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

Neural network-based intrusion detection algorithm for wireless sensor network

A network intrusion detection, wireless sensor technology, applied in wireless communication, network topology, electrical components, etc., can solve the problem of lack of research results in intrusion detection technology

Inactive Publication Date: 2014-03-05
TIANJIN POLYTECHNIC UNIV
View PDF0 Cites 17 Cited by
  • Summary
  • Abstract
  • Description
  • Claims
  • Application Information

AI Technical Summary

Problems solved by technology

[0003] The problem to be solved by the present invention is that the current wireless sensor network intrusion detection technology still lacks mature research results and cannot well meet the requirements of special networks such as wireless sensor networks, and proposes an intrusion detection suitable for wireless sensor network structures algorithm

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
  • Neural network-based intrusion detection algorithm for wireless sensor network
  • Neural network-based intrusion detection algorithm for wireless sensor network
  • Neural network-based intrusion detection algorithm for wireless sensor network

Examples

Experimental program
Comparison scheme
Effect test

Embodiment Construction

[0009] (1) A neural network-based wireless sensor network intrusion detection algorithm includes the following steps:

[0010] Preprocess the data;

[0011] Train the BP neural network;

[0012] Train the generalized neural network;

[0013] Improve and train the BP neural network.

[0014] (2) Preprocess the data as described in (1), and the main steps are as follows:

[0015] Step 1: Data Mapping. Each line of this data set is a record collected and processed by TCPdump, which contains 41 feature values ​​and 1 attack type description. Each feature is separated by a comma, and finally the attack type is separated by a comma. is a standard CSV file. Due to the complex types of data, there are discrete types (such as protocol types TCP, UDP...) and continuous types (duration, number of packets sent, etc.), which need to be processed separately. First, data mapping is performed to map symbolic data to numerical data. For example, in the feature value, the second dimensio...

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 simply discloses an intrusion detection model by combining the existing network intrusion detection technology aiming at cluster heads (Cluster Head, CH for short) of a cluster-based wireless sensor network (Cluster-based Wireless Sensor Network, CWSN for short). The characteristics of low CH operating rate and limited energy are fully considered; the designed model is simple in structure, and composed of the following three modules: a misuse detection module, an abnormality detection module and a decision module, wherein the misuse detection module utilizes the neural network as a core. The existing neural network is various in variety and each neural network has advantages and defects, a back propagation (BP) neural network, a generalized regression neural network and a BP neural network optimized on the basis of a genetic algorithm are respectively selected to carry out an experiment to obtain the neural network which is more suitable for an intrusion detection system (IDS) aiming at a wireless sensor network (WSN). The experiment adopts a KDDCUP1999 data set, and a matrix laboratory (MATLAB) is utilized to carry out a simulation experiment.

Description

technical field [0001] The invention relates to an intrusion detection algorithm of a wireless sensor network, in particular, an intrusion detection algorithm of a wireless sensor network based on a neural network. Background technique [0002] Intrusion detection research can be traced back to 1980, when James P. Anderson first proposed the concept of intrusion detection. In 1987, Dorothy Elizabeth Denning proposed the abstract model of intrusion detection system, and first put forward the concept of intrusion detection as a strategy of computer system security defense. Compared with traditional encryption and access control methods, intrusion detection system is a new computer security strategy. At present, there are three main development trends of intrusion detection technology at home and abroad: distributed intrusion detection, intelligent intrusion detection and the trend of combining with network security technology. However, the research on applying intrusion dete...

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): H04W12/12H04W84/18H04W12/121
Inventor 孙学梅张一鸣闫博
Owner TIANJIN POLYTECHNIC UNIV
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