Ernest Enyinnaya Onuiri
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Ernest Enyinnaya Onuiri has a total of 29 co-authors. Here are the top co-authors by number of shared publications:
- Ayomikun Abayomi Awoseyi
Department of Computer Science, Babcock University, Ilishan-Remo, Nigeria
3 shared publications - Oluwawemimo Oluwaseun Adebowale
Department of Veterinary Public Health and Preventive Medicine, Federal University of Agriculture, Abeokuta, Nigeria
3 shared publications - Ayodeji Oluwadare Olarinmoye
Department of Agriculture and Industrial Technology, Babcock University, Ilishan-Remo, Nigeria
2 shared publications Kelechi C. Umeaka
2 shared publicationsOlamide B. Kalesanwo
2 shared publicationsAderonke A. Adegbenjo
1 shared publication
Latest Publications
- Open Access
- 22 September 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Spatio-temporal dynamics, clustering, and hotspot evolution of reported foot-and-mouth disease outbreak burden in Nigeria, 2015–2025
- 22 September 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Open AccessSpatio-temporal dynamics, clustering, and hotspot evolution of reported foot-and-mouth disease outbreak burden in Nigeria, 2015–2025
- Open Access
- 8 June 2026
- Published by Center for Open Science in MetaArXiv
PROTOCOL FOR A SYSTEMATIC REVIEW OF COMPUTATIONAL METHODS, REPRODUCIBILITY, AND RESEARCH-CAPACITY PATTERNS IN FOOT-AND-MOUTH DISEASE STUDIES
Background: Foot-and-mouth disease (FMD) is a highly contagious transboundary animal disease with major implications for livestock production, food security, surveillance, and disease-control planning. Computational methods, including spatial analytics, statistical and mathematical modelling, machine learning, artificial intelligence, simulation, and integrated modelling approaches, are increasingly used to study FMD occurrence, spread, risk, prediction, and control. However, the methodological trends, reproducibility practices, and reported research-capacity patterns within computational FMD studies require structured synthesis.Objectives: This amended Version 2.0 protocol describes a systematic review and systematic mapping programme designed to synthesise computational methods, reproducibility and open-science practices, and research-capacity patterns in FMD studies published between 2013 and 2023. The review will support three planned outputs: a main computational-methods systematic review; a reproducibility and open-science audit; and a conditional funding, authorship, and research-capacity mapping study.Methods: The review will follow PRISMA-aligned reporting principles and a structured eligibility framework adapted from PICOS. Searches will be conducted in Embase, Google Scholar, PubMed, and Scopus, supplemented by hand searching where appropriate. Eligible studies will include peer-reviewed English-language articles published from 2013 to 2023 that apply computational, statistical, mathematical, spatial, machine learning, artificial intelligence, simulation, or related analytical methods to FMD. Records will be managed using Rayyan and Mendeley, while extracted data will be organised using a structured extraction form. Deduplication, screening, data extraction, and coding harmonisation will be documented during final dataset preparation.Synthesis and conclusion: Data will be synthesised using descriptive statistics, cross-tabulations, narrative synthesis, and, where appropriate, geographic visualisation using Python. Meta-analysis is not planned because the expected evidence base is methodologically heterogeneous and better suited to systematic mapping. This amended protocol sharpens the original OSF-registered review by moving from a generic trend review to an output-driven evidence-synthesis programme focused on computational methods, reproducibility, and research-capacity patterns.
- 8 June 2026
- Published by Center for Open Science in MetaArXiv
Open AccessPROTOCOL FOR A SYSTEMATIC REVIEW OF COMPUTATIONAL METHODS, REPRODUCIBILITY, AND RESEARCH-CAPACITY PATTERNS IN FOOT-AND-MOUTH DISEASE STUDIES
Background: Foot-and-mouth disease (FMD) is a highly contagious transboundary animal disease with major implications for livestock production, food security, surveillance, and disease-control planning. Computational methods, including spatial analytics, statistical and mathematical modelling, machine learning, artificial intelligence, simulation, and integrated modelling approaches, are increasingly used to study FMD occurrence, spread, risk, prediction, and control. However, the methodological trends, reproducibility practices, and reported research-capacity patterns within computational FMD studies require structured synthesis.Objectives: This amended Version 2.0 protocol describes a systematic review and systematic mapping programme designed to synthesise computational methods, reproducibility and open-science practices, and research-capacity patterns in FMD studies published between 2013 and 2023. The review will support three planned outputs: a main computational-methods systematic review; a reproducibility and open-science audit; and a conditional funding, authorship, and research-capacity mapping study.Methods: The review will follow PRISMA-aligned reporting principles and a structured eligibility framework adapted from PICOS. Searches will be conducted in Embase, Google Scholar, PubMed, and Scopus, supplemented by hand searching where appropriate. Eligible studies will include peer-reviewed English-language articles published from 2013 to 2023 that apply computational, statistical, mathematical, spatial, machine learning, artificial intelligence, simulation, or related analytical methods to FMD. Records will be managed using Rayyan and Mendeley, while extracted data will be organised using a structured extraction form. Deduplication, screening, data extraction, and coding harmonisation will be documented during final dataset preparation.Synthesis and conclusion: Data will be synthesised using descriptive statistics, cross-tabulations, narrative synthesis, and, where appropriate, geographic visualisation using Python. Meta-analysis is not planned because the expected evidence base is methodologically heterogeneous and better suited to systematic mapping. This amended protocol sharpens the original OSF-registered review by moving from a generic trend review to an output-driven evidence-synthesis programme focused on computational methods, reproducibility, and research-capacity patterns.
