Federal Polytechnic Ilaro Journal of Pure And Applied Sciences

Healthcare Professionals' Perceptions of Artificial Intelligence Integration: A Case Study of Lagos State, Nigeria

Olubukola Oluwatosin Olubena — 2025-08-06

This study investigated professional healthcare workers' perceptions of Artificial Intelligence (AI) integration in healthcare services within Lagos State, Nigeria. Guided by two research questions, the study employed a descriptive survey design. A sample of 45 professional health workers was selected using a stratified sampling technique. Data were collected via a self-designed instrument, the 'Perception of Professional on Artificial Intelligence (AI) Integration on Healthcare Services Questionnaire (PPAIIHSQ),' which demonstrated high reliability (coefficient of 0.98). Descriptive statistics were used for data analysis. Findings revealed that professionals perceived significant benefits of AI integration, including enhanced diagnosing and treatment planning, predictive analytics, accelerated drug discovery and development, the utility of virtual assistants and chatbots, and improved medical record keeping. However, the study also identified several critical challenges hindering effective AI integration. These include the absence of standard guidelines, concerns regarding data privacy and security, the risk of data breaches, issues of bias and fairness in training data, potential for misdiagnosis, and the poor state of health infrastructure development. Based on these findings, the study recommends that government and healthcare stakeholders collaborate to improve health infrastructure to facilitate AI adoption. Additionally, international organizations such as the World Health Organization (WHO) are encouraged to support the Nigerian health sector by providing necessary AI resources for healthcare services across the country.

Evaluating the Predictive Power of Random Forest Regression on Economic Growth

Gabriel O. Ojo — 2025-08-06

This paper examines the probabilities of using the Random Forest regression model to predict the Logarithm of Gross Domestic Product (LGDP), offering a valuable resource in economic forecasting. This model demonstrated outstanding predictive accuracy, with a Mean Squared Error (MSE) of 0.0045, Root Mean Squared Error (RMSE) of 0.0674, and Mean Absolute Error (MAE) of 0.0565. These metrics confirm the model's effectiveness in capturing economic trends. Additionally, an R-squared value of 0.9430 indicates that the model explains 94.30 per cent of the variation in LGDP, highlighting its strength and reliability in economic prediction. To provide a comprehensive assessment, the Random Forest model is compared with the traditional Ordinary Least Squares (OLS) regression, which shows higher error rates (MSE: 0.0089, RMSE: 0.0943, MAE: 0.0782) and a lower R-squared of 0.8975, demonstrating the superiority of the Random Forest approach in data prediction. The Labour Growth Rate (LAGR) emerges as the most influential predictor of economic growth, followed by the Service Sector Index (LSER) and the Industrial Output Index (LIND). It is important to note that agriculture has long been a major determinant of economic performance, further reinforcing the significance of the agricultural sector in national economic outcomes. These findings suggest that policymakers should consider targeted investments and supportive policies in agriculture to promote environmentally sustainable economic growth. The Random Forest regression model proves to be an effective and widely applicable tool for economic forecasting, serving as a foundation for policy planning and decision-making. This study offers a valuable framework for decision-makers to manage economic uncertainties and foster long-term growth by leveraging the method’s capacity to handle complex, non-linear relationships in high-dimensional data.

Addressing Gender Inequalities in TVET: Promoting Participation and Empowerment for Women

Oluwadamilola T. Ojenike — 2025-08-06

This research examines gender disparities in Technical and Vocational Education and Training (TVET) by analyzing enrollment patterns, completion rates, and employment outcomes disaggregated by gender. Using secondary data from the World Bank Gender Statistics, the study employs descriptive statistics, visualization tools, and regression analysis to examine these disparities. Findings reveal significant inequalities: male employment values exhibit greater variability compared to female employment, as shown by standard deviations of 1.64 and 0.17, respectively. Equally, male educational attainment shows higher variability (2.03) than female attainment (1.50). Regression analyses demonstrate a statistically significant positive relationship between female enrollment and attainment on educational outcomes, with female attainment accounting for 90.25% of variability in the response variable. Conversely, no significant relationship was found between female employment and TVET-related employment outcomes. These results highlight persistent gender disparities in TVET, particularly in employment, while highlighting the positive impact of female educational attainment on reducing inequalities. The discoveries advocate for targeted interventions to enhance female participation and equity in TVET programs.

A Comparative Analysis of CNN and Tesseract OCR on Handwritten Recognition System

James Olaleye Ogunseye — 2025-08-06

This study introduces a handwriting recognition system that utilises Convolutional Neural Networks (CNNs) to accurately identify handwritten characters. The methodology involves comprehensive data preprocessing, including normalisation, binarisation, and noise reduction, to enhance the quality of input images. A CNN model is trained on a diverse dataset to extract complex handwriting patterns. The system is deployed as a Flask-based web application for real-time predictions, ensuring accessibility and scalability. Results demonstrate that the CNN model achieves an accuracy of 95.8%, precision of 94.5%, recall of 93.7%, and F1-score of 94.1%. Compared to traditional Optical Character Recognition (OCR) systems, the CNN-based approach excels in handling varied handwriting styles and noisy inputs. Limitations in recognising non-Latin scripts indicate future research directions. This work highlights the effectiveness of CNNS for applications in digitising historical documents, banking, and education.

