University of Ibadan Journals
Not a member yet
794 research outputs found
Sort by
Comparison of Analytical Hierarchy Process and Fuzzy Analytical Hierarchy Process Models for E- Banking Websites Quality Evaluation
Full text linkThe process of evaluating the quality of e-banking websites has gained rapid attention in recent years with the adoption of multi-criteria decision-making (MCDM) approaches. The Analytical Hierarchy Process (AHP) and the fuzzy AHP models which are well suited to determine the outcomes of the e-banking website quality evaluation are explored in this study. In both cases, the decision-making activity is broken into criteria and sub criteria usually arranged as a pairwise comparison matrix layout. Though the latter is meant to be an advancement over the former, this paper compares the performances of the two MCDM approaches in evaluating e-banking websites of top-four Nigerian banks by profit margin. The data was collected from 33 out of 50 initially selected respondents using e-banking apps in Minna, Niger State through a non-random sampling technique. The outcome showed that the AHP and FAHP models are closely correlated based on the ranking of the weights of criteria and alternatives used in the study. Using the Wilcoxon Signed Rank Test, the Asymp Sig. (2-tailed) of criteria and sub-criteria is 0.500 for AHP and FAHP models indicating highly correlated decisions of the respondents. Also, the Wilcoxon Signed Rank Test (Asymp Sig. (2-tailed)) of alternatives is 1.000 for AHP and FAHP models indicating fairly correlated decisions on e-banking websites quality of alternatives (banks). However, the FAHP performances were superior to the AHP, which is consistent with some existing studies
Software Fault Prediction Using a Language-Proficient Transformer Model: An Enhanced Approach with BugsplorerPy
Full text linkThe pursuit of reliable software defect prediction (SDP) methodologies continues to confront fundamental limitations in addressing the idiosyncrasies of dynamically-typed languages, particularly Python, whose syntactic flexibility and implicit dependencies challenge conventional static analysis paradigms. This work presents BugsplorerPy, an architecturally innovative transformer-based framework that advances the state-of-the-art through three seminal contributions: (1) a syntax-aware hierarchical attention mechanism that dynamically adapts to Python’s indentation-scoped control flow and duck-typed variable semantics, (2) an interprocedural analysis pipeline that models cross-file defect propagation through import graphs and call-chain embeddings, and (3) a parameter-efficient adaptation strategy that maintains the expressivity of foundation models while optimizing for real-world IDE deployment constraints. Empirical validation on the Defectors benchmark—the first curated dataset for Python-specific defect analysis—reveals statistically significant improvements (p<0.01) across all evaluation dimensions: achieving 78.5-81.4% balanced accuracy (? +3.83% over baseline), 0.8620.882 AuROC (? +4.88%), and 72.2-80.1% Recall@20%LOC (? +6.23%), with particular gains in detecting type-system violations (F1 +7.1%) and exception handling flaws (F1 +5.8%). The model’s novel hybrid architecture, which synergizes static program analysis with learned representations, demonstrates 83% precision in identifying defect-prone file clusters—a critical capability for large-scale refactoring efforts. These findings not only validate the necessity of language-specific SDP adaptations but also establish a new methodological paradigm for balancing interpretability (through attention-based defect attribution) with the representational power of modern transformer networks in software engineering contexts
Public Servant Service Watch System: Leveraging Artificial Intelligence, Machine Learning, and Big Data Analytics to Combat Corruption in Nigeria
Full text linkPublic sector fraud continues to undermine governance and development efforts in Nigeria. Despite ongoing anti-corruption campaigns, existing detection mechanisms remain manual, reactive, and insufficiently equipped to flag complex financial irregularities in real time. A critical research gap exists in the integration of automated, data-driven approaches to proactively detect fraud among public officials. This study seeks to bridge that gap by developing and evaluating a machine learning–based system tailored for detecting suspicious financial behaviours using asset declarations and transaction records. The work employed two datasets: a synthetically generated dataset created with Python’s Faker library and publicly available financial transaction data from Kaggle. These were harmonized using unique identifiers, cleaned, and pre-processed to support analysis. Exploratory Data Analysis (EDA) helped uncover patterns relevant to fraud detection, such as transaction spikes and discrepancies between income and declared assets. A Random Forest classifier was chosen for its balance of predictive performance and interpretability. The model was trained and deployed using Microsoft Azure to enable scalable, real-time processing. Results indicate that the Public Servant Service Watch system effectively identifies anomalies such as sudden asset accumulation and undeclared financial interests. The Random Forest model achieved high scores across accuracy, precision, recall, and AUC-ROC metrics. This study demonstrates the feasibility and impact of applying machine learning within a cloud-based infrastructure to improve transparency, accountability, and fraud prevention in the Nigerian public sector
Augmented Reality Navigation Assistance System for Visually Impaired Individuals
