EUVIMEDEUVIMED entdecken
Crossref

A Deep Autoencoder-Driven Framework for Intelligent Anomaly Detection in Scalable Cloud-Native Environments

Animesh Pal, Sampa Nandi, Balamurugan M

International Journal of Emerging Technologies and Innovative Research · 27.03.2026 · 227

DOI: 10.48175/ijarsct-32219 ↗

Kurz gefasst

Fachartikel in der Zeitschrift International Journal of Emerging Technologies and Innovative Research, online erschienen am 27.03.2026. Verfasst von Animesh Pal und 2 weiteren Autor:innen. Die Arbeit nennt 27 Literaturangaben.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Data-intensive applications across cloud-native environments have increased the important of robust, scalable, and intelligent data quality management systems. The conventional rule-based data validation techniques are often inadequate for handling dynamic, heterogeneous, and large-scale datasets, particularly in real-time and distributed architectures. This paper introduces a novel deep autoencoder-driven framework for automated data quality detection within scalable cloud-native data engineering architectures. The proposed approach influences deep autoencoders to learn hidden representations of high- quality data and identify anomalies through reconstruction error analysis, enabling adaptive and self-learning data validation. This framework integrates real-time data ingestion, preprocessing, AI-driven anomaly detection, and automated data cleansing using unified pipeline. The cloud-native deployment strategies incorporated within this system to ensure scalability, fault tolerance, and efficient processing of high-volume data streams. A real-time monitoring dashboard is also proposed to provide predictive insights and active data quality management. This proposed system addresses key limitations of existing approaches by enabling continuous data quality assessment in streaming and Zero-ETL environments, reducing dependence of manual rule-based methods, and improving detection accuracy of complex datasets. The proposed model will be evaluated using benchmark and real- world datasets based on performance metrics such as accuracy, precision, recall, scalability, and computational efficiency. This article contributes to develop of next-generation intelligent data engineering systems by combining deep learning, automated data quality management, and scalable cloud architectures, finally ensuring data integrity and reliability for advanced analytics and decision-making applications.

Zitieren

APA

Pal, A., Nandi, S., & M, B. (2026). A Deep Autoencoder-Driven Framework for Intelligent Anomaly Detection in Scalable Cloud-Native Environments. International Journal of Emerging Technologies and Innovative Research, 227. https://doi.org/10.48175/ijarsct-32219

Vancouver

Pal A, Nandi S, M B. A Deep Autoencoder-Driven Framework for Intelligent Anomaly Detection in Scalable Cloud-Native Environments. International Journal of Emerging Technologies and Innovative Research. 2026:227. doi:10.48175/ijarsct-32219

BibTeX
@article{Pal2026,
  author = {Pal, Animesh and Nandi, Sampa and M, Balamurugan},
  title = {A Deep Autoencoder-Driven Framework for Intelligent Anomaly Detection in Scalable Cloud-Native Environments},
  journal = {International Journal of Emerging Technologies and Innovative Research},
  year = {2026},
  pages = {227},
  doi = {10.48175/ijarsct-32219}
}
Kostenlos starten →