Nnamdi Azikiwe University Journals
Not a member yet
5579 research outputs found
Sort by
FOSTERING CRITICAL THINKING AND CREATIVITY THROUGH ARTIFICIAL INTELLIGENCE (AI) IN NIGERIA PUBLIC TERTIARY INSTITUTIONS OF SOUTHEAST STATES
No full textThe study examined fostering of critical thinking and creativity through artificial intelligence (AI) inNigeria public tertiary institutions of South East States. Philosophy guides education in thedevelopment of critical thinking and creativity in learners. These higher order of thinking makelearners to think creatively, approach problems from different angles and develop innovative solutions.Thus, this study becomes imperative in order to make learners better prepared to fit into this everchanging world of technological advancement. Three research questions guided the study. A 15– itemstructured questionnaire constructed by the researchers was used for data collection. The instrumentwas validated by three experts each from the Department of Educational Foundations (measurementand evaluation), Department of Philosophy and Department of Computer Science of Nnamdi AzikiweUniversity Awka. Cronbach Alpha was used to determine the internal consistency reliability of theinstrument which was seen as reliable with an index of 0.83. Mean (x) was used to analyze the datacollected with the instrument. The results revealed among other things factors necessary for fosteringcritical thinking and creativity through Artificial Intelligence (AI) in Nigeria public tertiaryinstitutions of South East States as adequate digital infrastructure, adequate computer literateacademic staff, better staff welfare package, adequate funding of curriculum, organizing regularworkshop and conference on Artificial Intelligence (AI). The study also found out the reasons that callfor the necessity and benefits of fostering critical thinking and creativity through ArtificialIntelligence (AI) in Nigeria public tertiary institutions of South East States. It was recommendedamong other things that government at all levels should provide adequate digital infrastructure, recruitadequate computer literate academic staff and place their priority on staff welfare
Improving Research Productivity of Early-Career Academics through Knowledge Acquisition and Sharing Behaviours
No full textEarly-career academics face significant pressure to establish themselves in their field through research productivity. For early-career academics, publishing research in reputable journals is crucial for their academic and professional growth. Unfortunately, research that primarily focuses on their research productivity and the factors that influence it has hitherto, been ignored. This study investigates the nature and the interrelationships of knowledge acquisition (KA), knowledge sharing behaviours (KSB), and research productivity (RP) among early-career academics of three faculties which included sciences, social science/management and Engineering. A correlational survey research design was employed for the study. The population comprised 645 early-career academics from three universities in Ogun state. A sample size of 215 was obtained from a population of 675 using a multi-stage sampling technique that involved purposive and census method. 179 properly filled copies of the questionnaire were returned. Descriptive statistics, correlation, and multiple regression analysis were used for data analysis. The findings revealed high levels of KA and KS among the respondents. However, the overall mean level of research productivity was low, despite a high level of publications in learned journals. Correlation analysis results indicated a significant and positive relationship between KA and RP, and between KSB and RP. Multiple regression analysis showed that KA and KSB had a combined effect on the RP of the respondents. The study concluded that KA and KSB significantly influenced the RP of early-career academics in Ogun State, Nigeria. Recommendations were presented based on the study’s findings which included among others that funding should be made available for attending conferences where they can present their work and learn from established researchers because this engenders their research productivity by facilitating knowledge acquisition and knowledge sharing behaviours that lead to enhanced professional growth
Utilisation of Remote Teaching Platforms by Science Lecturers in Some Selected Federal Universities in South-West, Nigeria
No full textRemote teaching platforms have emerged as an essential tool for allowing effective teaching and learning in the face of changing conditions and rising demand for online education. The study investigated remote teaching platforms utilization by science lecturers in some selected federal universities in South- West, Nigeria. The study adopted an ex- post- facto research design.. Total enumeration technique was adopted to involve all the science lecturers. Structured questionnaire was used for collecting data for the study. Out of a total of four hundred and sixty seven (467) questionnaires administered, three hundred and thirty six (336) were returned. However, only three hundred and sixteen (316) were found useful for the study. The study revealed that science lecturers mainly use Skype 272 (86.1%), Chat rooms 229 (72.5%), and Zoom 253 (80.1%) as remote teaching platforms. The result of frequency also revealed that zoom 266 (84.2%) was used always. Poor internet connectivity (x̅ =3.65), epileptic power supply (x̅ = 3.78), inadequate/slow bandwidth (x̅ = 3.64), were the main challenges encountered by the science lecturers while using the remote platforms. The study concluded that science lecturers may not be able to fully explore and adopt remote teaching platforms for their lectures due to the various challenges identified. The study thus recommended regular power supply, internet access, training and increased exposure to remote teaching platforms.
