Related Experiment Video
Updated: May 5, 2026
13:19
Deep Neural Networks for Image-Based Dietary Assessment
Published on: March 13, 2021
9.0K
GSOOA-1DDRSN: Network traffic anomaly detection based on deep residual shrinkage networks.
Fengqin Zuo1, Damin Zhang1, Lun Li1
1College of Big Data and Information Engineering, Guizhou University, Guiyang, 550025, China.
Heliyon
|June 13, 2024
Summary
This study introduces GSOOA-1DDRSN for network traffic anomaly detection, improving accuracy and reducing computation time. The new method enhances cybersecurity by effectively identifying malicious network behavior.
Area of Science:
- Cybersecurity
- Network Intrusion Detection
- Machine Learning
Background:
- Network traffic anomaly detection is crucial for cyberspace security.
- Traditional machine learning methods struggle with large-scale network data.
- Deep learning offers advantages in feature extraction and generalization for intrusion detection.
Purpose of the Study:
- To propose an enhanced network traffic anomaly detection method.
- To improve the accuracy and efficiency of detecting malicious network traffic.
- To address the limitations of traditional methods in handling complex threats.
Main Methods:
- Developed GSOOA-1DDRSN, a network traffic anomaly detection system.
- Utilized an improved Osprey optimization algorithm for feature selection and dimensionality reduction.
- Employed a one-dimensional deep residual shrinkage network (1DDRSN) as the classifier.
Main Results:
- GSOOA-1DDRSN improved multi-classification accuracy, precision, recall, and F1 Score by 2-3% compared to 1DDRSN.
- Reduced computation costs by 20-30% on NSL-KDD and UNSW-NB15 datasets.
- Demonstrated superior classification accuracy and effective feature reduction compared to other models.
Conclusions:
- GSOOA-1DDRSN significantly enhances network traffic anomaly detection performance.
- The proposed method offers a more efficient and accurate solution for intrusion detection.
- This approach provides a robust defense against evolving cyber threats.