Full text linkVisually impaired people face a lot of issues navigating and moving around their environment, mostly depending on their mobility cane, memory, and familiarity with the environment to navigate. Technologies designed for them are usually expensive, hard to get, or uncomfortable. This research presents the design, implementation and evaluation of an Augmented Reality (AR)-based indoor navigation system for visually impaired individuals, compatible with Android and iOS devices. Using an Agile methodology, we conducted interviews, gave out questionnaires, and made observations with a number of visually impaired individuals in order to establish user requirements and refine the scope of the project. The system was implemented using the AR library, Niantic Lightship ARDK with real time meshing and semantic segmentation features, the Unity 3D engine, and the C# programming language. The AR navigation tool digitally maps the environment, detecting obstacles and filtering out the ground. When an obstacle is detected within one meter, the system provides haptic and auditory feedback, alerting the user until they move away. Usability testing was conducted with 18 visually impaired participants through questionnaires, interviews, and observations. The system’s usability was assessed using the John Brooke System Usability Scale (SUS), achieving a score of 81.39, classified as “Best Imaginable.” This research contributes to the field of AR-based assistive technologies
Application of Machine Learning Algorithms in Predicting the Toxicity of Chemical Compounds for Safer Pharmaceuticals
Full text linkThe development of safe pharmaceuticals requires accurate and efficient prediction of chemical toxicity to minimize adverse health risks and reduce reliance on costly and ethically challenging animal testing. This study investigates the application of three machine learning (ML) algorithms—Random Forest (RF), Support Vector Machine (SVM), and Linear Regression (LR)—for predicting the toxicity of aromatic chemical compounds. A dataset of 11,001 compounds was curated, preprocessed, and analyzed using molecular descriptors such as molecular weight, lipophilicity, and polar surface area. Model performance was evaluated using accuracy, precision, recall, F1-score, and specificity. Results showed that the Linear Regression model performed poorly, with accuracy around 52%, indicating limited suitability for toxicity classification. The SVM model achieved substantially better results, with an accuracy of 80%, demonstrating its effectiveness in capturing nonlinear structure–toxicity relationships. Notably, the Random Forest model outperformed both, achieving perfect classification accuracy (100%) across all metrics, with zero false positives and false negatives. Feature importance analysis revealed that descriptors such as Topological Polar Surface Area and Molecular Fractional Polar Surface Area were key contributors to toxicity prediction. The findings demonstrate that Random Forest is a robust and interpretable tool for early toxicity screening, offering both predictive accuracy and insight into molecular features driving toxicity. By integrating ML models into pharmaceutical research pipelines, drug discovery can be accelerated, costs reduced, and ethical imperatives met by minimizing animal testing. Future work should focus on external validation, hybrid model development, and explainable AI techniques to enhance generalizability and regulatory acceptance
Particle Swarm Optimization-Random Forest Weather-Based Crop Yield Prediction Model
Full text linkCrop production is a vital source of food for humans, and improving crop yield requires a deep understanding of crop production processes. It has been proven that increasing crop yield reduces poverty, crop failure risk, increases productivity, and optimizes the value of agricultural land. Many factors affect the amount of crop harvested in a specific area and several studies, mainly in the agricultural context, have been conducted to estimate crop yield production with Machine learning (ML) techniques. This study explores five cereal crop yields: rice, maize, wheat, sorghum, and soybeans with Particle Swarm Optimization (PSO) and Random Forest prediction approaches. Performance metrics such as R2 score, Mean Absolute Error, and Root Mean Squared Error confirm the authenticity of the model. The result of the optimized Crop yield prediction has an R2 score of 97.13, MAE of 124.75, and RMSE of 1273.73. The model performed better than other existing approaches, such as Random Forest (RF) and Decision Tree (DT). This study will provide farmers with reliable crop yield predictions, enabling better planning based on weather conditions
Pipeline Leakage Detection and Monitoring Model using Enhanced Multiple Signal Classification Algorithm and Hybrid Acoustic Emission Techniques
Full text linkThe consequences of pipeline leakages pose great multifaceted hazards, including carcinogenicity and cytotoxicity in humans exposed to leaked toxic substance from pipelines. Pipeline leak also causes environmental contamination of soil resulting to environmental pollution, fire disaster and even loss of life. Therefore, pipeline leakage detection monitoring is a crucial concern in pipeline industry for ensuring the safe and efficient operations. Background noise and detection of single leak are significant limitations of the existing pipeline monitoring and leakage detection techniques. These undesired noises can arise from multiple sources, including environmental, proximity industries, pipe vibration, and electronic interferences. This study therefore optimizes the conventional Multiple Signal Classification (MUSIC) algorithm and Acoustic Emission (AE) technique with the aim to develop a novel technique to address the effect of the background noise. The proposed method combines the advantages of the MUSIC algorithm and AE techniques with real-time monitoring to promptly and accurately detect leakages in pipeline systems. The model achieved Accuracy of 95.5%, Sensitivity of 75%, Mean Detection Time of 1.02 seconds and Response Time of 1.06 seconds. These quantitative results demonstrate the effectiveness of our proposed Enhanced MUSIC algorithm and Hybrid AE technique (Enhanced-MUSICHAE) to detect and monitor pipeline leakage. This has the potential to improve pipeline safety, reduce economic losses, and minimize environmental damages
