Taboo and artificial bee colony two-way optimized support vector machine-based intrusion detection method

A technology of support vector machine and artificial bee colony, which is applied in the field of network security, can solve the problems of difficult synchronization of search and modeling, parameter optimization, inability to solve the problem of minimum feature subset search, low feature selection search efficiency, etc., and achieves improved neighborhood search. ability, faster algorithm convergence, and the effect of expanding the diversity of solutions

Inactive Publication Date: 2018-08-24
GUILIN UNIV OF ELECTRONIC TECH
View PDF7 Cites 8 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0005] What the present invention aims to solve is that the feature selection search efficiency in the existing intrusion detection model is not high, the minimum feature subset search cannot be solved, and the search and modeling are difficult to optimize parameters simultaneously. Intrusion Detection Method Based on Group Bidirectional Optimal Support Vector Machine

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
  • Taboo and artificial bee colony two-way optimized support vector machine-based intrusion detection method
  • Taboo and artificial bee colony two-way optimized support vector machine-based intrusion detection method
  • Taboo and artificial bee colony two-way optimized support vector machine-based intrusion detection method

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0056] In order to make the object, technical solution and advantages of the present invention clearer, the present invention will be further described in detail below in combination with specific examples and with reference to the accompanying drawings.

[0057] The present invention is based on the intrusion detection method of taboo and artificial bee colony bidirectional optimization support vector machine, firstly reconstructs the original artificial bee colony algorithm, the general idea is to encode the honey source and support vector machine parameters to be optimized synchronously, and use the random generation method Generate the initial solution of the nectar source, and execute the search strategy based on the taboo-artificial bee colony to find the optimal feature subset. Specifically, it includes introducing the first taboo table in the hired bee search stage, storing and memorizing the local optimal solutions found, and avoiding these local optimal solutions in t...

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 discloses a taboo and artificial bee colony two-way optimized support vector machine-based intrusion detection method. Firstly an original artificial bee colony algorithm is reconstructed; an overall thought is that a honey source and to-be-optimized parameters of a support vector machine are synchronously coded; an initial solution of the honey source is generated in a random generation mode; and a taboo-artificial bee colony-based search strategy is executed to search for an optimal feature subset. The method specifically comprises the steps of introducing a first taboo table in an initial employed bee search stage, performing storage memory on found local optimal solutions, and avoiding the local optimal solutions in subsequent predetermined-time iteration; introducing a second taboo table in an observation bee stage, and introducing a reward and punishment mechanism to improve a fitness function of the honey source, thereby improving the diversity of the solutions; and finally introducing a third taboo table in an investigation bee stage to store the solutions with maximum development frequencies and unimproved fitness values. The method has relatively high feasibility and high practicality.

Description

[0001] technology neighborhood [0002] The invention relates to the technical field of network security, in particular to an intrusion detection method based on a taboo and artificial bee colony bidirectional optimization support vector machine. Background technique [0003] In recent years, with the increasing scale of the network, while the computer network has brought convenience to people's life and work, the methods of network intrusion and attack have become more complex, and the losses caused by various destructive network attacks have become increasingly serious. Although traditional security defense methods and strategies have played a protective role in network security to a certain extent, they have been unable to prevent complex, changeable and increasingly rampant intrusions. Intrusion Detection System) came into being. This kind of active protection strategy technology has been valued by experts and scholars at home and abroad, and how to study an effective int...

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
IPC IPC(8): G06F21/56G06N3/00
CPCG06F21/566G06N3/006
Inventor 古天龙陈汉宜李龙常亮徐周波张少伟
Owner GUILIN UNIV OF ELECTRONIC TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Try Eureka
PatSnap group products