THE IMPACT OF ARTIFICIAL INTELLIGENCE IN DIGITAL COMMUNICATION AND SOCIAL MEDIA: A REVIEW
No full textThe functions and requisition of Artificial Intelligence are increasing daily. Artificial Intelligence is an arm of computer science that deals with the capability of computer system to exhibit human characteristics such as thinking and reasoning intelligently. its relevance has remarkably progressed within the past few years and the applications have been displayed in virtually every sector of life. In this paper, we explored the various ways in which Artificial Intelligence has impacted digital communication and social media as well as their implications to developers, entrepreneurs and the world at large. Digital communication and social media are among the verse number of domains benefitting from the innovative strength of artificial intelligence. It has tremendously transformed how people interact and communicate online providing them with sophisticated tools for more efficient digital communication experience, automatic content creation/moderation, customized recommendations for internet advertising and so on. From 2021 Statista record, about 4.26 billion people worldwide using social media spend averagely 2 hours, 27 minutes on daily basis and with this heightened number of social media users, artificial intelligence technology is crucial in order to meet the demands of these users with ease
HARNESSING THE POTENTIALS OF MACHINE LEARNING ALGORITHMS IN INFORMATION TECHNOLOGY FOR PREDICTIVE HEALTHCARE ANALYTICS
No full textThis research investigates the fundamental human right to access high-quality healthcare by leveraging machine learning algorithms within information technology systems for predictive healthcare analytics. Specifically, it focuses on utilizing healthcare data to accurately predict disease risks, overcoming the challenges posed by incompatible IT systems. By delving into various aspects of machine learning processes, including data acquisition, preprocessing, model selection, and evaluation within the context of chronic disease prediction—diabetes in this instance—the study demonstrates the potential of integrating machine learning algorithms into information technology to enhance clinical decision-making, optimize operational efficiency, and improve patient outcomes. The methodology employed follows the Feature-Driven Development (FDD) approach, a subset of Agile Methodology, an approach that guides the development process. A Stack Ensemble Technique, combining multiple machine learning models, is employed for enhanced predictive accuracy. The Logistic Regression model achieved an accuracy of 74.54%, a precision of 74.56%, a recall of 74.54%, and an F1-score of 74.53%. The Decision Tree model attained an accuracy of 66.61%, a precision of 66.63%, a recall of 66.61%, and an F1-score of 66.6%. The Random Forest model demonstrated superior performance with an accuracy of 79.76%, a precision of 79.85%, a recall of 79.76%, and an F1-score of 79.75%. Furthermore, Receiver Operating Characteristic (ROC) and Precision-Recall (PR) curves were employed for comprehensive evaluation. This research underscores the significant potential of integrating machine learning and IT systems to enhance healthcare delivery. By effectively predicting disease risks, optimizing resource allocation, and improving clinical decision-making, this approach contributes to a more efficient and effective healthcare system. The findings from this study provide a foundation for future research to explore the effectiveness of other ensemble techniques, incorporate additional features, and delve into interpretability methods to gain deeper insights into the model\u27s decision-making process
EFFECT OF COMPLEXING AGENT ON THE THICKNESS AND TRANSMITTIVITY OF CHEMICAL BATH DEPOSITED LEAD SELENIDE (PbSe+) THIN FILMS
No full textLead Selenide (PbSe) thin films were successfully deposited on glass substrates using the chemical bath deposition (CBD) method at room temperature (300 K). The study focused on examining the effect of the complexing agent, EDTA, on both the thickness and optical transmittance of the films. Structural characterization was conducted using an X-ray mini diffractometer (MD-10), and the results confirmed that the films were crystalline with a cubic structure, exhibiting a prominent diffraction peak corresponding to the (200) plane of PbSe. The pH of the deposition solutions, measured with a Mac Digital pH meter (MSW-552), was found to be in the alkaline range. It was observed that an increase in film thickness led to a corresponding decrease in transmittance, indicating the potential application of these films as thermal window coatings or in opaque coatings