MOBILE-BASED REAL-TIME LECTURE REMINDER SYSTEM

Jumoke SOYEMI — 2025-08-06

The proliferation of technology is significantly transforming manual operations and improving their performance. Lecture Reminder is a tool that helps students and teachers keep track of Lecture dates and locations. It is a very important tool for time management. Widespread inefficiencies are associated with the traditional manual method of course reminders within tertiary institutions. Staff and faculty often forget an appointment that has been scheduled and may not teach a course on the scheduled date. Students skip classes due to incorrect location and time following an impromptu change of location and time, inaccuracies, and placement errors from paper records, as well as a lack of streamlined recall processes. This study conceptualizes and creates a dedicated Android mobile-based real-time lecture reminder system to bypass the limitations associated with the manual method of course reminders. A lecture reminder system is important for busy people because of the burden of remembering and memorizing all academic activities. Again, modern mobile devices such as smartphones have become increasingly powerful and are part of people's daily lives. The growing popularity of Android devices partly explains the motivation for choosing the platform for implementing this system.

Mathematical Modelling of the Moisture Retaining Characteristic of Clay Soil Over Some Other Soil Types

Olalekan A. Olaleye — 2025-08-06

The characteristic of clay soil to retain moisture better than some other soil types was modelled. Relevant assumptions were made based on the conditions under which the flow occurs. Using the usual Boussinesq approximation guided by these assumptions, the equations governing heat and mass flow were derived. The energy and momentum equations were both reduced to non-dimensional form and then to ordinary differential equations. These were subsequently resolved analytically, with numerical results computed using MATLAB software. The results were visually presented in graphs to illustrate the rate at which fluids passed through selected soil samples. Therefore, the model confirms the slower rate of fluid flow through clay soil compared to other soil samples considered.

Leveraging Digital Marketplaces to Enhance the Contribution of Local Artisans and Craftsmen to Nigeria's Economic Diversification

Lanre Olakanmi — 2025-08-06

This study delves into the transformative potential of digital marketplaces for Nigeria's local artisans and craftsmen. Leveraging these platforms aims to significantly enhance their visibility, accessibility, and economic value, ultimately contributing to the nation's vital economic diversification. A simple digital platform was meticulously designed and implemented to achieve this, adhering to the robust Model-View-Controller (MVC) architectural pattern. The Model component efficiently handles data logic and storage, ensuring seamless management of product information and artisan profiles. The View is responsible for presenting this data in a user-friendly and engaging manner to both artisans and prospective buyers. Finally, the Controller acts as the intermediary, diligently processing user inputs and facilitating smooth interactions within the platform. The core methodology prioritized ease of use, accessibility, and scalability, recognizing the diverse needs of both seasoned craftsmen and first-time online shoppers. The findings are compelling: integrating local artisans into these digital ecosystems demonstrably improves market access, leading to increased sales and broader customer reach. Furthermore, it fosters greater customer engagement, bridging the gap between creators and consumers. This, in turn, strongly supports inclusive economic growth across the country.

Histological Assessment of the Ethanolic Extract of Ficus platyphylla on N-Nitroso-N-Methylurea Induced Toxicity in Female Albino Mice (Mus musculus).

Love Emmanuel Adeboye — 2025-08-06

Ficus platyphylla Del. Holl (Moraceae) is used traditionally for treating stomach pain, infertility, and psychosis. The present study investigated the tissue repairing and protective potential of the ethanol extract of Ficus platyhylla bark in N-Nitoso-N-Methylurea-induced toxicity in female albino mice. Twenty-five (25) albino mice weighing 19-28g were grouped into five groups, with five mice in each group. Mice in all groups were injected intraperitoneally with Nitroso-Methyl Urea at a dose of 50mg/kg body weight. Mice were allowed to stay 7 days after the substance was induced to take effect before the commencement of the treatment. Mice in groups A, B, and C were treated orally with 1600mg/kg/day, 800mg/kg/day, and 400mg/kg/day of the plant extracts, respectively. Meanwhile, the mice in Group D received a standard dose of cisplatin through intraperitoneal injection, and the mice in Group E had access to water. Mice were sacrificed after 63 days of treatment. The liver, kidney, breast, heart, and lung tissues were harvested for histological studies. The histopathological examination showed that there is no presence of pathological changes in the heart and breast tissue. However, signs of tissue damage like features aligning with Renal Toxicity and Glomeruli toxicity are observed in the kidney, and mild hepatic toxicity in the liver of the treatment mice. The observed pathology and organ damage in the liver and kidneys are associated with the actions of NMU and cisplatin treatment. The treatments of the plant extract show signs of immune response and tissue rehabilitation. The extracts show possible tissue protection and rehabilitation.