Real-Time Anomaly Detection in Big Data Pipelines Using Deep Learning Techniques

Authors

  • Ivan Petrov Department of Artificial Intelligence, Sofia University "St. Kliment Ohridski", Bulgaria

Abstract

As big data continues to expand across various industries, detecting anomalies in real time within data pipelines has become critical for ensuring the integrity, security, and operational efficiency of modern systems. This paper explores how deep learning techniques can be leveraged for real-time anomaly detection in big data environments. We investigate different deep learning architectures, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), and Autoencoders, that have shown promise in detecting anomalies across various industries. Furthermore, we evaluate the challenges of real-time anomaly detection in big data pipelines, such as scalability, performance, and adaptability, and propose solutions using deep learning models.

Downloads

Published

2023-06-13

How to Cite

Petrov, I. (2023). Real-Time Anomaly Detection in Big Data Pipelines Using Deep Learning Techniques. MZ Computing Journal, 4(1). Retrieved from http://mzresearch.com/index.php/MZCJ/article/view/302