- 27 May 2026
- Published by Springer Nature
- p. 485-511
Hybrid Deep Learning Model for Reversible Image Steganography
- 27 May 2026
- Published by Springer Nature
- p. 485-511
Hybrid Deep Learning Model for Reversible Image Steganography
- Open Access
- 6 August 2025
- Published by Springer Nature in Discover Public Health
- Vol. 22 (1) , 1-19
Perspective on ethical AI in computational epidemiology and one health with COHRCIE framework and computational prophylaxis
- 6 August 2025
- Published by Springer Nature in Discover Public Health
- Vol. 22 (1) , 1-19
Open AccessPerspective on ethical AI in computational epidemiology and one health with COHRCIE framework and computational prophylaxis
- Open Access
- 24 April 2025
- Published by Acadlore Publishing Services Limited in Acadlore Transactions on AI and Machine Learning
- Vol. 4 (2) , 97-108
Enhancing Non-Invasive Diagnosis of Endometriosis Through Explainable Artificial Intelligence: A Grad-CAM Approach
Significant advancements in artificial intelligence (AI) have transformed clinical decision-making, particularly in disease detection and management. Endometriosis, a chronic and often debilitating gynecological disorder, affects a substantial proportion of reproductive-age women and is associated with pelvic pain, infertility, and a reduced quality of life. Despite its high prevalence, non-invasive and accurate diagnostic methods remain limited, frequently resulting in delayed or missed diagnoses. In this study, a novel diagnostic framework was developed by integrating deep learning (DL) with explainable artificial intelligence (XAI) to address existing limitations in the early and non-invasive detection of endometriosis. Abdominopelvic magnetic resonance imaging (MRI) data were obtained from the Crestview Radiology Center in Victoria Island, Lagos State. Preprocessing procedures, including Digital Imaging and Communications in Medicine (DICOM)-to-PNG conversion, image resizing, and intensity normalization, were applied to standardize the imaging data. A U-Net architecture enhanced with a dual attention mechanism was employed for lesion segmentation, while Gradient-weighted Class Activation Mapping (Grad-CAM) was incorporated to visualize and interpret the model’s decision-making process. Ethical considerations, including informed patient consent, fairness in algorithmic decision-making, and mitigation of data bias, were rigorously addressed throughout the model development pipeline. The proposed system demonstrated the potential to improve diagnostic accuracy, reduce diagnostic latency, and enhance clinician trust by offering transparent and interpretable predictions. Furthermore, the integration of XAI is anticipated to promote greater clinical adoption and reliability of AI-assisted diagnostic systems in gynecology. This work contributes to the advancement of non-invasive diagnostic tools and reinforces the role of interpretable DL in the broader context of precision medicine and women's health.
- 24 April 2025
- Published by Acadlore Publishing Services Limited in Acadlore Transactions on AI and Machine Learning
- Vol. 4 (2) , 97-108
Open AccessEnhancing Non-Invasive Diagnosis of Endometriosis Through Explainable Artificial Intelligence: A Grad-CAM Approach
Significant advancements in artificial intelligence (AI) have transformed clinical decision-making, particularly in disease detection and management. Endometriosis, a chronic and often debilitating gynecological disorder, affects a substantial proportion of reproductive-age women and is associated with pelvic pain, infertility, and a reduced quality of life. Despite its high prevalence, non-invasive and accurate diagnostic methods remain limited, frequently resulting in delayed or missed diagnoses. In this study, a novel diagnostic framework was developed by integrating deep learning (DL) with explainable artificial intelligence (XAI) to address existing limitations in the early and non-invasive detection of endometriosis. Abdominopelvic magnetic resonance imaging (MRI) data were obtained from the Crestview Radiology Center in Victoria Island, Lagos State. Preprocessing procedures, including Digital Imaging and Communications in Medicine (DICOM)-to-PNG conversion, image resizing, and intensity normalization, were applied to standardize the imaging data. A U-Net architecture enhanced with a dual attention mechanism was employed for lesion segmentation, while Gradient-weighted Class Activation Mapping (Grad-CAM) was incorporated to visualize and interpret the model’s decision-making process. Ethical considerations, including informed patient consent, fairness in algorithmic decision-making, and mitigation of data bias, were rigorously addressed throughout the model development pipeline. The proposed system demonstrated the potential to improve diagnostic accuracy, reduce diagnostic latency, and enhance clinician trust by offering transparent and interpretable predictions. Furthermore, the integration of XAI is anticipated to promote greater clinical adoption and reliability of AI-assisted diagnostic systems in gynecology. This work contributes to the advancement of non-invasive diagnostic tools and reinforces the role of interpretable DL in the broader context of precision medicine and women's health.
- 31 October 2023
- Published by International Information and Engineering Technology Association in Journal Européen des Systèmes Automatisés
- Vol. 56 (5) , 889-897
Design and Analysis of an Automated IoT System for Data Flow Optimization in Higher Education Institutions
- 31 October 2023
- Published by International Information and Engineering Technology Association in Journal Européen des Systèmes Automatisés
- Vol. 56 (5) , 889-897
Design and Analysis of an Automated IoT System for Data Flow Optimization in Higher Education Institutions