Network Requests Classification using Advanced Metaheuristic
Optimization for Enhanced Network Security Systems
Marwa M. Eid1,2,*
1Faculty of Artificial Intelligence, Delta University for Science and Technology, Mansoura 11152, Egypt
2Jadara Research Center, Jadara University, Irbid 21110, Jordan
Email: mmm@ieee.org
Abstract
The importance of network security has greatly been enhanced in the modern digital environment that
continuously changes. Network security, on the other hand, is a multi-layered defense mechanism that seeks
to protect networks, data, and systems from malpractices such as unauthorized access breaches or activities.
Cyber threats become ever more advanced, and traditional protective measures can no longer prove to be
adequate. Given the necessity of such a threat to adapt and be intelligent, an active intrusion detection system
must necessarily rapidly evolve its methods in response. The central element contained in this research is
the proposal of a novel algorithm, BBERSC (Balance Between Al Biruni Earth Radius Optimization and
Sine Cosine Algorithm). This algorithm is carefully crafted to achieve a compromise between the means
for local search provided by Al-Biruni Earth Radius Optimization and probabilistic improvement, which are
characteristic of the Swine Cosine Algorithm. BBERSC brings forward the cause of harmonizing these two
optimization methods to revolutionize model accuracy and credibility, which may be achieved for network
security’s distinctiveness. One of the crucial elements of this study lies in the fact that hyperparameter tuning
is quite a detailed process, especially for Random Forest. Parameters, including the number of trees, maximum
depth, and minimum samples, are systematically employed to vary to augment pattern recognition capability
by employing model processing network traffic. To ensure the validation of the effectiveness of the proposed
models and algorithms, statistical analysis is carried out through ANOVA test & Wilcoxon Signed Rank
Test. These tests show the models’ results through rigorous assessments and emphasize differences between
them. As the conclusion of this study, It is displayed that the Random Forest model utilized inside BBERSC
algorithmic framework facilitates operational accuracy level 0.9901719, which is incomparable among all
other machine learning algorithms.
Keywords: Network Requests; Al-Biruni Earth Radius Optimization; Sine Cosine Algorithm; Network
Security; Intrusion Detection