a population, initializing the population, and encoding the population by adopting real number encoding; processing the crossover operator and the mutation operator by using an adaptive method; roughly adjusting and optimizing the initial weight distribution by using an adaptive genetic algorithm based on dynamic fuzzy clusteringoptimization; and calculating an individual fitness function of the population. The method has good fault tolerance and stability.

Description

technical field [0001] The invention relates to the field of computers, in particular to a network security prediction method based on dynamic fuzzy clustering and gray neural network. Background technique [0002] The rapid development of network and communication technology has led to the large-scale application of the Internet. The application of Internet services has greatly facilitated people's life and work, and promoted the progress and development of society. But at the same time, the frequency of network security incidents has greatly increased, and they are organized, purposeful, and highly targeted. Existing traditional security protection devices have single functions, low organizational cooperation ability, and fail to protect the security of the network from a macro perspective. These traditional security protection measures can no longer protect us from malicious attacks from the network. . Therefore, security technology should keep pace with the times, use ...

Claims

the structure of the environmentally friendly knitted fabric provided by the present invention; figure 2 Flow chart of the yarn wrapping machine for environmentally friendly knitted fabrics and storage devices; image 3 Is the parameter map of the yarn covering machine
Login to View More

Application Information

Patent Timeline
no application Login to View More
Patent Type & Authority Applications(China)
IPC IPC(8): H04L12/24G06K9/62G06N3/08G06N3/12
CPCH04L41/147H04L41/145G06N3/084G06N3/126G06F18/23
Inventor 徐光侠张家俊马创刘俊王利
Owner CHONGQING UNIV OF POSTS & TELECOMM