http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/103 2026-05-05T09:02:24Z 2026-05-05T09:02:24Z Muhammad, Idris Oluwaseun, Adeniyi Ojerinde Muhammad, Muhammed Kudu http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30583 2026-04-23T17:00:27Z 2025-10-01T00:00:00Z

Title: PRIVACY-CENTRIC SELF-SOVEREIGN IDENTITY FRAMEWORK DESIGN FOR PUBLIC BLOCKCHAINS Authors: Muhammad, Idris; Oluwaseun, Adeniyi Ojerinde; Muhammad, Muhammed Kudu Abstract: Identity management has evolved over time, yet centralized and federated models remain vulnerable to large-scale data breaches and privacy concern. This paper presented a privacy- centric Self-Sovereign Identity (SSI) framework for public blockchains that incorporates advanced cryptographic method, such as ephemeral Decentralized Identifiers (DIDs), BBS+ selective disclosure signatures, and accumulator-based revocation. The framework was designed and evaluated using a Design Science Research (DSR) methodology, it encompassing architectural design, prototype implementation, and performance testing on the Ethereum testnet. With a slight performance overhead of 10–15% in latency and throughput, experimental results show an 80% reduction in linkability risk when compared to baseline SSI models. These results demonstrate that blockchain-based identity systems can successfully balance privacy, scalability, and usability. The study contributes a deployable, empirically validated architecture that advances privacy-by- design principles for next-generation digital identity infrastructures.

2025-10-01T00:00:00Z Dodo, Simon Numduck Muhammad, Muhammad Kudu Sulaimon, Adebayo Bashir http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30272 2026-03-01T12:52:35Z 2025-12-01T00:00:00Z

Title: Severity Prediction Scheme for Temporal Dependency Learning in Traffic Accidents Authors: Dodo, Simon Numduck; Muhammad, Muhammad Kudu; Sulaimon, Adebayo Bashir Abstract: This study presents a novel hybrid deep learning framework, Distil-BERT-CNN, designed to optimize spatial pattern extraction and temporal dependency learning for predicting traffic accident severity. However, this hybridization is achieved by integrating the lightweight, attention-based Distil- BERT model for efficient sequence processing with Convolutional Neural Networks (CNN) for robust spatial feature extraction, the proposed approach addresses the limitations of traditional statistical and machine learning models, which often struggle with class imbalance and complex, nonlinear relationships in real-world traffic data. Extensive experiments on multi-source datasets, including historical accident records, real-time traffic flow, and weather data, demonstrate that Distil-BERT-CNN significantly improves precision and recall, particularly for minority accident severity classes, compared to existing methods such as Random Forest, Gradient Boosting, LSTM, and cascade deep learning models. The enhanced predictive performance of this framework has the potential to support traffic management authorities in proactive accident prevention, resource optimization, and rapid emergency response, ultimately contributing to safer and more efficient transportation systems.

2025-12-01T00:00:00Z ANWO, Abdulmalik Olayinka GANA, Celina Shitna HASSAN, Ahmed Ahmed MOSES, Abiodun Stephen BASHIR, Ahmad Usman MUHAMMAD, Muhammad Kudu http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30163 2025-11-16T06:28:38Z 2025-05-01T00:00:00Z

Title: Revolutionizing Physics Education: Leveraging Vee-Diagrams for Improved Secondary School Students’ Achievement and Retention Authors: ANWO, Abdulmalik Olayinka; GANA, Celina Shitna; HASSAN, Ahmed Ahmed; MOSES, Abiodun Stephen; BASHIR, Ahmad Usman; MUHAMMAD, Muhammad Kudu Abstract: This paper explores the integration of Vee-diagrams into physics education as a transformative approach to enhance secondary school students’ achievement and retention. Traditional teaching methods often leave students with superficial knowledge and misconceptions regarding fundamental concepts in physics. Vee-diagrams serve as visual tools that help students organize their thoughts, clarify relationships between concepts, and foster a deeper understanding of physics principles. By promoting active, reflective learning, Vee-diagrams align with constructivist theories and the Ausubel-Novak theory of meaningful learning, encouraging students to connect new information with prior knowledge. Empirical research and case studies demonstrate the effectiveness of Vee-diagrams in improving academic performance, conceptual understanding, and retention of knowledge. Various studies reveal significant increases in student achievement, with some reporting up to 30% improvement in understanding complex topics. Furthermore, Vee-diagrams address common misconceptions and enhance student engagement, with a majority of students expressing increased motivation when using these tools. Despite concerns regarding implementation complexity and varying benefits for different learning styles, the advantages of Vee-diagrams in fostering critical thinking and real-world problem-solving skills outweigh these challenges. This paper argues for the broader adoption of Vee-diagrams in physics curricula, emphasizing their potential to cultivate scientifically literate individuals prepared to navigate and contribute to an increasingly complex world.

2025-05-01T00:00:00Z Yusuf, Ayuba Enesi, Femi Aminu Muhammad, Muhammed Kudu http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30160 2025-11-12T08:14:01Z 2025-04-09T00:00:00Z

Title: A Framework for Optimized Diabetes Detection Model Based on Binary Butterfly and Machine Learning Algorithms Authors: Yusuf, Ayuba; Enesi, Femi Aminu; Muhammad, Muhammed Kudu Abstract: Diabetes has become a major cause of death in both developed and developing countries, affecting a large number of people globally. prompting significant investments in research to find a cure for this critical disease. Traditional approaches reliant on diabetes detection are time-consuming, this necessitates a paradigm shift towards more efficient methodologies. In response, this study introduces a conceptual framework for diabetes detection by leveraging the power of optimized machine learning algorithms. Addressing data preprocessing techniques and optimized feature selection algorithms, and machine learning algorithms, specifically Random forest, multilayer perceptron, and Gradient boosting model, the result shows that Random forest emerges as the potent model showcasing a remarkable performance metrics: accuracy score of 97.66%, F1-score of 97.56%, AUC-ROC of 98.54%, Multilayer perceptron achieved an accuracy of 96.10%, F1-score of 95.96%, AUC-ROC of 98.65% Gradient boost achieved and accuracy of 91.82%, F1-score of 91.49% and AUC-ROC of 98.01% respectively. These findings underscore the significant role of feature selection and machine learning in detecting diabetes offering transformative possibilities for global healthcare enhancement.

2025-04-09T00:00:00Z