Analysis of Computer Network User's Activities Using Support Vector Machine (svm) and Long Short-Term Memory (lstm) Network

Abstract

The rapid growth of number of network users have led to a significant rise in network traffic. Analysing user activities within computer networks is essential for optimizing performance, enhancing security, and improving user experience. This study explores the application of machine learning techniques, specifically Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) networks, to analyse computer network user activities. SVM is employed for its effectiveness in binary classification tasks and its ability to handle high-dimensional data, making it suitable for identifying distinct user activities based on network traffic patterns. Conversely, LSTM networks was utilized to capture temporal dependencies in sequential data, allowing for the prediction of future user actions based on their historical activities. The precision, recall, FI-score and accuracy results for SVM model for analysing computer network user’s activities are 96.00, 99.00, 98.00 and 95.40 respectively. While the precision, recall, FI-score and accuracy results for LSTM model for analysing computer network user’s activities are 90.00, 91.00, 91.21 and 93.50 respectively. Trailing to this, the SVM has a better performance than the LSTM model. Therefore, this research contributes to the field of network analytics by offering insights that will improve network management strategies, resource allocation, and security measures.