Autoencoder Based Anomaly Detection in IOT Networks
International Journal of Creative and Open Research in Engineering and Management · 08.05.2026 · 02 (05) · 1-9
DOI: 10.55041/ijcope.v2i5.277 ↗Kurz gefasst
Fachartikel in der Zeitschrift International Journal of Creative and Open Research in Engineering and Management, online erschienen am 08.05.2026. Verfasst von Ashok D. und 1 weiteren Autor:innen.
Abstract (Originalsprache)
With the tremendous growth of the Internet of Things, the demand for intelligent security systems that can effectively detect anomalous network behaviour in real time has risen rapidly. Most traditional methods fail in detecting anomalies in the high-dimensional, dynamic, real-time IoT network traffic. In this paper, we investigate a system for automatically detecting anomalies in the IoT networks by using deep learning and machine learning approaches to develop an Autoencoder based anomaly detection framework. For evaluating the proposed system we generate a synthetic IoT network traffic dataset with several network relevant features (such as packet size, byte count, packet type, connection information, etc.). After preparing the data with normalization and scaling, we used Autoencoder, Random Forest and Isolation Forest models to detect the network anomalies and evaluated our system using accuracy, precision, recall, F1-score and AUC
Zitieren
APA
D., A., & Shine, S. (2026). Autoencoder Based Anomaly Detection in IOT Networks. International Journal of Creative and Open Research in Engineering and Management, 02(05), 1-9. https://doi.org/10.55041/ijcope.v2i5.277
Vancouver
D. A, Shine S. Autoencoder Based Anomaly Detection in IOT Networks. International Journal of Creative and Open Research in Engineering and Management. 2026;02(05):1-9. doi:10.55041/ijcope.v2i5.277
BibTeX
@article{D2026,
author = {D., Ashok and Shine, Sharon},
title = {Autoencoder Based Anomaly Detection in IOT Networks},
journal = {International Journal of Creative and Open Research in Engineering and Management},
year = {2026},
volume = {02},
number = {05},
pages = {1--9},
doi = {10.55041/ijcope.v2i5.277}
}
EUVIMED