DEVELOPMENT OF A MACHINE LEARNING BASED FAULT DETECTION MODEL FOR RECEIVED SIGNAL LEVEL IN TELECOMMUNICATION ENTERPRISE INFRASTRUCTURE

Aug 5, 2026

Upload by Violet

The dissertation develops a machine learning based fault detection model targeted at received signal level within telecommunication enterprise infrastructure. It establishes the study background and clearly states the research problem, aiming to define scope, justification, and motivation. The work reviews fault analysis and maintenance strategies used in telecom networks, then surveys machine learning methods suitable for signal strength prediction, including tree based models and classical classifiers. A structured framework guides model selection and evaluation for practical reliability improvement.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages15

Reading Time38 min

AccessFree to download

Acceptance

Declaration

Certification

Dedication

Acknowledgments

Abstract

Chapter One: Introduction

Background to the Study

Statement of the Problem

Aim and Objectives

Scope of Study

Justification of the Research

Motivation for the Research

Organization of the Dissertation

Chapter Two: Literature Review

Preamble

Fault Analysis in a Telecommunications Network

Maintenance Strategies

Reactive Maintenance

Preventive Maintenance

Total Productive Maintenance (TPM)

Reliability Centered Maintenance (RCM)

Predictive Maintenance

Machine Learning

Machine Learning Model for Signal Strength Prediction

Overview of Machine Learning Techniques

Extreme Gradient Boosted Trees (XGBoost)

Logistic Regression (LR)

Support Vector Machine

Decision Tree (DT)

Random Forest

Naïve Bayes’ Theorem

K-Nearest Neighbor (K-NN)

Artificial Neural Networks (ANNs)

Frameworks for Building Machine Learning Systems

DEVELOPMENT OF A MACHINE LEARNING BASED FAULT DETECTION MODEL FOR RECEIVED SIGNAL LEVEL IN TELECOMMUNICATION ENTERPRISE INFRASTRUCTURE NWOKOLO, OZULONYE INNOCENT (20PCK02095) APRIL 2023 DEVELOPMENT OF A MACHINE LEARNING BASED FAULT DETECTION MODEL FOR RECEIVED SIGNAL LEVEL IN TELECOMMUNICATION ENTERPRISE INFRASTRUCTURE BY NWOKOLO, INNOCENT OZULONYE (20PCK02095) B.Eng. Electrical and Electronics Engineering, Bells University of Technology, Ogun State. A DISSERTATION SUBMITTED TO THE SCHOOL OF POSTGRADUATE STUDIES IN PARTIAL FULFILLMENT OF THE REQUIREMENTS FOR THE AWARD OF MASTER OF ENGINEERING (M.Eng.) DEGREE IN INFORMATION AND COMMUNICATION ENGINEERING IN THE DEPARTMENT OF ELECTRICAL AND INFORMATION ENGINEERING, COLLEGE OF ENGINEERING, COVENANT UNIVERSITY, OTA, OGUN STATE APRIL 2023 ACCEPTANCE This is to attest that this dissertation has been accepted in partial fulfilment of the requirements for the award of the degree of Master of Engineering in Information and Communication Engineering in the Department of Electrical and Information Engineering, College of Engineering, Covenant University, Ota, Nigeria. Miss Adefunke F. Oyinloye (Secretary, School of Postgraduate Studies) Signature and Date Prof. Akan B. Williams (Dean, School of Postgraduate Studies) Signature and Date DECLARATION I, NWOKOLO, INNOCENT OZULONYE (20PCK02095) declare that this dissertation is a representation of my work and is written and implemented by me under the supervision of Dr. Kennedy O. Okokpujie of the Department of Electrical and Information Engineering, Covenant University, Ota, Nigeria. I attest that this dissertation has in no way been submitted either wholly or partially to any other university or institution of higher learning for the award of a masters’ degree. All information cited from published and unpublished literature has been duly referenced. NWOKOLO, INNOCENT OZULONYE Signature and Date CERTIFICATION This is to certify that the research work “DEVELOPMENT OF A MACHINE LEARNING BASED FAULT DETECTION MODEL FOR RECEIVED SIGNAL LEVEL IN TELECOMMUNICATION ENTERPRISE INFRASTRUCTURE” is an original research work carried out by NWOKOLO, INNOCENT OZULONYE (20PCK02095) , meets the requirements and regulations governing the award of Master of Engineering (M.Eng.) degree in Information and Communication Engineering from the Department of Electrical and Information Engineering, College of Engineering, Covenant University, Ota, and is approved for its contribution to knowledge and literary presentation. Dr. Kennedy O. Okokpujie (Supervisor) Signature and Date Prof. Emmanuel Adetiba (Head of Department) Signature and Date Dr. Oluwunmi Adetan (External Examiner) Signature and Date Prof. Akan B. Williams (Dean, School of Postgraduate Studies) Signature and Date DEDICATION I dedicate this dissertation to God almighty for giving me knowledge and understanding throughout this research. His grace was sufficiently available for me. ACKNOWLEDGMENTS My heartfelt appreciation goes to the Almighty God for his immeasurable Grace and strength to begin and complete this program. I would also like to thank the Chancellor of Covenant University, Dr. David Oyedepo for this great vision. Thank you, Sir, for the supportive structures and enabling environment, and I pray that God replenishes you with His abundance. I also want to extend my appreciation to the Vice Chancellor, Prof. Abiodun H., Adebayo, the Dean School of Postgraduate Studies, Prof. Akan B. Williams, the Dean College of Engineering, Professor David O. Olukanni, the Head of the Department Electrical and Information Engineering, Prof. Emmanuel Adetiba and all my course lecturers. In addition, I would like to express my sincere gratitude to my supervisor, Dr. Kennedy O. Okokpujie, for the knowledge, time and efforts he provided throughout the course of this project. His useful advice and suggestions were really helpful. May God bless

FAQs

What problem does the dissertation address?

The dissertation addresses faults in telecommunication enterprise infrastructure by focusing on received signal level and aiming to enable effective fault detection using machine learning.

Which maintenance strategies are reviewed?

It reviews reactive maintenance, preventive maintenance, Total Productive Maintenance (TPM), reliability centered maintenance (RCM), and predictive maintenance.

What machine learning methods are discussed for signal strength related tasks?

The literature review covers models and techniques including Extreme Gradient Boosted Trees (XGBoost), Logistic Regression (LR), Support Vector Machine, Decision Tree, Random Forest, Naïve Bayes, K-Nearest Neighbor, and Artificial Neural Networks (ANNs).

Aug 5, 2026

Upload by Violet