Enhancing Network Security Using Machine Learning Model-Agnostic Approach on Diverse Datasets - Configuration Manual

Sep 17, 2026

Uploaded by Theodora

Configuration manual for an MSc Data Analytics 2024 research project on network security using a mode-agnostic machine learning approach applied to multiple network traffic classification and intrusion datasets. The project addresses class imbalance, feature importance, and hyperparameter tuning to identify an environment that improves model accuracy and efficiency. The document also supports reproducibility by specifying system setup, hardware and software requirements, dataset sources used in the study, and required Python library versions to run the accompanying notebooks consistently. It further outlines system aims to guide deployment in real-life intrusion detection systems and firewalls.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages24

Reading Time1 h 0 min

AccessFree to download

1 Introduction

2 System Requirements

2.1 Hardware requirements

2.2 Software Requirements

3 Dataset Collection

4 Project Development

Enhancing Network Security Using Machine Learning Model-Agnostic Approach on Diverse Datasets Configuration Manual MSc Research Project Data Analytics Muhammad Zaeem Student ID: x23108088 School of Computing National College of Ireland Supervisor: Arjun Chikkankod National College of Ireland MSc Project Submission Sheet School of Computing Muhammad Zaeem Student Name: X23108088 Student ID: ……………………………………………………………………………………………………………..…… MSc Data Analytics 2024 Programme: ……………………………………………………………… Year: ………………………….. MSc Research Project Module: Arjun Chikkankod Lecturer: Submission 12th August, 2024 Due Date: Enhancing Network Security Using Machine Learning Model-Agnostic Project Title: Approach on Diverse Datasets ………………………………………………………………………………………………………….……… 2500+ 22 Word Count: ……………………………………… Page Count: ………………………………….…….……… I hereby certify that the information contained in this (my submission) is information pertaining to research I conducted for this project. All information other than my own contribution will be fully referenced and listed in the relevant bibliography section at the rear of the project. ALL internet material must be referenced in the bibliography section. Students are required to use the Referencing Standard specified in the report template. To use other author's written or electronic work is illegal (plagiarism) and may result in disciplinary action. Muhammad Zaeem Signature: 12th August, 2024 Date: PLEASE READ THE FOLLOWING INSTRUCTIONS AND CHECKLIST | Attach a completed copy of this sheet to each project (including multiple copies) | □ | | --- | --- | | Attach a Moodle submission receipt of the online project submission, to each project (including multiple copies) . | □ | | You must ensure that you retain a HARD COPY of the project, both for your own reference and in case a project is lost or mislaid. It is not sufficient to keep a copy on computer. | □ | Assignments that are submitted to the Programme Coordinator Office must be placed into the assignment box located outside the office. | Office Use Only | | | --- | --- | | Signature: | | | Date: | | | Penalty Applied (if applicable): | | Enhancing Network Security Using Machine Learning Model-Agnostic Approach on Diverse Datasets Muhammad Zaeem X23108088 1 Introduction It is a mode-agnostic project for the in-depth analysis of different network traffic classifications and intrusion datasets to address challenges like class imbalance, feature importance, and hyperparameter tuning aiming to find the best-performing environment for model to improve their accuracy and efficiency. Another goal is to find an inference model that can be suggested to be implemented in real-life intrusion detection systems and firewalls to enhance network security. This configuration manual is designed to provide all the details that can help anyone recreate this research. 2 System Requirements For the efficient execution of this research artefact, the following hardware and software requirements should be considered beforehand 2.1 Hardware requirements Table 1. shows the needed hardware requirements to run the code artefact | Operating System (OS) | Windows 10 or similar OS | | --- | --- | | Processor | Intel i5 8th Gen or above | | RAM | 16 GB DDR4 | | Storage | 50 GB available space | Table 1: Hardware Specifications 2.2 Software Requirements Microsoft Excel is used for the early exploration of datasets. For the implementation of the project, the Jupyter Notebook IDE from Anaconda Environment is used which has Python kernel preinstalled in it. • Python Kernel version: 3.11.4 • Jupyter Notebook version: 7.0.0 3 Dataset Collection Three datasets are used in this research. The first one is the network traffic classification dataset taken from the UCI Machine Learning repository 1 named as Internet Firewall Dataset. The second Dataset is the UNSW NB15 datas

FAQs

What is the main aim of the project described in this configuration manual?

To perform an in-depth, mode-agnostic analysis of network traffic classification and intrusion datasets, improving model accuracy and efficiency while addressing class imbalance, feature importance, and hyperparameter tuning.

Which datasets are used in the research?

Internet Firewall Dataset (UCI), UNSW NB15 (Kaggle), and NF-UQ-NIDS-v2 (Kaggle, created by combining small datasets).

What hardware and software requirements are specified for running the project artefact?

Hardware includes Windows 10 or similar OS, Intel i5 8th Gen or above, 16 GB DDR4 RAM, and 50 GB available storage. Software setup uses Microsoft Excel for early exploration and Jupyter Notebook in an Anaconda environment with Python kernel and specific package versions.

Sep 17, 2026

Uploaded by Theodora