Related Experiment Video
Updated: Jun 14, 2026
07:35
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
Published on: October 11, 2018
7.9K
Network security analysis based on feature selection and optimized fireworks algorithm.
Liang Zhou1, Chang Liu1, Li Tian1
1State Grid Hubei Electric Power Research Institute, Hubei, 430077, Wuhan, China.
Scientific Reports
|December 19, 2025
Summary
This study introduces an improved Fireworks Algorithm for network security, enhancing data processing and threat detection sensitivity. While efficient, it shows potential overfitting on complex datasets, requiring further generalization improvements.
Area of Science:
- Cybersecurity
- Artificial Intelligence
- Machine Learning
Background:
- Traditional network security methods struggle with high-dimensional dynamic data, leading to poor feature selection and low threat detection sensitivity.
- Evolving cyber threats necessitate advanced analytical models for real-time network security.
- Existing algorithms lack adaptability and efficiency in processing large-scale, dynamic network data.
Purpose of the Study:
- To propose a multi-objective, multi-label feature selection model for enhanced network security analysis.
- To integrate an optimized Fireworks Algorithm with fuzzy neural networks for improved real-time threat detection.
- To address limitations in data processing capacity, sensitivity, and efficiency of traditional network security methods.
Main Methods:
- Developed an Improved Fireworks Algorithm Model incorporating Gaussian operators and adaptive functions.
- Integrated fuzzy neural networks for enhanced real-time threat response capabilities.
- Validated the model on Palmer Penguin, Fashion MNIST, and Bike Sharing datasets of varying scales.
Main Results:
- Achieved data processing capacity of 5,000 samples, a 66% improvement over baseline algorithms.
- Demonstrated detection sensitivity ranging from 70% to 100%, outperforming traditional methods by 30% points.
- Reduced adaptive adjustment time by 50%, indicating significant efficiency gains.
- Observed potential overfitting or insufficient generalization on a medium-sized dataset, scoring 5/10 in comprehensive performance.
Conclusions:
- The proposed model offers a robust framework for dynamic network security analysis, significantly improving processing capacity and detection sensitivity.
- The optimized Fireworks Algorithm demonstrates enhanced efficiency in network security applications.
- Scalability constraints and generalization in complex data environments require further investigation and model refinement.
Related Concept Videos
01:26Pharmacokinetic Models: Comparison and Selection Criterion
Physiological and compartmental models are valuable tools used in studying biological systems. These models rely on differential equations to maintain mass balance within the system, ensuring an accurate representation of the dynamic processes at play.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
Physiological models take a detailed approach by considering specific molecular processes. They can predict drug distribution, metabolism, and elimination changes, providing a comprehensive understanding of how drugs interact with the body.
01:28Methods of Medium Optimization
Optimizing growth media enhances microbial proliferation and maximizes product yield. Statistical experimental design methodologies provide structured and reproducible approaches, offering progressively higher levels of robustness and efficiency.The One-Factor-at-a-Time (OFAT) MethodThe One-Factor-at-a-Time (OFAT) method involves adjusting a single variable while keeping all others constant. However, it cannot detect interactions between variables, often leading to suboptimal outcomes when...