Related Experiment Video
Updated: Aug 17, 2025
07:35
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
7.6K
A Novel Anomaly-Based Intrusion Detection Model Using PSOGWO-Optimized BP Neural Network and GA-Based Feature
Saeid Sheikhi1, Panos Kostakos1
1Center for Ubiquitous Computing, University of Oulu, 90570 Oulu, Finland.
Sensors (Basel, Switzerland)
|December 11, 2022
Summary
This study introduces a new intrusion detection model using a genetic algorithm for feature selection and a hybrid optimization technique for training a neural network. The model enhances network security by improving intrusion detection accuracy and reducing errors.
Area of Science:
- Computer Science
- Cybersecurity
- Network Security
Background:
- Intrusion detection systems (IDS) face challenges with high-dimensional data in modern networks.
- Irrelevant features increase complexity, processing time, and reduce detection rates in IDS.
Purpose of the Study:
- To develop a novel intrusion detection model to address dimensionality issues in network security.
- To enhance the accuracy and efficiency of intrusion detection systems.
Main Methods:
- Utilized a genetic algorithm (GA) for effective feature selection from the NSL-KDD dataset.
- Employed a hybrid optimization algorithm (HPSOGWO), combining Particle Swarm Optimization (PSO) and Grey Wolf Optimization (GWO), to train a Back-Propagation Neural Network (BPNN).
- Applied the HPSOGWO-BPNN model for binary and multi-class classification on network traffic data.
Main Results:
- The GA effectively selected highly correlated features, improving detection capabilities.
- The HPSOGWO-BPNN model demonstrated superior performance compared to existing methods.
- Achieved higher accuracy, lower error rates, and improved detection of various attack types.
Conclusions:
- The proposed hybrid optimization and feature selection model significantly enhances intrusion detection system performance.
- This approach offers a more accurate and efficient solution for network security against diverse cyber threats.
