NETWORK TRAFFIC ANALYSIS USING MACHINE LEARNING

Abstract

In the field of networking, it is often necessary to identify the sorts of applications that traverse a 
network in order to complete certain tasks. Classification of network traffic is primarily used by Internet 
service providers (ISPs) to examine the characteristics necessary for network architecture, which 
impacts the network's overall performance. There are several classification methods for network 
protocols, such as port-based, payload-based, and Machine Learning-based, and each has its own 
advantages and disadvantages. Due to its widespread use in different domains and academics' rising 
awareness of its superior accuracy when compared to others, the Machine Learning approach is now 
prominent. In this research, we examine the performance of two fundamental algorithms, Nave Bayes 
and K nearest, when applied to networking data retrieved from live video stream using the Wireshark 
program. Python's sklearn library is used to implement the Machine Learning algorithm, together with 
the numpy and pandas libraries as assistance libraries. Finally, we see that the K closest approach 
provides more precise predictions than the Naive Bayes, Decision Tree, and Support Vector Machine 
algorithms.