Paper Key : IRJ************830
Author: Sahil Sachin Pawar,Deepali Gobare,Ravi Tarate,Ankita Patil
Date Published: 02 Apr 2024
Abstract
Network traffic analysis plays a pivotal role in maintaining the security and efficiency of modern computer networks. With the increasing complexity and volume of network data, robust and accurate methods are required for traffic classification and anomaly detection. In this paper, we propose a novel approach for network traffic analysis utilizing the Random Forest algorithm. Random Forest is an ensemble learning method capable of handling high-dimensional data, making it an ideal choice for analyzing network traffic patterns. Our research involves the collection of network traffic data, feature extraction, and the application of the Random Forest algorithm to classify network traffic into various categories, such as normal, malicious, or specific application types. We explore the effectiveness of Random Forest in discerning complex patterns within network data, and we compare its performance with other machine learning and deep learning techniques. Our results show that the Random Forest algorithm provides high accuracy and reliability in network traffic analysis, with the added benefit of interpretability .Furthermore, we discuss the practical implications of our approach for network security and management, including real-time anomaly detection and network optimization. The proposed method can contribute significantly to enhancing the robustness and security of computer networks in various domains, from enterprise networks to critical infrastructure systems .
DOI Requested