Nelder-Mead Optimized Weighted Voting Ensemble Learning for Network Intrusion Detection

Authors : Mustafa Burak Ürün, Yusuf Sönmez

Pages : 2139-2158

Doi:10.29130/dubited.1440640

View : 35 | Download : 59

Publication Date : 2024-10-23

Article Type : Research Paper

Abstract :The rise in internet usage and data transfer rates has led to numerous anomalies. Hence, anomaly-based intrusion detection systems (IDS) are essential in cybersecurity because of their ability to identify unknown cyber-attacks, especially zero-day attacks that signature-based IDS cannot detect. This study proposes an ensemble classification for intrusion detection using a weighted soft voting system with KNN, XGBoost, and Random Forest base models. The base model weights are optimized using the Nelder-Mead simplex method to improve the overall ensemble performance. We propose a robust intrusion detection framework that uses soft-voting classifier-level weights optimized using the Nelder-Mead algorithm and feature selection. We evaluated the system\'s performance using the KDD99 and UNSW-NB15 datasets, which demonstrated that the proposed approach exceeded other existing methods in respect of accuracy and provided comparable results with fewer features. The proposed system and its hyperparameter optimization technique were compared with other cyber threat detection and mitigation systems to determine their relative effectiveness and efficiency.
Keywords : Saldırı Tespit Sistemleri, Topluluk Öğrenme, Yumuşak Oylama, Hiperparametre Optimizasyonu, Nelder Mead Algoritması