Izvorni znanstveni članak
https://doi.org/10.62598/JVA.11.1.5.16
Analysis of computer network user’s activities using support vector machine (svm) and long short-term memory (lstm) network
Olajide Blessing Olajide
orcid.org/0000-0002-6498-2475
; Department of Computer Engineering, Federal University Wukari,Wukari, Nigeria
Adetoyese Elijah Adeogun
orcid.org/0009-0006-9054-8468
; Department of Computer Science, Ladoke Akintola University of Technology, Ogbomoso, Nigeria
Temitope Omotayo Olayinka
; Department of Electrical and Computer Engineering, University of Maine, Orono, United State
Emmanuel Balogun
; ICT Unit, Ajayi Crowther University, Oyo, Nigeria
Raphael Ibukun Areola
; Department of Electrical Power Engineering, Durban University of Technology
Mutiu Bolarinwa Falade
; epartment of Computer Engineering, Federal University Wukari,Wukari, Nigeria
Ogunniyi Olufunke Kemi
; epartment of Computer Science, Ladoke Akintola University of Technology, Ogbomoso, Nigeria
Sažetak
The rapid growth of number of network users have led to a signifi cant rise in network traffi c. 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, specifi cally
Support Vector Machine (SVM) and Long Short-Term Memory (LSTM) networks, to analyse computer network
user activities. SVM is employed for its eff ectiveness in binary classifi cation 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, FIscore
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 fi eld of
network analytics by off ering insights that will improve network management strategies, resource allocation,
and security measures.
Ključne riječi
network; user; activities; SVM; LSTM; management
Hrčak ID:
333166
URI
Datum izdavanja:
30.6.2025.
Posjeta: 0 *