Development of a Text Mining System for Summarising Sickle Cell Disease Research in Nigeria
No full textInformation about diseased and healthy individuals is readily available online. Mining such biomedical content provides valuable insights into patients’ conditions and research trends. However, this content is scattered, and manually gathering relevant data using traditional search engines is both laborious and incomplete. This paper reviews an ongoing study that aims to develop a text mining system for summarising and predicting research findings on Sickle Cell Disease (SCD) in Nigeria. The system includes a focused web crawler equipped with natural language processing (NLP) tools to extract and summarise abstracts from relevant biomedical databases like PubMed and BMJ Journals. Designed with Python, the crawler effectively mimics search functions to systematically gather relevant data. Results show that the crawler successfully scraped structured data, including article titles and abstracts, using targeted keywords such as "sickcell Nigeria" and "sick cell Nigeria." The next step involves integrating NLP-based summarisation techniques to forecast research trends. This study advances biomedical text mining and provides a scalable solution for automating knowledge extraction in SCD research across Nigeria. Ongoing improvements aim to enhance the crawler’s robustness, enabling bulk page crawling and expansion to additional databases
Application of Electrical Method for Geophysical Assessment of Subsurface Structures Contributing to Road Failures in Shao-Malete Road, Kwara State
No full textThis study applies the Electrical Resistivity Method using the Vertical Electrical Sounding (VES) technique to investigate and evaluate subsurface structures contributing to recurrent road failures along the Shao-Malete Road in Kwara State, Nigeria. A total of seventy-one (71) VES stations were conducted using the Schlumberger array to delineate the subsurface lithological variations and assess their influence on pavement stability. The interpretation resistivity data revealed a different subsurface layer’s sequence consisting of lateritic topsoil, clayey-sand, sandy-clay, weathered basement and fresh basement. The reveal that the lateritic topsoil was found to be thin or discontinuous in several failed segments of VES 6-10, 12, 14, 16 and 21 locations, making these areas vulnerable to deformation under vehicular loads. The clayey and sandy-clay layers is also characterized by low to moderate resistivity values identified at shallow depths in VES 5, 11, 22, 35, 42, 51, 52, 58, and 62 locations, which indicate high moisture retention and swelling potential that further contribute to pavement weakening during the wet season. In addition, a thick and poorly consolidated weathered basement layer was delineated beneath some failed segments, contributing to reduced subgrade strength and the development of pavement distress such as cracks and potholes. This study demonstrates that subsurface heterogeneity and moisture-sensitive materials play significant roles in the observed road failures. It recommends integrating geophysical surveys in preconstruction assessments to guide subgrade stabilization and drainage design for sustainable road infrastructure
A Comparative Analysis on diabetes using Ensemble Machine Learning Models on Pima Indian Datasets
No full textDiabetes is a major global health concern, affecting millions worldwide and leading to severe health complications if not detected early. Timely and accurate diabetes prediction can greatly enhance patient outcomes. We suggest a diabetes prediction system in this article that uses a number of machine learning (ML) models, such as Logistic Regression, Random Forest, Support Vector Machine, and XGBoost. The models were evaluated using the Pima Indians Diabetes Dataset. Accuracy, precision, recall, F1-score, and The receiver operating characteristic (ROC) curve\u27s area under the curve (ROC) metrics were used to evaluate performance. Our findings reveal that ensemble methods like Random Forest and XGBoost outperformed traditional classifiers, achieving prediction accuracy of above 88.0%. This work highlights the potential of machine learning models in the early detection of diabetes and provides insights for developing scalable, real-time prediction systems