Issue |
ITM Web Conf.
Volume 70, 2025
2024 2nd International Conference on Data Science, Advanced Algorithm and Intelligent Computing (DAI 2024)
|
|
---|---|---|
Article Number | 01014 | |
Number of page(s) | 7 | |
Section | Traffic Prediction and Analysis | |
DOI | https://doi.org/10.1051/itmconf/20257001014 | |
Published online | 23 January 2025 |
Network traffic monitoring based on CNN-SVM
Department of Computer Science and Software Engineering, School of Hebei University of Technology, 300401 Tianjin, China
Corresponding author: 225813@stu.hebut.edu.cn
In a modern complex network, network monitoring and measurement have become increasingly important. The traditional network traffic monitoring methods face the challenge of efficiency and accuracy when dealing with massive data. The proposed hybrid model in this study uses convolutional neural networks (CNNs) and support vector machines (SVMs) to address these concerns and increase the effectiveness of network traffic monitoring. This paper uses CNN to extract features from network traffic data. CNN has the ability to recognize intricate patterns in the data and automatically extract valuable characteristics from the raw data. The SVM classifier receives the retrieved characteristics and uses them to further classify the data in order to distinguish between normal and abnormal traffic. By doing this, this paper may more successfully combine the benefits of SVM for classification with CNN’s advantages for feature learning, enhancing traffic monitoring’s precision and resilience. According to the experimental data, the hybrid model performs far better in network traffic categorization tasks than the standard techniques, with a reduced false positive rate and higher accuracy. This research shows that CNN-SVM model is an effective network traffic monitoring tool, which can provide high quality detection results while ensuring high efficiency.
© The Authors, published by EDP Sciences, 2025
This is an Open Access article distributed under the terms of the Creative Commons Attribution License 4.0, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
Current usage metrics show cumulative count of Article Views (full-text article views including HTML views, PDF and ePub downloads, according to the available data) and Abstracts Views on Vision4Press platform.
Data correspond to usage on the plateform after 2015. The current usage metrics is available 48-96 hours after online publication and is updated daily on week days.
Initial download of the metrics may take a while.