Computer Science, Artificial Intelligence, Software, Computer Vision and Pattern Recognition
11
Scopus Publications
26
Scholar Citations
3
Scholar h-index
1
Scholar i10-index
Scopus Publications
Traffic Accident Severity Classification Using ResNet-18 Oni Oluwadamilola, Ogbonnia Emmanuel E3s Web of Conferences, 2026 The paper describes a system of automated classification of the severity of traffic accidents based on a fine-tuned ResNet-18 architecture. To meet the requirement of quick emergency reaction in low-resource urban areas, we pre-selected a dataset of about 50000 images, integrating the CADP and UCF-Crime datasets with rescue images of the area. The images were processed and augmented in order to rectify the imbalance of the classes. Transfer learning was used to train the model using Focal Loss and AdamW optimizer. Testing on a held-out test set shows a total accuracy of 98.54 and a precision of 0.99 on severe incidents and an F1-score of 0.98. The system maximizes the edge deployment, which provides low-latency inference applicable to real-time municipal surveillance. Comparative analysis shows that ResNet-18 offers a superior trade-off between accuracy and computational efficiency compared to deeper architectures..
Landmark-Aware Heterogeneous Graph Framework for Multi-Source Road Crash Data Integration in Nigeria Emmanuel Ogbonnia O, O. A. Ojerinde, E. F. Aminu, Isiaq Olúdáre Alabi, S. A. Adepoju Nipes Journal of Science and Technology Research, 2025 Proper forecasting of road crash in developing nations requires holistic, contextually relevant information that characterises complex spatial-temporal relationships. This paper presents a novel data collection and integration paradigm that was developed to address the most serious gaps in the studies on road safety in Nigeria. Using both Federal Road Safety Corps (FRSC) crash records and OpenStreetMap (OSM) geospatial data, a heterogeneous graph model of 559,622 road nodes and 81,986 amenity nodes in 37 administrative regions is built. The approach uses the Haversine-based proximity calculations and Gaussian radial basis functions to enrich the structure that provides a geocoding success rate of 93.7% and a 100.0% weather data enrichment in 104,672 crash records. The framework also builds landmark aware graph construction, where road infrastructure properties (type, speed limit, surface) are combined with contextual amenities (hospitals, schools, markets) by relation specific edges. Findings indicate high levels of completeness of data (95-100 percent core attributes) and effective implementation in a Neo4j graph system architecture. This paper provides a basis of context-specific Graph Neural Network (GNN) models to match the local infrastructural and traffic peculiarities of developing countries, thus overcoming the constraints of Western-oriented datasets.
Digitisation of the Nigerian Bail Process: A Framework for Interoperable, API-Driven Verification O. A. Ojerinde, E. F. Aminu, A. Ekundayo, M. Nwankwo, A. T. Zakka, et al. Nipes Journal of Science and Technology Research, 2025 The Nigerian bail processing system is complicated and leads to delays in the release of accused persons while awaiting trial. Its widespread pretrial detention and ineffectiveness which contributes to the severe infringement of constitutional rights and the threat of overcrowding prisons. Although the Manual of the Administration of Criminal Justice in Nigeria (ACJA) 2015 provides a sophisticated legal context, the shortcomings of the system are in slowness, tediousness, and finally paper-based procedures regarding the verification of the bail conditions. In this paper, a fully digitalised system has been proposed for the bail system, based on the adoption of interoperable systems and APIs to automate some of the most important bail conditions verification processes, i.e., surety employment, identification, financial capability, and property collateral verification. This proposed system takes the provision of the 2015 ACJA into account. The proposed system opens real-time, crossing, and interlocked API bridges to the NIN, land, tax, and revenue, and financial inter-institutions to overcome the time consuming, error-prone manual processes. In so doing it will greatly decrease the time that is taken to process and make decisions, make the process more transparent, decrease the chances of extortion, and make sure that the decisions made when bailing are based on legally permissible grounds. It also shows in the paper that a gradual, legally based digitisation plan can shift the process of bail administration in Nigeria to be quicker, more equitable, and more responsible, adhering to both the national legislation and to the international rights regulations.
