Faculty of Computing

Permanent URI for this communityhttps://repository.nileuniversity.edu.ng/handle/123456789/13

Browse

Author: search.filters.author.Atoyebi, Temitope OlufunmiSubject: search.filters.subject.Artificial intelligence

Search Results

Now showing 1 - 2 of 2
  • No Thumbnail Available
    Item
    Malaria Disease Prediction and Grading System
    (International Journal for Research in Applied Science & Engineering Technology, 2023-10-02) Atoyebi, Temitope Olufunmi; Rashidah Funke Olanrewaju; N. V. Blamah; Morufu Olalere
    Malaria disease is the number one cause of death all over the Sub-Sahara world. Data mining can help extract valuable knowledge from available data in the healthcare sector. This allows training a patient health prediction model faster than in a clinical trial. Various implementation of machine learning algorithms such as Bayesian Theorem, Logistic Regression, K-Nearest Neighbor, Support Vector Machine and Multinomial Naïve Bayes (MNB), etc. have been applied on Public Hospital Malaria Disease datasets but there has been a limit to modeling using Multinomial Naïve Bayes Algorithm. This research applied MNB modeling to discover the relationship between 15 relevant attributes of the Public Hospitals data collected from Bwari General Hospital in Bwari Area Council and Maitama Hospital in Abuja Municipal Area Council, Abuja, FCT, and Nigeria. The goal is to examine how dependencies between attributes affect the performance of the classifier. The MNB produces a reliable and transparent graphical representation between the attributes with the ability to predict new scenarios. The model has an accuracy of 97%. It was concluded that the model outperformed the GNB classifier which has an accuracy of 100% and RF which also has an accuracy of 100%.
  • No Thumbnail Available
    Item
    Engineering Resilience
    (World Journal of Advanced Engineering Technology and Sciences, 2025-10-21) Ohaka Amarachi Mavisclara; Ibrahim Isiaka Oshobugie; Atoyebi, Temitope Olufunmi; Suleiman Mustapha; Adeyinka Taslim Olabode; Ozuruoha Nkiruka Esther; Oyeboade Adekunle Yakub
    As climate change intensifies floods, heatwaves, and sea-level rise, global infrastructure faces unprecedented vulnerabilities, with damages reaching $360 billion in 2022. This review explores how smart technologies, artificial intelligence (AI), Internet of Things (IoT), digital twins, and resilient materials, transform climate-resilient infrastructure to withstand these escalating hazards. Synthesizing recent advancements from the last five years, it examines their applications in urban and rural contexts, drawing on case studies from the Netherlands’ IoT-enabled dikes, Singapore’s AI-driven urban planning, and Ghana’s cost-effective rural solutions. These innovations reduce maintenance costs by 15-25%, enhance flood response times by 40%, and align with Sustainable Development Goals (SDGs) for equitable, sustainable development. However, economic barriers, governance gaps, and equity challenges hinder global adoption, particularly in developing nations where connectivity and funding limit scalability. The review proposes future directions, including open-source platforms, public-private partnerships, and interdisciplinary research to address multi-hazard risks. By integrating data-driven engineering with green infrastructure, this study offers a roadmap for policymakers and engineers to build climate-proof infrastructure that ensures safety, sustainability, and resilience. This comprehensive synthesis underscores the urgent need for collaborative, inclusive strategies to safeguard global infrastructure against climate change, providing actionable insights for a resilient future.