A Robust PCA Feature Selection To Assist Deep Clustering Autoencoder-Based Network Anomaly Detection

This paper presents a novel method to enhance the performance of Clustering-based Autoencoder models for network anomaly detection. Previous studies have developed regularized variants of Autoencoders to learn the latent representation of normal data in a semi-supervised manner, including Shrink Aut...

Ausführliche Beschreibung

Bibliographische Detailangaben

Veröffentlicht in:	2021 8th NAFOSTED Conference on Information and Computer Science (NICS) S. 335 - 341
Hauptverfasser:	Nguyen, Van Quan, Nguyen, Viet Hung, Cao, Van Loi, Khac, Nhien - An Le, Shone, Nathan
Format:	Tagungsbericht
Sprache:	Englisch
Veröffentlicht:	IEEE 21.12.2021
Schlagworte:	Anomaly detection Benchmark testing Clustering-based Autoencoders (CAEs) Computer science Data models Deep Learning Feature extraction Latent Representation Principal component analysis Principal Component Analysis (PCA)
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!