An Efficient Automated System for E-Waste Identification and Classification Using Yolov8 Ogbonnia O. Emmanuel, Mitong Z. Dorcas, Ayodele A. Adebiyi, Marion O. Adebiyi Nipes Journal of Science and Technology Research, 2025 The growing quantity and intricacy of electronic waste (e-waste) is proving to be an obstacle for efficient waste management and resource recycling. Identification and differentiation of e-waste plays an indispensable role in the recycling sequence. This study is aimed at filling this gap through development and testing of an automated e-waste identification model based on deep learning technologies. Particularly, the study uses YOLOv8 (You Only Look Once version 8) object detection framework with transfer learning for enhanced accuracy and effective training. For this study, a subset of images containing five categories of e-waste, including laptops, monitors, mice, mobile phones, and keyboards, were retrieved from the e-waste repository on Kaggle. The methodologies included data preprocessing, which comprised image standardization and augmentation, model training unto 100 epochs, and evaluation using standard object detection metrics on a separate test set. The results demonstrate the effectiveness of the proposed approach with an mAP@0.5 of 0.950 and mAP@0.5-0.95 of 0.808. Furthermore, the model is said to be reliable with precision of 0.936, recall of 0.941, F1 score of 0.939, constituting efficient identification and localization of e-waste elements. To showcase practical applicability, the trained model was successfully deployed into an interactive web application using Streamlit, enabling users to upload images and receive real-time e-waste identification results.
Unimodal to Multimodal Machine Learning in Malaria Diagnosis: Challenges and Opportunities Oghenegueke F. Amrevuawho, Marion O. Adebiyi, Ayodele A. Adebiyi, Emmanuel O. Ogbonnia, Peter E. Alfa, et al. Nipes Journal of Science and Technology Research, 2025 Malaria continues to pose an enormous global health burden, particularly in Sub-Saharan Africa, where early and correct diagnosis is essential for effective treatment. Traditional unimodal machine learning (ML) models have been widely used for malaria detection, mostly based on microscopic blood smeared pictures. Nevertheless, these models are limited in their generalizability, interpretability, and reliance on just one data source. The shift to multimodal ML, which incorporates imaging, clinical, and genomic data, opened up new avenues for improved diagnostic accuracy and early-stage malaria diagnosis. This research investigated the obstacles and potential of transitioning from unimodal to multimodal machine learning for malaria diagnosis. We examined existing unimodal approaches, highlighted fusion strategies for multimodal learning, and addressed issues such as data integration difficulty, computing needs, and interpretability. Finally, the potential of multimodal ML for increased diagnostic reliability, early illness identification, and clinical decision-making was discussed. This study emphasized the necessity for more research in multimodal ML for malaria diagnosis.
Bayesian Optimized Machine Learning Models for Predicting Gas Flaring Volumes in Nigeria's Oil and Gas Sector Ogbonnia O. Emmanuel, Mitong Z. Dorcas, Alfa Peter Eleojo, Ishola Oluwaseun Joshua, Oghenegueke F. Amrevuawho, et al. Nipes Journal of Science and Technology Research, 2025 This study aims to understand the application of Machine Learning algorithms such as Support Vector Regression (SVR), Random Forest, and K-Nearest Neighbors (KNN) in predicting gas flaring activities in Nigeria’s oil and gas sector. This research examined models’ performance with both default and Bayesian Optimized hyperparameters, with the best Bayesian optimized hyperparameters set through training. According to the results of experiments, all models have performed remarkably well; however, the SVR model outperformed the others with an R-squared score of 0.993, MSE of 0.657. The optimized versions of the Random Forest and KNN models also performed well. This serves as a testament to the growing capabilities of technology through Machine Learning to estimate nonlinear flare co2 volume functions, which improves environmental, regulatory, and legislative monitoring in Nigeria’s petroleum industry.
