An AdamW-Based Deep Neural Network Using Feature Selection and Data Oversampling for Intrusion Detection DOI

Zhuoer Lu,

Xiaoyong Li, Pengfei Qiu

et al.

Published: Aug. 18, 2023

With the development of Internet and increasing number users, cyber security has become a major concern for most netizens. In this paper, we propose an AdamW-based neural network using feature selection data oversampling intrusion detection. First, use Random Forest classifier to select 25 important features classifying traffic. Second, given imbalance different types samples in NSL-KDD dataset, ADASYN oversample minority samples. addition, achieve better performance, AdamW as optimizer our deep network. Finally, tune hyperparameters get best classification results Compared with other classical machine learning models detection, achieves high detection performance: test set loss is reduced 0.0001 accuracy improved 99.8%.

Language: Английский

A Comprehensive Survey of Intrusion Detection System Using Machine Learning and Deep Learning Approaches DOI

Kotnur Abhiram,

M. Hariharan,

Sindhu Ravindran

et al.

2022 8th International Conference on Advanced Computing and Communication Systems (ICACCS), Journal Year: 2024, Volume and Issue: unknown, P. 1927 - 1932

Published: March 14, 2024

Language: Английский

Citations

0
An RNA Evolutionary Algorithm Based on Gradient Descent for Function Optimization DOI Creative Commons
Qiuxuan Wu,

Zikai Zhao,

Mingming Chen

et al.

Journal of Computational Design and Engineering, Journal Year: 2024, Volume and Issue: 11(4), P. 332 - 357

Published: July 3, 2024

Abstract The optimization of numerical functions with multiple independent variables was a significant challenge numerous practical applications in process control systems, data fitting, and engineering designs. Although RNA genetic algorithms offer clear benefits function optimization, including rapid convergence, they have low accuracy can easily become trapped local optima. To address these issues, new heuristic algorithm proposed, gradient descent-based algorithm. Specifically, adaptive moment estimation (Adam) employed as mutation operator to improve the development ability Additionally, two operators inspired by inner-loop structure molecules were introduced: an crossover operator. These enhance global exploration early stages evolution enable it escape from consists stages: pre-evolutionary stage that employs identify individuals vicinity optimal region post-evolutionary applies descent further solution’s quality. When compared current advanced for solving problems, Adam Genetic Algorithm (RNA-GA) produced better solutions. In comparison RNA-GA (GA) across 17 benchmark functions, ranked first best result average rank 1.58 according Friedman test. set 29 CEC2017 suite, such African Vulture Optimization Algorithm, Dung Beetle Optimization, Whale Grey Wolf Optimizer, 1.724 Our not only achieved improvements over but also performed excellently among various achieving high precision optimization.

Language: Английский

Citations

0
An AdamW-Based Deep Neural Network Using Feature Selection and Data Oversampling for Intrusion Detection DOI

Zhuoer Lu,

Xiaoyong Li, Pengfei Qiu

et al.

Published: Aug. 18, 2023

With the development of Internet and increasing number users, cyber security has become a major concern for most netizens. In this paper, we propose an AdamW-based neural network using feature selection data oversampling intrusion detection. First, use Random Forest classifier to select 25 important features classifying traffic. Second, given imbalance different types samples in NSL-KDD dataset, ADASYN oversample minority samples. addition, achieve better performance, AdamW as optimizer our deep network. Finally, tune hyperparameters get best classification results Compared with other classical machine learning models detection, achieves high detection performance: test set loss is reduced 0.0001 accuracy improved 99.8%.

Language: Английский

Citations

0