Browsing by Author "Babatunde, Akinbowale Nathaniel"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    An Enhanced Web-Based Examination System using Automated Proctoring and Background Activity Detection
    (Journal of Institutional Research, Big Data Analytics and Innovation (JIRBDAI.), 2025-08-20) Olanrewaju, Olaitan Toyyib; Isiaka, Mope Isiaka; Babatunde, Seyi Ronke; Jimoh, Muhammed Kamaldeen; Babatunde, Akinbowale Nathaniel
    The rise of online education demands sturdy systems to uphold academic integrity during remote assessments. This paper presents the design and implementation of a web-based examination platform integrated with automated, multi-modal proctoring tools to detect potential cheating. The system enables educators to create and manage diverse assessments while students’ complete exams in a monitored virtual environment. Key security measures include user authentication with facial recognition using the DeepFace library and continuous webcam analysis to detect mobile phone usage, unauthorized individuals, and unusual head or eye movements. Additional features include browser focus tracking to monitor navigation away from the exam window, and background audio analysis using Voice Activity Detection (VAD) and Root Mean Square (RMS) energy to flag suspicious sounds or conversations. Detected anomalies are logged in real-time for review. The prototype effectively combines visual, auditory, and behavioral monitoring into a cohesive framework, offering a comprehensive solution to reduce academic misconduct in remote settings. Functional testing showed 72% overall system accuracy and over 90%+ accuracy in specific detection modules. Future work should intend to enhance the system's AI capabilities, improve performance on models, and ensure fairness for all users, contributing to credible and secure digital learning environments across disciplines.
  • Thumbnail Image
    Item
    The Critical Role of Hyperparameter Tuning in Machine Learning: Implications for Reproducibility and Model Comparison
    (Technoscience Journal for Community Development in Africa, 2025-12-31) Isiaka, Mope Rafiu; Yusuf, Ronke Shakirat; Babatunde, Akinbowale Nathaniel; Mohammed, Babatunde Shuaib
    Despite being a fundamental aspect of machine learning model development, hyperparameter tuning remains underreported in the literature. This article highlights the importance of hyperparameter optimisation, outlines common hyperparameters across various algorithms, and discusses the consequences of inadequate hyperparameter documentation. We argue that the lack of transparency in hyperparameter settings impedes reproducibility, hinders fair model comparisons, and contributes to the hyperparameter deception. The importance of hyperparameter tuning in machine learning was demonstrated by comparing the performance of the decision tree, support vector machine and random forest models on Iris, Digits and Breast Cancer datasets using default and tuned hyperparameters. This further justifies the need to document and report the process and values of the hyperparameter settings used in the models. To facilitate this, an architecture that encourages the documentation of the hyperparameters has been proposed. By emphasising the need for comprehensive reporting, this study aims to raise awareness and encourage best practices in machine learning research.