Paper
28 November 2022 Identification of abnormal traffic in combined network based on impulse response feature detection
Rongping Wang
Author Affiliations +
Proceedings Volume 12503, International Conference on Network Communication and Information Security (ICNCIS 2022); 125030X (2022) https://doi.org/10.1117/12.2657132
Event: International Conference on Network Communication and Information Security (ICNCIS 2022), 2022, Qingdao, China
Abstract
In order to improve the ability of identifying the abnormal traffic of 5G terminal cascaded wireless sensor networks, a method of identifying the abnormal traffic of 5G terminal cascaded wireless sensor networks based on impulse response feature detection is proposed. Construct the abnormal traffic data distribution structure model of the 5G terminal cascaded wireless sensor composite network, collect the big data and analyze the spectrum parameters of the 5G terminal cascaded wireless sensor composite network traffic by single frame scanning and mixed coding monitoring methods, extract the characteristic parameters of the sudden differential traffic data in the 5G terminal cascaded wireless sensor composite network, and analyze the data according to the traceability parameters of the abnormal traffic. The fuzzy clustering center tracking and detection of abnormal traffic data of 5G terminal cascade wireless sensor composite network is realized by adopting the traffic output conversion identification method of 5G terminal cascade wireless sensor composite network. According to the clustering result of fuzzy information, an abnormal feature distribution fusion model of abnormal traffic sequence of 5G terminal cascade wireless sensor composite network is established, and the impulse response characteristic value and association rule distribution set of abnormal traffic information are used for tracking and detection. The fuzzy weight analysis and adaptive learning of the abnormal traffic sequence of the 5G terminal cascade wireless sensor network are realized, and the abnormal traffic data in the 5G terminal cascade wireless sensor network is classified and marked by the BP neural network classification method, so as to realize the feature extraction and tracking detection of the abnormal traffic information of the 5G terminal cascade wireless sensor network. The test results show that this method has high accuracy, good tracking performance and strong anti-interference ability in tracking and detecting abnormal traffic data of 5G terminal cascaded wireless sensor integrated network, which improves the security and anti-attack ability of 5G terminal cascaded wireless sensor integrated network.
© (2022) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Rongping Wang "Identification of abnormal traffic in combined network based on impulse response feature detection", Proc. SPIE 12503, International Conference on Network Communication and Information Security (ICNCIS 2022), 125030X (28 November 2022); https://doi.org/10.1117/12.2657132
Advertisement
Advertisement
RIGHTS & PERMISSIONS
Get copyright permission  Get copyright permission on Copyright Marketplace
KEYWORDS
Sensor networks

Sensors

Data modeling

Composites

Fuzzy logic

Computing systems

Data conversion

Back to Top