A Hybrid Chaotic Tent Map-Pelican Optimization Algorithm for Software Defect Prediction Olufemi S. Ojo, Mayowa O. Oyediran, Kazeem M. Olagunju, Kafayat B. Opoola, Emmanuel O. Ogbonnia, et al. Nipes Journal of Science and Technology Research, 2025 Software defect prediction has a critical function in ensuring software quality and minimizing maintenance costs. This study introduces a novel hybrid optimization approach called the Pelican Optimization Algorithm-Chaotic Tent Map (POA-CTM) technique, designed to improve the performance of defect prediction systems. The proposed technique combines the exploration and exploitation capabilities of the Pelican Optimization Algorithm (POA) with the randomness and ergodicity properties of the Chaotic Tent Map (CTM) to fine-tune model parameters effectively. The POA-CTM technique is tested on multiple software defect datasets and compared with existing optimization methods to evaluate its accuracy, precision, and computational efficiency. Results reveal that the hybrid technique achieves superior prediction performance, which makes it a promising tool for improving software reliability and helping developers detect defects early. The proposed approach also highlights the potential of integrating bio-inspired optimization methods with chaos theory in addressing complex software engineering challenges.
A Systematic Review of Python Libraries for Modern UI Development Ogbonnia O. Emmanuel, Mitong Z. Dorcas, Oghenegueke F. Amrevuawho, Alfa Peter Eleojo, Prisca O. Olawoye, et al. Nipes Journal of Science and Technology Research, 2025 Python plays a big role in today's software engineering when it comes to creating graphical user interfaces (GUIs). It offers a diverse set of libraries for this purpose. This review takes a close look at important Python libraries for modern UI development. We aim to compare these libraries based on their design, features, how they render graphics, which platforms they work on, how active their communities are, how well they perform, and what limits they have. This research used the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) method to gather information from peer-reviewed papers, software repositories, and trusted technical guides. Our main findings show different types of libraries: basic toolkits (Tkinter) advanced desktop frameworks (PyQt/PySide, and wxPython), mobile-focused and custom-rendering options (Kivy, Flet, and Toga), speed-optimized choices (DearPyGui), libraries that use web tech (Eel, Flexx, and PyWebIO), and specialized interfaces for AI/ML apps (Streamlit, and Gradio Chainlit). This study reveals current usage trends, points out ongoing issues like maintaining consistency across platforms and performance bottlenecks, and spots gaps in areas such as mature native mobile toolkits and standard accessibility support. The results give developers a factual basis to choose libraries and show paths for future research and community efforts to set standards.
Bayesian Optimized Xgboost for Enhanced Chronic Kidney Disease Prediction and Feature Importance Analysis Ogbonnia O. Emmanuel, Mitong Z. Dorcas, Ishola Oluwaseun Joshua, Oghenegueke F. Amrevuawho, Alfa Peter Eleojo, et al. Nipes Journal of Science and Technology Research, 2025 Chronic Kidney Disease (CKD) poses an intricate challenge to global healthcare. Timely prediction is critical for effective patient management on an individual level. Existing approaches to predicting CKD tend to apply more traditional techniques with systematic and linear methodologies, resulting in lower accuracy as they miss complex, non-linear relationships within the individual patient data. In this study, we offer a new approach that evaluates CKD risk using eXtreme Gradient Boosting (XGBoost) machine learning and improves it further with Bayesian Optimization. The method comprises of collecting and merging clinical, demographic, and laboratory data for 400 patients. Accomplished with the proposed model is thorough preprocessing, applying generalization through cross-validation, stepwise data partitioning into training and test subgroups, and avoidance of data leakage. For these reasons, the Bayesian Optimized XGBoost Model achieved an astonishing 98.8% prediction accuracy on the test set.
A Hybrid SVM-Bayesian-Fuzzy Logic Framework for Predictive Maintenance Peter E. Alfa, Olufunso D. Alowolodu, Kazeem M. Olagunju, Oghenegueke F. Amrevuawho, Emmanuel E. Ogbonnia, et al. Nipes Journal of Science and Technology Research, 2025 In order to minimize unscheduled downtime and maximize operational efficiency, predictive maintenance (PdM), is essential in contemporary industrial systems. Conventional singlemodel techniques, on the other hand, frequently struggle with dynamic operational situations, complex multi-source data, and inherent uncertainties, which results in reactive maintenance tactics and missed early failures. In order to improve fault detection accuracy, interpretability, and flexibility, this study suggests a hybrid architecture that combines Support Vector Machines (SVM), Bayesian Networks (BN), and Fuzzy Logic Inference (FLI). With a 94% fault detection accuracy, the SVM component is excellent at detecting patterns of equipment degradation. Fuzzy Logic deals with uncertainty of data and gives all interpretable risk assessments, whereas Bayesian Networks express probabilistic relationships among system parts and can perform causal reasoning. The data inbalance was dealt with by means of the SMOTETomek method. Compared with individual models, the reliability, decision support and early defect diagnosis can be improved using the proposed framework. It is widely suitable for noisy and dynamic industry data, for example, industrial production, power systems, automobile, healthcare and aviation. The results show that the framework is robust in practical situation.
