The WSN intrusion detection method based on deep data mining

Aiming at the defects that wireless sensor network is vulnerable to intrusion attacks and affects communication performance, a WSN intrusion detection method based on deep data mining is presented. The network traffic capture tool is used to capture the data stream of the wireless sensor network, an...

Full description

Saved in:
Bibliographic Details
Published in:Journal of cyber security Vol. 7; no. 3; pp. 115 - 133
Main Author: Zhang, Yiwei
Format: Journal Article
Language:English
Published: Taylor & Francis 03.07.2023
Subjects:
Deep data mining
genetic algorithm
intrusion detection method
k-means clustering
WSN
ISSN:2374-2917, 2374-2925
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Aiming at the defects that wireless sensor network is vulnerable to intrusion attacks and affects communication performance, a WSN intrusion detection method based on deep data mining is presented. The network traffic capture tool is used to capture the data stream of the wireless sensor network, and the captured data stream is cleaned and normalized. An improved deep sparse autoencoder is used to extract WSN intrusion features from the normalized data stream. The extracted intrusion features are taken as the initial data of K-means clustering, to optimize the k-means clustering algorithm (KMCA) by genetic algorithm. The reasonable initial center point searched by the genetic algorithm is taken as the input parameter of the improved KMCA. The proposed method can detect internal attacks, external attacks and other intrusion behaviors in wireless sensor networks, and the false detection rate is less than 1%.
ISSN:2374-2917
2374-2925
DOI:10.1080/23742917.2022.2162195