Can I read Hybrid Dimensionality Reduction for Intrusion Detection on EtoBox?
Hybrid Dimensionality Reduction for Intrusion Detection by taha.archi is a document available to read on EtoBox.
What is Hybrid Dimensionality Reduction for Intrusion Detection about?
This research presents a hybrid dimensionality reduction system for network intrusion detection that combines feature selection using Recursive Feature Elimination and feature extraction through Principal Component Analysis, reducing 41 input features to 15 components. The system was evaluated on the UNSW-NB15 dataset, achieving high classification performance with 94.34% accuracy and a low false positive rate of 5.23% using an ensemble of classifiers including Support Vector Classifier, K-nearest Neighbor,
- Author
- taha.archi
- Language
- EN