Real-Time Network Traffic Analysis and Anomaly Detection to Enhance Network Security and Performance: Machine Learning Approaches

https://doi.org/10.55529/jecnam.44.32.44

Authors

  • Anil Kumar Jakkani Research Consultant, the Brilliant Research Foundation Pvt. Ltd., Hyderabad, India.

Keywords:

Network, Traffic Analysis, Anomaly Detection, Network Security, Machine Learning.

Abstract

There are numerous proceedings that take place within an actual computer network, and one of them is the monitoring of the network traffic in real-time with the added function of anomaly detection. This research focuses on the use of machine learning to improve these capabilities as stated in the following section. In the context of the current study, the emphasis is made of building powerful anomaly detection models that would be capable to work in real life by defining network and potential threats on their own due to their machine learning capabilities. Furthermore, the study gives a detailed analysis of the more complex methods like feature selection in addition to dimensionality reduction for enhancing the abilities of machine learning algorithms in the management of big data samples for world-wide network traffic. Furthermore, the presented research focuses on the application of definitions of edge computing paradigms to facilitate decentralized processes of the identification of anomalies, thereby enhancing the sensitivity and response time of essential networks. Thus, the research objectives are to address the aforelisted challenges and generate insights into constructing better network security frameworks to prevent and respond to future threats in a precise and effective mechanism.

Published

2024-07-29

How to Cite

Anil Kumar Jakkani. (2024). Real-Time Network Traffic Analysis and Anomaly Detection to Enhance Network Security and Performance: Machine Learning Approaches. Journal of Electronics, Computer Networking and Applied Mathematics , 4(4), 32–44. https://doi.org/10.55529/jecnam.44.32.44

Similar Articles

1 2 3 4 > >> 

You may also start an advanced similarity search for this article.