Browsing by Author "Muuro, Elizaphan"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Integrating Generative Artificial Intelligence in Assessment Generation for Higher Education: Computer Science Use Case
    (IST-Africa, 2025) Kituku, Benson; Araka, Eric; Muuro, Elizaphan
    The overburdened lecturers today face the dual challenge of monitoring online attendance and ensuring active student engagement, while also receiving instant feedback on concept comprehension during live lectures. They are further pressed to extend practical problem-solving experiences beyond the classroom and deliver higher-order thinking assessments - all without increasing their workload. In response, this paper presents a one-year experiment involving 590 students across seven computer science units. The study integrated generative AI-generated questions into live lectures, weekly discussion forums, and both formative and summative exams. The findings reveal that, with ethical use and proper human-inthe-loop, AI can significantly boost student engagement, promptly rectify misconceptions, and foster collaborative learning outside traditional settings and offer diverse question styles. However, given potential pitfalls such as low-quality outputs and overreliance, instructors must adhere to best practices and maintain rigorous oversight to ensure that assessments remain balanced, engaging, and of high quality, eventually benefiting both educators and learners.
  • Thumbnail Image
    Item
    K-Hyperparameter Tuning in High-Dimensional Space Clustering: Solving Smooth Elbow Challenges Using an Ensemble Based Technique of a Self-Adapting Autoencoder and Internal Validation Indexes
    (Tech Science Press, 2023-10-26) Gikera, Rufus; Mwaura, Jonathan; Muuro, Elizaphan; Mambo, Shadrack
    k-means is a popular clustering algorithmbecause of its simplicity and scalability to handle large datasets.However, one of its setbacks is the challenge of identifying the correct k-hyperparameter value. Tuning this value correctly is critical for building effective k-means models. The use of the traditional elbow method to help identify this value has a long-standing literature. However, when using this method with certain datasets, smooth curves may appear, making it challenging to identify the k-value due to its unclear nature.Onthe other hand, various internal validation indexes, which are proposed as a solution to this issue, may be inconsistent. Although various techniques for solving smooth elbow challenges exist, k-hyperparameter tuning in high-dimensional spaces still remains intractable and an open research issue. In this paper, we have first reviewed the existing techniques for solving smooth elbow challenges. The identified research gaps are then utilized in the development of the new technique. The new technique, referred to as the ensemble-based technique of a self-adapting autoencoder and internal validation indexes, is then validated in high-dimensional space clustering. The optimal k-value, tuned by this technique using a voting scheme, is a trade-off between the number of clusters visualized in the autoencoder’s latent space, k-value from the ensemble internal validation index score and one that generates a value of 0 or close to 0 on the derivative f ___ (k)(1+f _ (k)2)−3 f __ (k)2f __ ((k)2f _ (k), at the elbow. Experimental results based on theCochran’sQtest,ANOVA, andMcNemar’s score indicate a relativelygoodperformanceof thenewlydevelopedtechnique ink-hyperparameter tuning.