University of Ibadan Journal of Science and Logics in ICT Research

An Optimal Detection for Leukaemia Cancer Based On RNS-Metaheuristic Technique in Micro Array Dataset

S.A. Bamidele — 2024-04-15

This paper addresses the critical challenge of leukaemia cancer detection through the integration of Residue Number System (RNS) and Convolutional Neural Network (CNN) Deep Learning Framework using a Microarray dataset. Leveraging a dataset obtained from the Kaggle machine learning repository, the study employs a comprehensive image processing pipeline, encompassing grayscale conversion, data augmentation, contrast enhancement, geometry normalization, and OTSU segmentation. The subsequent stages involve feature extraction using Histogram of Gradient (HOG) and comparative feature selection through Ant Colony Optimization (ACO) and an optimized ACO+RNS approaches. Results indicates that incorporating ACO+RNS outperforms the ACO-only in terms of classification accuracy, sensitivity, specificity, precision, and F1-score. Notably, the ACO+RNS model achieves a lower error rate and reduced training time, emphasizing the efficiency of incorporating Residue Number System encoding in feature selection.

Design of a Web-Based Vehicle Registration System Using QR Code

M. O Oloyede — 2024-04-15

The emergence of Information Technology (IT) and its application to our everyday life has made life easier by improving on the manual processes and operations across every facet of life. Information Technology has made great impacts on applications including health, finance, agriculture, and most importantly as this study is concerned with vehicle registration. In Nigeria, the whole vehicle registration process used to be purely manual; however, the current process is a combination of manual and technology-driven processes where problems such as inaccuracy, inefficiency and lack of flexibility still exist. Hence, this study is aimed to design and develop an online vehicle registration that would integrate different forms of registration needed for vehicle use. The designed system incorporates vehicle and user information page into a QR code such that the information can be accessible when the QR code is scanned. The study highlights related work from different studies, and provides useful recommendation for the improvement and deployment of the vehicle registration system in Nigeria.

Factors Influencing Telemedicine Adoption and Use among University of Ilorin Students

A. L Ibrahim — 2024-04-15

The pandemic severely affected Nigeria's healthcare sector, diminishing its functionality and hampering healthcare services. Telemedicine emerged as a potential solution, promising to alleviate and enhance Nigeria's healthcare system. Despite its potential benefits, there is limited research on the factors influencing students' adoption of telemedicine applications. This study focused on University of Ilorin undergraduate students, representing a significant part of Nigeria's ecosystem. Utilizing a multistage sampling approach with 380 participants, the study employs a conceptual framework based on the Unified Theory of Acceptance and Use of Technology (UTAUT) and Information Decision Process (IDP). The research utilized questionnaires to
gather data. Statistical analyses, including correlation, regression, ANOVA, and T-test, were conducted using SPSS. Findings indicate that students were aware of telemedicine, hold a positive perception, and express willingness to adopt it. However, barriers like privacy concerns, economic constraints, and lack of a supportive framework impeded adoption. The study concluded that telemedicine's impact on the health sector was substantial. Recommendations included government consultation on citizen perception for informed policy decisions, university and health organizations promoting telemedicine adoption, and government-led initiatives to educate and train healthcare stakeholders in telemedicine applications.

Fault Prediction in Power Transformer Using Ensemble Models

C. E Igodan — 2024-04-15

One of the highly important elements of electrical system networks is the power transformer. There is an increasing amount of research being done on early warning systems and faults detection because the failure of these elements can ground economic activities. More so, using dissolved gas analysis (DGA) as one of the mostly used conventional techniques is deficient in locating these incipient faults as this may be caused by a variety of factors which includes but not limited to imbalance problem, inadequate and overlap in the DGA datasets, thereby restricts its capacity to obtain precise diagnosis. Therefore, this paper proposed an ensemble machine learning methods for incipient faults prediction using DGA datasets comprising 166 samples and eight variables. This research compares the accuracies of four ensemble machine learning methods: Bagging, Adaboost, Stacking, and Voting methods using multilayer perceptron and support vector machines respectively. The results obtained ranges from 90.50% to 100% with the Adaboost (MLP) achieving the highest accuracy, whilst the misclassification percentage ranges from 1.62% - 18.06% with Stacking method as the least performing. In the end, our findings highlighted the importance of the use of ensemble methods and has future prospects for further advancement

Internet of Things (IoT) Model for the Detection of an Infectious Disease (COVID-19)

P. I Campbell — 2024-04-15

The COVID-19 pandemic, originating in late 2019 due to the highly transmissible SARS-CoV-2 virus, has precipitated a global health crisis with profound impacts on healthcare systems, economies, and societal structures. Despite advancements in vaccination and treatment development, persistent challenges endure due to viral mutations, necessitating continuous vigilance and robust screening efforts. In response, remote photoplethysmography (rPPG) technology has emerged as a critical tool for contactless heart monitoring during COVID-19 screening protocols. This innovation reduces virus transmission risks by eliminating physical contact during vital sign assessments, capturing crucial data including heart rate, body temperature, and oxygensaturation levels. The presented thesis investigates the utilization of IoT devices, incorporating an RGB camera and an infrared camera, to non invasively predict the presence of COVID-19. The methodology entails video capture, frame extraction, facial detection techniques, and prediction of vital signs including body temperature, heart rate, and oxygen saturation. Leveraging an artificial neural network trained on a COVID-19 dataset, the implemented system achieves an impressive 95% accuracy in infection prediction. This system offers promising prospects to mitigate infection risks, enhance case detection, and find application across various settings,
including entry points, containment zones, and home quarantine

Comparative Analysis of Machine Learning Algorithms for the Classification of Twitter Bots

B. A. Ayogu — 2024-04-15

Social media platforms have become risky for actual users due to the rise in the number of bots. The security mechanisms put in place to help identify and categorize bots accounts from legitimate human accounts have significant drawbacks, such as the misclassification of accounts because of behavioral change. In general, studies on Twitter bots identification demonstrate that bots can be useful while also having a negative impact on users by broadcasting misleading news, spamming, or posing as a phony follower to boost an account's popularity. This study employed Logistic Regression, Catboost, and Random Forest algorithms to develop Twitter bots classification systems, capable of distinguishing between useful and harmful bots accounts in order to limit their impact on users and the Twitter community. The feasibility of the algorithms was tested on Twitter spam bots dataset gotten from Kaggle, containing eight(8) features, which were reduced to two (2) using decision tree. The selected features were further utilized to develop bots classification systems. Comparative analysis of the results showed that Random forest classifier recorded best performance when evaluated on training set, while the Logistic recorded highest performance in terms of accuracy, precision, and F1 Score achieving 83%, 78%, and 81%, respectively when evaluated on test set. The classification systems can help identify and mitigate the impact of harmful bots on Twitter, such as those used for spamming or disseminating fake news. The study has demonstrated the effectiveness of machine learning algorithms in classifying Twitter bots and provided a potential solution for improving online social media platforms.