Traffic Accident Severity Classification Using ResNet-18 O Oluwadamilola, O Emmanuel E3S Web of Conferences 684, 01002 , 2026 2026.0
Digitisation of the Nigerian Bail Process: A Framework for Interoperable, API-Driven Verification OA Ojerinde, EF Aminu, A Ekundayo, M Nwankwo, AT Zakka, E Ogbonnia NIPES JSTR SPECIAL ISSUE 7 (2), 4043–4048-4043–4048 , 2025 2025.0
Landmark-Aware Heterogeneous Graph Framework for Multi Source Road Crash Data Integration in Nigeria E Ogbonnia, OA Ojerinde, EF Aminu, IO Alabi, SA Adepoju NIPES JSTR SPECIAL ISSUE 7 (2), 4036–4042-4036–4042 , 2025 2025.0
A Hybrid Chaotic Tent Map-Pelican Optimization Algorithm for Software Defect Prediction OS Ojo, MO Oyediran, KM Olagunju, KB Opoola, EO Ogbonnia, ... NIPES JSTR SPECIAL ISSUE 7 (1), 2386–2394-2386–2394 , 2025 2025.0
Bayesian Optimized Machine Learning Models for Predicting Gas Flaring Volumes in Nigeria's Oil and Gas Sector OO Emmanuel, MZ Dorcas, AP Eleojo, IO Joshua, OF Amrevuawho, ... NIPES JSTR SPECIAL ISSUE 7 (1), 2107–2115-2107–2115 , 2025 2025.0
Bayesian Optimized Xgboost for Enhanced Chronic Kidney Disease Prediction and Feature Importance Analysis OO Emmanuel, MZ Dorcas, IO Joshua, OF Amrevuawho, AP Eleojo, ... NIPES JSTR SPECIAL ISSUE 7 (1), 2128–2134-2128–2134 , 2025 2025.0
An Efficient Automated System for E-Waste Identification and Classification Using Yolov8 OO Emmanuel, MZ Dorcas, AA Adebiyi, MO Adebiyi NIPES JSTR SPECIAL ISSUE 7 (1), 1752–1760-1752–1760 , 2025 2025.0
A Systematic Review of Python Libraries for Modern UI Development OO Emmanuel, MZ Dorcas, OF Amrevuawho, AP Eleojo, PO Olawoye, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1745–1751-1745–1751 , 2025 2025.0
A Hybrid SVM-Bayesian-Fuzzy Logic Framework for Predictive Maintenance PE Alfa, OD Alowolodu, KM Olagunju, OF Amrevuawho, EE Ogbonnia, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1768–1773-1768–1773 , 2025 2025.0
Unimodal to Multimodal Machine Learning in Malaria Diagnosis: Challenges and Opportunities OF Amrevuawho, MO Adebiyi, AA Adebiyi, EO Ogbonnia, PE Alfa, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1068–1074-1068–1074 , 2025 2025.0
Integrating Text Intelligent Systems (TIS) across the Academic Workflows in Nigerian Institutions OF Amrevuawho, OM Ruben, PO Olawoye, PE Alfa, EO Ogbonnia, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1153–1157-1153–1157 , 2025 2025.0
Web-Based Diagnosis of Typhoid and Malaria using Machine Learning PO Odion, EO Ogbonnia Nigerian Defence Academy Journal of Military Science and Interdisciplinary … , 2024 2024.0 Citations: 7
Ensemble learning approach for symptom-based diagnosis of typhoid and Malaria Co-Infection PO Odion, EO Ogbonnia, MN Musa Nigerian Defence Academy Journal of Military Science and Interdisciplinary … , 2024 2024.0 Citations: 3
A predictive symptoms-based system using support vector machines to enhanced classification accuracy of malaria and typhoid coinfection EF Aminu, EO Ogbonnia, IS Shehu MECS , 2016 2016.0 Citations: 16
International Journal of Mathematical Sciences and Computing (IJMSC) EF Aminu, EO Ogbonnia, IS Shehu