Prediction of Loan Defaulters Using Machine Learning
Full text linkFinancial institutions face significant challenges in accurately assessing the risk of loan defaults, which can lead to substantial financial losses and impact overall stability. The primary objective of this study is to develop predictive models that accurately identify potential loan defaulters, enabling lenders to make more informed lending decisions. The study addresses the critical need for more reliable and data-driven credit risk assessment tools by employing logistic regression, random forest, and decision tree algorithms. The research design involves a systematic approach to data collection, preprocessing, feature selection, model development, and evaluation. The dataset, sourced from Coursera's Loan Default Prediction Challenge, includes 255,347 instances and 18 features relevant to loan default prediction. The study employed an under sampling technique to address class imbalance and used train-test split to evaluate model performance. Logistic regression, random forest, and decision tree models were trained and assessed for their predictive capabilities. The results indicate that Logistic regression and random forest models demonstrated superior performance, with accuracy rates of approximately 69% and 68%, respectively. The feature importance analysis revealed key factors influencing loan defaults, such as credit score, loan amount, and employment history
Effects of Incessant Electric Power Outages on Physical Development in Akure, Nigeria
Full text linkElectricity is a necessity in modern life, on which human work, healthcare, leisure, economy, and livelihood depend. Hence, incessant electric power outages can lead to relative chaos, financial setbacks, and loss of life. This paper examines the effect of incessant electric power outages on the physical development and livelihood of residents in Akure, Nigeria, with a view to improving the reliability and accessibility of electricity supply in the region. The study annexed both primary and secondary sources of data gathering. The primary data were retrieved directly from residents within the metropolis of Akure while the secondary data were retrieved from related organizations in charge of power generation and distribution to the study area such as National Bureau of Statistics (NBS), Energy Commission of Nigeria (ECN), Benin Electricity Distribution Company of Nigeria (BEDC), and the Nigerian Electricity Regulatory Commission (NERC) among others. The study area was categorized into core, periphery, and suburban areas. Systematic Random sampling was used to administer the questionnaire to sampled residents in the selected communities across the three zones. The data obtained were analyzed using SPSS, and the results of the findings revealed that incessant power supply has significant effects on the construction and completion of amenities within the area. It was also affirmed that frequent electric power outages in the area negatively impacted the operation of local businesses and industries, thereby affecting the overall economic growth. This has discouraged new investments, development projects, as well as the quality of life and standard of living of residents in the study area. The study concluded to affirm that these impacts created a challenging environment for physical development, which has possibly trapped the area in a low-development equilibrium. Therefore, infrastructure modernization, capacity enhancement, and implementation of a robust maintenance programme were recommended as strategies towards the improvement of power supply within the metropolis
Toxicological Influence of Aqueous Tephrosia bracteolata Leaf Extract on Haematological and Biochemical Parameters in Clarias gariepinus Juveniles
No full textFish farmers traditionally explore plants to catch fish from the wild without knowing theexact dose that would not pose a threat to the fish. The study investigated impacts ofvaried concentrations (8.00, 4.00, 2.00 and 1.00ml/L and 0.00 (the control) in replicates,using completely randomized design (CRD) and injection method, for a duration of 96hrs)of aqueous leaf extract of Tephrosia bracteolata impacts on haematology, blood serumbiochemistry and mortality rate of Clarias gariepinus using 200 juveniles. The data wereanalysed for mean, standard deviation, and Pearson’s correlation using IBM SPSS version23. Results indicated determination of Alkaloids 52%, Saponin 31%, Flavonoids 29%,Phenol 27%, Glucosides 18% and anthraquinone 12%; and the treatments’ LD50 was 2mL (log concentration of 0.301). Unlike in control, levels of the PCV, Hb, RBC, andWBC decreased as the treatments increased, with a strong and direct correlation amongthe four haematological indices; the glucose levels increased while cholesterol and proteindecreased as the treatments increased, with the glucose levels having a very strong butindirect correlation with protein and cholesterol levels. The protein level was stronglycorrelated (r = 0.922, p < 0.01) with cholesterol. The study concluded that the plantinduced dose-dependent physiological stress on the experimental fish. There was no furtherobservation post-treatment, and cautious usage of the plant around the fish habitat and forfish harvesting by the fish artisans is recommended