A Hybrid System for Network Traffic Forecast Using Firefly and Cortical Learning Algorithm

Network traffic forecast is a critical aspect of network management and cybersecurity, encompassing the prediction and analysis of data transmission patterns within computer networks. As the volume and complexity of network traffic continue to increase exponentially, accurate forecasting becomes indispensable for ensuring efficient resource allocation, optimizing network performance, and detecting potential security threats. Object Oriented Analysis and Design (OOAD) was adopted as the research methodology, and python was used as the programming language. An experiment was conducted to detect malicious traffic on network systems using a hybrid approach of firefly algorithm and cortical learning, encompassing two phases: Exploratory Data Analysis (EDA) and training of the Random Forest Classifier. In the EDA phase, techniques were employed to address dataset imbalance in the NSL-KDD dataset through random oversampling, alongside identifying the ten most important features using Isolation Forest. During the model training phase, parameters were initialized for both algorithms, leading to iterative optimization to achieve an optimal balance between exploration and exploitation crucial for capturing complex network traffic patterns. Evaluation of the model's outcomes, including training and testing results, was conducted using classification reports and confusion matrices. The model showcased promising results, achieving an accuracy of 99.9% in detecting malicious network traffic, and significantly outperformed existing systems, demonstrating the efficacy of the hybrid approach in network intrusion detection. This study underscores the effectiveness of the hybrid approach, offering superior performance compared to traditional methods.

Authors

Institutions

Publication Details

Journal
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Published
2026-11-13
DOI
https://doi.org/10.56201/ijcsmt.v10.no3.2024.pg105.120
Primary Topic
Network Security and Intrusion Detection
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

A Hybrid System for Network Traffic Forecast Using Firefly and Cortical Learning Algorithm

K. C. Eme
2 links
INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Network Security and Intrusion Detection
article

A Hybrid System for Network Traffic Forecast Using Firefly and Cortical Learning Algorithm

K. C. Eme
article en

Abstract

Network traffic forecast is a critical aspect of network management and cybersecurity, encompassing the prediction and analysis of data transmission patterns within computer networks. As the volume and complexity of network traffic continue to increase exponentially, accurate forecasting becomes indispensable for ensuring efficient resource allocation, optimizing network performance, and detecting potential security threats. Object Oriented Analysis and Design (OOAD) was adopted as the research methodology, and python was used as the programming language. An experiment was conducted to detect malicious traffic on network systems using a hybrid approach of firefly algorithm and cortical learning, encompassing two phases: Exploratory Data Analysis (EDA) and training of the Random Forest Classifier. In the EDA phase, techniques were employed to address dataset imbalance in the NSL-KDD dataset through random oversampling, alongside identifying the ten most important features using Isolation Forest. During the model training phase, parameters were initialized for both algorithms, leading to iterative optimization to achieve an optimal balance between exploration and exploitation crucial for capturing complex network traffic patterns. Evaluation of the model's outcomes, including training and testing results, was conducted using classification reports and confusion matrices. The model showcased promising results, achieving an accuracy of 99.9% in detecting malicious network traffic, and significantly outperformed existing systems, demonstrating the efficacy of the hybrid approach in network intrusion detection. This study underscores the effectiveness of the hybrid approach, offering superior performance compared to traditional methods.

INTERNATIONAL JOURNAL OF COMPUTER SCIENCE AND MATHEMATICAL THEORY E-ISSN
Rivers State University (NG)
Network Security and Intrusion Detection
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon