Business Faculty Publications
Document Type
Article
Publication Date
9-22-2024
Publication Title
Engineering, Technology & Applied Science Research
Keywords
autoencoders; anomaly detection; high-dimensional data; machine learning; data analysis; model evaluation; Convolutional Neural Networks (CNNs); NSL-KDD; UNSW-NB15; MSE
Disciplines
Business | Computer and Systems Architecture
Abstract
This study presents an Auto-Encoder Convolutional Neural Network (AECNNs) approach for anomaly detection in high-dimensional datasets. Unsupervised learning-based algorithms have a strong theoretical foundation and are widely used for anomaly detection in high-dimensional datasets, but some limitations significantly reduce their performance. This study proposes an algorithm to address these limitations. The proposed AECNN combines various convolutional layers, feature extraction, dimensionality reduction, and data preprocessing and was evaluated using accuracy, precision, recall, and F1-score. The performance of the proposed model was evaluated using a large real benchmark dataset. The proposed CNN-based autoencoder distinguished anomalies with an AUC score of 0.83 and remarkable accuracy, precision, recall, and F1 score.
Recommended Citation
Javad, Aetsam; Anjum, Madiha; Ahmed, Hassan; Ali, Arshad; Shahzad, H. M.; Lhan, Hamayun; and Alshahrani, Abdulaziz M., "Leveraging Convolutional Neural Network (CNN)-based Auto Encoders for Enhanced Anomaly Detection in High-Dimensional Datasets" (2024). Business Faculty Publications. 356.
https://engagedscholarship.csuohio.edu/bus_facpub/356
Version
Publisher's PDF
Publisher's Statement
This article was originally published in Engineering, Technology & Applied Science Research (ETASR).
Volume
14
Issue
6