University of Abuja Institutional Repository
Welcome to University of Abuja institutional repository for research material including: journal articles, conference papers, practice research, video, audio, art works and exhibitions, books and book chapters, doctoral theses and datasets. The repository provides full text access where permitted, and full citation details where restrictions apply. Please contact the Research Support Team (repository@uniabuja.edu.ng) with any related queries.
Recent Submissions
Item type:Item, NEURAL NETWORK-BASED EARLY LIGHTNING STRIKE PREDICTION FOR DISTRIBUTION INFRASTRUCTURE RESILIENCE ENHANCEMENT(UNIABUJA, 2026) ALLI AHMED JIMOHLightning-induced outages are a persistent threat to the resilience and reliability of power distribution networks, especially during convective weather seasons. This study presents a neural network-based early lightning detection framework aimed at enhancing distribution network resilience by integrating advanced deep learning and power system simulation. Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) architectures were optimized through hyperparameter tuning (grid search, Bayesian optimization) and evaluated using precision, recall and F1-scores. Results demonstrated the LSTM model’s superior performance, achieving 91% accuracy and 83% recall for lightning events, outperforming the CNN model (81% accuracy, 63% recall). While both models identified wet-season peaks (April–October) and afternoon maxima (15:00–20:00), the CNN exhibited anomalous dry-season predictions, highlighting its limitations in capturing long-term climatological trends. The LSTM’s robust handling of temporal dependencies yielded a realistic 365-day forecast for 2024, aligning with historical seasonality. The optimized LSTM model’s predictions are subsequently validated and fed into a MATLAB-based distribution network simulation environment. Where, predicted lightning events triggered adaptive operational strategies, such as dynamic relay setting adjustments and preemptive sectionalizing, informed by predicted lightning occurrence data. Simulation results demonstrated that integrating early lightning prediction reduces unnecessary breaker operations and power outages, with quantifiable improvements in key reliability indices such as System Average Interruption Frequency Index (SAIFI), System Average Interruption Duration Index (SAIDI) and Customer Average Interruption Duration Index (CAIDI). SAIFI improved from 1.82 to 0.92 (49% improvement), SAIDI improved from 3.5 to 1.15 (65% improvement), CAIDI improved from 1.92 to 1.25 (35% improvement). This also led to faster restoration times compared to conventional reactive approaches to lightning disturbances. This study underscores the value of combining deep learning, historical data, and power system simulation for modern grid resilience, and provides a scalable blueprint for utilities seeking to minimize weather-related disruptions through predictive analytics.Item type:Item, AUDIENCE PERCEPTION OF KAPITAL FM COVERAGE OF THE 2014 EBOLA CRISIS IN NIGERIA(2026) TERSOO PETER ZAMBERDisease epidemics come always as a surprise to human society. These emergencies can be manmade or natural with their proportionate consequences on the socio-economic, political and health needs of society. Ebola outbreak in Nigeria in the year 2014 was one of the most frightening health emergencies in recent times, and as a social problem, there was need to inform Nigerians properly on the dangers associated with the disease and to keep them informed on how to escape the monster (Ebola virus). However, the concern of this study is to evaluate Kapital FM Radio campaign against the Ebola outbreak in Nigeria 2014 as a subsidiary of FRCN. The quantitative approach was adopted in gathering the information used in this study where questionnaires and interviews were designed to obtain information from FCT residents and the data analysed using tables, numbers and percentages. The study adopted the ‘social responsibility and agenda setting’ theories as the conceptual framework. However, it was discovered in the study that radio is a potent medium for information needs for most Nigerians, but the mode or language of communication of the radio, especially in times of emergencies, still poses some challenges. Therefore, the recommendation of this study is that radio in Nigeria should be more creative and committed during emergencies like Ebola, in language choice. If epidemics and other forms of emrgencies are reported in digestible language as this study suggests, such situations might not warrant the overbearing fear and suspicion that usually follow them.Item type:Item, SECTORIAL IMPACT ASSESSMENT OF BUHARINOMICS: A CANONICAL APPROACH(SSRN, 2024-12-25) Amina Mohammed Bashir; Yekeen Abdul-MaliqThis study assesses the impact of the, Buharis microeconomic management policiesand actions on the Nigerian economy from 2015 to 2023:Q2. The study takes asectorial perspective (break-down of GDP rather than aggregated) while canonicalcorrelation analysis is conducted on five independent variables: money supply;(M2), FDI. The dependent variables are, external borrowing, domestic debt and FDIand exchange rate as a moderating sectorial GDP output: agriculture, industry(manufacturing), building & construction, trade and services. Analyses reveal that only the exchange rate (moderating variable); has significant impact on Nigeriasectorial GDP. The impacts are on Industry, 𝛽=-1.8675; P=<.001. Trade, 𝛽=-21.8675; P=<.001, and the Service sector, 𝛽=4.8654; P=.016. As can be gleanedfrom the statistics; only the impact of exchange rate on the services sector is positive;while on Trade and Industry the impacts are negative. The study therefore concludesthat; on an unbiased, non-presumptive but empirically based assessment;buharinomics has no positive growth impact on the Nigerian economy in its eight-year period.Item type:Item, Properties of Semiconductor(2026) Seun, JohnItem type:Item, Introduction to Engineering Physics(2025) Newton, John