MOST CITED SCHOLAR PUBLICATIONS
A predictive symptoms-based system using support vector machines to enhanced classification accuracy of malaria and typhoid coinfection EF Aminu, EO Ogbonnia, IS Shehu MECS , 2016 2016.0 Citations: 16
Web-Based Diagnosis of Typhoid and Malaria using Machine Learning PO Odion, EO Ogbonnia Nigerian Defence Academy Journal of Military Science and Interdisciplinary … , 2024 2024.0 Citations: 7
Ensemble learning approach for symptom-based diagnosis of typhoid and Malaria Co-Infection PO Odion, EO Ogbonnia, MN Musa Nigerian Defence Academy Journal of Military Science and Interdisciplinary … , 2024 2024.0 Citations: 3
Traffic Accident Severity Classification Using ResNet-18 O Oluwadamilola, O Emmanuel E3S Web of Conferences 684, 01002 , 2026 2026.0
Digitisation of the Nigerian Bail Process: A Framework for Interoperable, API-Driven Verification OA Ojerinde, EF Aminu, A Ekundayo, M Nwankwo, AT Zakka, E Ogbonnia NIPES JSTR SPECIAL ISSUE 7 (2), 4043–4048-4043–4048 , 2025 2025.0
Landmark-Aware Heterogeneous Graph Framework for Multi Source Road Crash Data Integration in Nigeria E Ogbonnia, OA Ojerinde, EF Aminu, IO Alabi, SA Adepoju NIPES JSTR SPECIAL ISSUE 7 (2), 4036–4042-4036–4042 , 2025 2025.0
A Hybrid Chaotic Tent Map-Pelican Optimization Algorithm for Software Defect Prediction OS Ojo, MO Oyediran, KM Olagunju, KB Opoola, EO Ogbonnia, ... NIPES JSTR SPECIAL ISSUE 7 (1), 2386–2394-2386–2394 , 2025 2025.0
Bayesian Optimized Machine Learning Models for Predicting Gas Flaring Volumes in Nigeria's Oil and Gas Sector OO Emmanuel, MZ Dorcas, AP Eleojo, IO Joshua, OF Amrevuawho, ... NIPES JSTR SPECIAL ISSUE 7 (1), 2107–2115-2107–2115 , 2025 2025.0
Bayesian Optimized Xgboost for Enhanced Chronic Kidney Disease Prediction and Feature Importance Analysis OO Emmanuel, MZ Dorcas, IO Joshua, OF Amrevuawho, AP Eleojo, ... NIPES JSTR SPECIAL ISSUE 7 (1), 2128–2134-2128–2134 , 2025 2025.0
An Efficient Automated System for E-Waste Identification and Classification Using Yolov8 OO Emmanuel, MZ Dorcas, AA Adebiyi, MO Adebiyi NIPES JSTR SPECIAL ISSUE 7 (1), 1752–1760-1752–1760 , 2025 2025.0
A Systematic Review of Python Libraries for Modern UI Development OO Emmanuel, MZ Dorcas, OF Amrevuawho, AP Eleojo, PO Olawoye, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1745–1751-1745–1751 , 2025 2025.0
A Hybrid SVM-Bayesian-Fuzzy Logic Framework for Predictive Maintenance PE Alfa, OD Alowolodu, KM Olagunju, OF Amrevuawho, EE Ogbonnia, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1768–1773-1768–1773 , 2025 2025.0
Unimodal to Multimodal Machine Learning in Malaria Diagnosis: Challenges and Opportunities OF Amrevuawho, MO Adebiyi, AA Adebiyi, EO Ogbonnia, PE Alfa, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1068–1074-1068–1074 , 2025 2025.0
Integrating Text Intelligent Systems (TIS) across the Academic Workflows in Nigerian Institutions OF Amrevuawho, OM Ruben, PO Olawoye, PE Alfa, EO Ogbonnia, ... NIPES JSTR SPECIAL ISSUE 7 (1), 1153–1157-1153–1157 , 2025 2025.0
International Journal of Mathematical Sciences and Computing (IJMSC) EF Aminu, EO Ogbonnia, IS Shehu
