• Home
  • Search
  • A Machine Learning-Based Framework with Enhanced Feature Selection and Resampling for Improved Intrusion Detection
  • Cite Icon9
  • https://doi.org/10.3390/math12121799Copy DOI Icon

A Machine Learning-Based Framework with Enhanced Feature Selection and Resampling for Improved Intrusion Detection

Show More
  • Abstract
  • Highlights & Summary
  • PDF
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Intrusion Detection Systems (IDSs) play a crucial role in safeguarding network infrastructures from cyber threats and ensuring the integrity of highly sensitive data. Conventional IDS technologies, although successful in achieving high levels of accuracy, frequently encounter substantial model bias. This bias is primarily caused by imbalances in the data and the lack of relevance of certain features. This study aims to tackle these challenges by proposing an advanced machine learning (ML) based IDS that minimizes misclassification errors and corrects model bias. As a result, the predictive accuracy and generalizability of the IDS are significantly improved. The proposed system employs advanced feature selection techniques, such as Recursive Feature Elimination (RFE), sequential feature selection (SFS), and statistical feature selection, to refine the input feature set and minimize the impact of non-predictive attributes. In addition, this work incorporates data resampling methods such as Synthetic Minority Oversampling Technique and Edited Nearest Neighbor (SMOTE_ENN), Adaptive Synthetic Sampling (ADASYN), and Synthetic Minority Oversampling Technique–Tomek Links (SMOTE_Tomek) to address class imbalance and improve the accuracy of the model. The experimental results indicate that our proposed model, especially when utilizing the random forest (RF) algorithm, surpasses existing models regarding accuracy, precision, recall, and F Score across different data resampling methods. Using the ADASYN resampling method, the RF model achieves an accuracy of 99.9985% for botnet attacks and 99.9777% for Man-in-the-Middle (MITM) attacks, demonstrating the effectiveness of our approach in dealing with imbalanced data distributions. This research not only improves the abilities of IDS to identify botnet and MITM attacks but also provides a scalable and efficient solution that can be used in other areas where data imbalance is a recurring problem. This work has implications beyond IDS, offering valuable insights into using ML techniques in complex real-world scenarios.

Loading PDF

Similar Papers
  • PDF
  • Research Article
  • Citations11

A Rebalancing Framework for Classification of Imbalanced Medical Appointment No-show Data

  • Jan 27, 2021
  • Journal of Data and Information Science
  • Ulagapriya Krishnan +1
  • Research Article
  • Citations15

Impact of Data Balancing and Feature Selection on Machine Learning-based Network Intrusion Detection

  • Feb 28, 2023
  • JOIV : International Journal on Informatics Visualization
  • Azhari Shouni Barkah +3
  • PDF
  • Research Article
  • Citations101

Enhanced Intrusion Detection with LSTM-Based Model, Feature Selection, and SMOTE for Imbalanced Data

  • Jan 05, 2024
  • Applied Sciences
  • Hussein Ridha Sayegh +2
  • PDF
  • Research Article
  • Citations2

Advanced Predictive Modeling for Hepatitis C Diagnosis Using Machine Learning

  • Nov 19, 2024
  • Clinical and Molecular Epidemiology
  • Mahdyeh Abbasi Hezari +3
  • Research Article
  • Citations37

Applying machine learning methods to predict geology using soil sample geochemistry

  • Aug 11, 2022
  • Applied Computing and Geosciences
  • Timothy C.C Lui +4
  • Research Article
  • Citations41

Advanced Hybrid Transformer-CNN Deep Learning Model for Effective Intrusion Detection Systems with Class Imbalance Mitigation Using Resampling Techniques

  • Dec 23, 2024
  • Future Internet
  • Hesham Kamal +1
  • Research Article
  • Citations1

A machine learning-based EEG signal analysis framework to enhance emotional state detection.

  • Dec 01, 2025
  • Cognitive neurodynamics
  • Md Amir Abdal Sobhani +4
  • Research Article

Towards Robust Intrusion Detection: Exploring Feature Selection, Balancing Strategies, and Deep Learning for Minority Class Optimization

  • Jan 01, 2026
  • International Journal of Advanced Computer Science and Applications
  • Khalid Labhalla +1
  • PDF
  • Research Article
  • Citations1

A Performance Analysis of ML-Based Intrusion Detection Systems in Cloud Environments

  • Jan 01, 2025
  • International Journal of Electrical and Electronic Engineering & Telecommunications
  • Gandla Shivakanth
  • Research Article

A Weighted Average-Based Heterogeneous Datasets Integration Framework for Intrusion Detection Using a Hybrid Transformer–MLP Model

  • Mar 16, 2026
  • Technologies
  • Hesham Kamal +1
  • Research Article

Interpretable Ensemble-Based Intrusion Detection Using Feature Selection on the ToN_IoT Dataset

  • Dec 24, 2025
  • JISA(Jurnal Informatika dan Sains)
  • Vaman Shakir Sulaiman +1
  • Research Article
  • Citations265

Improving AdaBoost-based Intrusion Detection System (IDS) Performance on CIC IDS 2017 Dataset

  • Mar 01, 2019
  • Journal of Physics: Conference Series
  • Arif Yulianto +2
  • Conference Article

Effective Intrusion Detection in WSNs: Evaluating Machine Learning Models on WSN DS and WUSTL EHMS-2020 Datasets

  • Feb 13, 2025
  • Ziaur Rahman +1
  • Conference Article
  • Citations4

GMR based pain intensity recognition using imbalanced data handling techniques

  • Oct 01, 2016
  • Anima Majumder +2
  • Research Article
  • Citations128

Sentiment Analysis of Customers’ Reviews Using a Hybrid Evolutionary SVM-Based Approach in an Imbalanced Data Distribution

  • Jan 01, 2022
  • IEEE Access
  • Ruba Obiedat +6
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.