Looking for breakthrough ideas for innovation challenges? Try Patsnap Eureka!

Intrusion detection method by use of improved self-organizing feature neural network clustering algorithm

A clustering algorithm and neural network technology, applied in the field of machine learning and intrusion detection, intrusion detection, can solve the problem of neuron position deviation and reduce the possible effect of human control

Active Publication Date: 2017-05-31
BEIJING UNIV OF TECH
View PDF4 Cites 6 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

Some of the above-mentioned problems can be improved by locally optimal adjustment or adding neurons, but growing new neurons from existing neurons will lead to the possibility that the position of the current neurons will deviate. There is also a coupling between neurons that needs to be considered

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
  • Intrusion detection method by use of improved self-organizing feature neural network clustering algorithm
  • Intrusion detection method by use of improved self-organizing feature neural network clustering algorithm
  • Intrusion detection method by use of improved self-organizing feature neural network clustering algorithm

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0020] Such as figure 1 As shown, the present invention provides a kind of intrusion detection method that adopts improved self-organizing feature neural network clustering algorithm to comprise: by data cleaning, two-level clustering algorithm (Canopy) and improved self-organizing feature mapping neural network clustering method (SOFM) and abnormal intrusion detection, as follows:

[0021] 1.1 Data cleaning

[0022] Such as figure 2 As shown, the data to be detected comes from log files in the cloud storage system environment. For unstructured log files, data structure initialization processing is required here to make the data to be detected meet the input format. The algorithm description is shown in Algorithm 1.

[0023] Algorithm 1. Data cleaning algorithm description

[0024] Input: the log file log_file.txt under the cloud storage system, the regular expression reg for extracting feature attributes

[0025] Output: structured training data dataSet

[0026] 1. Tra...

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 provides an intrusion detection method by use of an improved self-organizing feature neural network clustering algorithm. The intrusion detection method comprises the following steps: performing data cleaning on log file data under a cloud storage system environment, training the cleaned log data by use of a self-organizing feature neural network clustering method based on a dual-layer clustering algorithm to produce a data classification result, and performing exception analysis based on a PCA algorithm so as to achieve an intrusion detection aim.

Description

technical field [0001] The invention belongs to the field of machine learning and intrusion detection, and in particular relates to an intrusion detection method implemented in a cloud storage environment by adopting a self-organizing feature mapping neural network clustering algorithm. Background technique [0002] With the rapid development of the information age, various industries are transforming to the direction of Internet +. With the popularization of network services, network security issues have become the focus of everyone's attention. Therefore, the intrusion detection system has also entered people's field of vision. It can evaluate the security of computer systems and networks by obtaining behavioral information of computer systems, networks and users through real-time analysis. In addition, with the explosive growth of data volume in various industries, cloud storage has become the leader in all fields. As a new storage model, cloud storage has changed the tra...

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): H04L12/24H04L29/06G06K9/62G06N3/02
CPCH04L41/145H04L63/1416G06N3/02G06F18/23
Inventor 王丹魏卓君赵文兵付利华杜晓林
Owner BEIJING UNIV OF TECH
Who we serve
  • R&D Engineer
  • R&D Manager
  • IP Professional
Why Patsnap Eureka
  • Industry Leading Data Capabilities
  • Powerful AI technology
  • Patent DNA Extraction
Social media
Patsnap Eureka Blog
Learn More
PatSnap group products