http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/52 Computer Science Tue, 15 Sep 2026 04:23:14 GMT 2026-09-15T04:23:14Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31769 Title: An Ensemble Machine Learning Approach for Fake News Detection and Classification Using a Soft Voting Classifier Authors: Lasotte, Y, B.; Garba, E. J.; Malgwi, Y. M.; Buhari, M. A Abstract: Fake news has grown in popularity and spread as a result of increased insecurity, political events, and pandemics, among other things. This study used an ensemble machine learning technique to better predict fake news on social media based on the content of news articles. The proposed model used a soft voting classifier to aggregate four machine learning algorithms, namely, Naïve Bayes, Support Vector Machine (SVM), and Logistic Regression, for the classification of news articles as fake or real. GridSearchCV was used to fine-tune the algorithms to get the optimal results during the training process. A Kaggle dataset was used for the experiment; it was comprised of both false and true news. Performance evaluation metrics were used to measure the performance of the base learners and our proposed ensemble technique on the dataset. The results of our experiment show that the proposed ensemble approach produced the highest accuracy, precision, recall, and F1_score values of 93%, 94%, 92%, and 93%, respectively, on the dataset as compared to the individual learners. This approach may also be used in other classification techniques for spam detection, sentiment analysis, and prediction of loan eligibility, among other things. Tue, 01 Mar 2022 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31769 2022-03-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31768 Title: AN INVESTIGATION ON ADOPTION OF BLOCKCHAIN-BASED FERTILIZER DISTRIBUTION ECOSYSTEM IN NIGER STATE, NIGERIA Authors: Saliu, A. M.; Hashim, I. B.; Lasotte, Y. B.; Benjamin, A; Idris, M. K.; Muhammad, B. H. Abstract: This paper proposes the use of a blockchain based fertilizer distribution ecosystem in Niger State, Nigeria. The system addresses major challenges such as the prevalence of counterfeit fertilizers, high costs, and inefficiencies within the distribution network, faced by farmers. By leveraging blockchain's core attributes of transparency, traceability, efficiency and immutability, the system ensures that fertilizer products are genuine and easily verifiable throughout the supply chain. A survey was conducted to assess the awareness and readiness of key stakeholders, including farmers, distributors, and government officials, to adopt a blockchain solution. The survey administered to 100 participants (farmers, distributors, retailers, and government officials) revealed a response rate of 46%. Farmers constituted the majority of respondents (78.3%), followed by retailers and wholesalers (8.7% each), and government officials (4.3%). On the issue of counterfeit fertilizers, 32.6% rated it as extremely severe, while 47.8% identified high costs as extremely severe. Furthermore, 63% of respondents had prior knowledge of blockchain, and 76.1% indicated they were likely or very likely to adopt a blockchain-based fertilizer distribution system. The findings revealed strong interest of the stakeholders, particularly in the area of improving the fertilizer distribution process. This research paper concludes that the developed system, combined with active stakeholder participation and regulatory support, has the potential to significantly reduce the circulation of counterfeit fertilizers, reduce corruption and the cost of the products. Furthermore, the study emphasizes the need for education, pilot programs, and infrastructure to ensure successful system implementation and long-term sustainability. Sun, 01 Mar 2026 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31768 2026-03-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31767 Title: Development of a Secure Web-Based Crime Information Management System for Nigerian Campuses Authors: Lasotte, Y, B.; Elijah, M. G.; Lawal, O. L.; Abubakar, S. T.; Saidu, A. A.; Mohammed, I. K. Abstract: Effective security systems are a crucial concern for all stakeholders of global tertiary institutions, as they guarantee human safety and infrastructure protection. The continued use of manual crime reporting systems in many Nigerian institutions results in significant inefficiencies, such as delayed replies, weak record-keeping, and poor data analytics. While digital solutions exist, they often lack the integrated, campus-specific focus that is necessary. This study designs, develops, and evaluates a secure, web-based Crime Information Management System (CIMS) that integrates real-time reporting with multi-factor authentication, role-based access, and data analytics to address these challenges. The system was developed using Next.js, Node.js, and MongoDB. Multi-factor authentication and other advanced features ensure data security, and data analytics tools enable security personnel to identify patterns and efficiently allocate resources. A comprehensive evaluation was conducted over a four-week pilot with 10 users confirming the system's robustness. Performance benchmarking with Google Lighthouse yielded perfect scores of 100% in Performance and Best Practices, and a 96% score in Accessibility. Importantly, a security assessment using OWASP ZAP revealed no high-risk vulnerabilities, confirming the effectiveness of the basic security architecture. Medium and low-risk vulnerabilities identified were remediated. Usability testing with students and security personnel yielded a mean System Usability Scale (SUS) score of 77.5, signifying "good" usability. The findings confirm that the CIMS significantly enhances the efficiency, security, and usability of campus crime management compared to manual processes. While the results are promising, the study's limitations, such as its design as a single-campus pilot test with a limited duration, suggest that further multi-institutional and long-term studies are recommended before any broader national rollout. Mon, 01 Sep 2025 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31767 2025-09-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31766 Title: Comparison of Analytical Hierarchy Process and Fuzzy Analytical Hierarchy Process Models for E- Banking Websites Quality Evaluation Authors: Adepoju, S. A.; Shaba, C. D.; Lasotte, Y. B.; Ekundayo, A Abstract: The process of evaluating the quality of e-banking websites has gained rapid attention in recent years with the adoption of multi-criteria decision-making (MCDM) approaches. The Analytical Hierarchy Process (AHP) and the fuzzy AHP models which are well suited to determine the outcomes of the e-banking website quality evaluation are explored in this study. In both cases, the decision-making activity is broken into criteria and sub-criteria usually arranged as a pairwise comparison matrix layout. Though the latter is meant to be an advancement over the former, this paper compares the performances of the two MCDM approaches in evaluating e-banking websites of top-four Nigerian banks by profit margin. The data was collected from 33 out of 50 initially selected respondents using e-banking apps in Minna, Niger State through a non-random sampling technique. The outcome showed that the AHP and FAHP models are closely correlated based on the ranking of the weights of criteria and alternatives used in the study. Using the Wilcoxon Signed Rank Test, the Asymp Sig. (2-tailed) of criteria and sub-criteria is 0.500 for AHP and FAHP models indicating highly correlated decisions of the respondents. Also, the Wilcoxon Signed Rank Test (Asymp Sig. (2-tailed)) of alternatives is 1.000 for AHP and FAHP models indicating fairly correlated decisions on e-banking websites quality of alternatives (banks). However, the FAHP performances were superior to the AHP, which is consistent with some existing studies. Sun, 01 Jun 2025 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31766 2025-06-01T00:00:00Z