BSpace

The British University in Dubai (BUiD) Digital Repository

Welcome to BSpace, the online institutional repository of the British University in Dubai. BSpace provides access to the Dissertations, Thesis, Research projects, Faculty publications and archives of BUiD.

Submit your dissertation/thesis by completing the registration using your BUiD email.

Review the submission guidelines before you submit the final version

Communities in DSpace

Select a community to browse its collections.

Now showing 1 - 7 of 7

Recent Submissions

  • Thumbnail Image
    Item type:Item,
    A Robust Hybrid Ensemble Framework for Anomaly Detection in Financial Transactions
    (The British University in Dubai (BUiD), 2026-02-17) Shanaa, Mohammad; Abdallah, Sherief
    Detecting fraudulent transactions in financial systems remains a critical challenge, owing to the highly imbalanced distribution of legitimate versus fraudulent activities and the continuously evolving sophistication of fraud strategies. Conventional supervised models, which are effective at learning known patterns, often struggle to identify rare anomalies, leading to low recall or increased false positives. Conversely, unsupervised methods, although capable of discovering novel patterns, frequently suffer from reduced precision and model instability. To address these limitations, this study proposes XRAI, which is a robust hybrid ensemble framework for anomaly detection in financial transactions. The framework integrates supervised learners (XGBoost and Random Forest) with unsupervised detectors (Autoencoder and Isolation Forest), combining their complementary strengths to enhance the overall detection capability. The outputs of these models were aggregated through an optimized weighted scoring and thresholding mechanism, ensuring a balance between sensitivity and specificity. Furthermore, explainable AI (XAI) techniques, specifically SHAP (SHapley Additive exPlanations), were employed to interpret model decisions, highlight influential features, and improve transparency for regulatory and operational auditability. Experimental evaluation using the creditcard.csv dataset demonstrated superior results, with a precision of 0.9569, recall of 0.9250, F1-score of 0.9407, MCC of 0.9407, and accuracy of 0.9998, outperforming the established benchmarks. The findings confirm XRAI’s capability to deliver a scalable, interpretable, and reproducible fraud detection framework adaptable to cross-domain anomaly detection applications and aligned with emerging AI governance and transparency requirements.
  • Thumbnail Image
    Item type:Item,
    Student Motivation Towards Learning English as a Second language (L2) in Selected Schools in Abu Dhabi: Students’ Perceptions and Teachers’ Roles
    (The British University in Dubai (BUiD), 2025-06) SULIMAN, WESAM FATHI NAZMI; Dr. Tendai, Charles
    This research targets to examine high school students’ perceptions of motivation in learning English as a second language (ESL) in Grades 10,11, and 12. The research also targets to examine demographic variations including age, gender, and proficiency levels in these perceptions, and explore both educators’ and students’ perspectives on motivation in English second language instruction and learning. To achieve the mentioned objectives, the research employs an explanatory sequential mixed-methods approach, incorporating both quantitative and qualitative methods. In the quantitative phase, 323 student participants have participated in the online questionnaire. The qualitative phase included 13 semi-structured interviews with students, and 8 interviews with teachers. Quantitative data were analysed in the Statistical Package for the Social Sciences (SPSS, version 27), employing descriptive statistics, Independent Samples T-Test for gender differences, and One-Way-ANOVA for grade differences with Games-Howell post-hoc comparisons. Cronbach's alpha was employed to assess reliability. Qualitative data were thematically analysed in MAXQDA, with member checking conducted after the interviews to enhance credibility. The findings revealed substantial motivational differences across different grade levels, with the highest motivational levels were observed among Grade 12 responses who showed high awareness about the value of English for their personal goals and future careers. On the other hand, affective factors were almost equal across all of the participating grade levels. In addition, the findings demonstrated that teachers’ constructive feedback, supportive learning environment, digital learning tools, and real-life strategies, affect students’ motivation positively. The overall conclusion from the integrated findings emphasised the significance of the supportive learning environment along with the use of instructional strategies suitable for each grade level in order to promote both instrumental and integrative motivation for learning English. Moreover, the researcher suggests many recommendations for key stakeholders involving educators, researchers, policy makers, and curriculum designers to promote English teaching by implementing well-tested approaches. The study also suggests implications that hopefully can be useful for teaching approaches, educational policy, and future research.
  • Thumbnail Image
    Item type:Item,
    The Project Manager Competencies Towards Effective Performance of AI Projects in the UAE Banking Sector
    (The British University in Dubai, 2024-12) ALZAABI, ALYA HASSAN ALI IBRHIM; Dr Khan, Muhammed Waris
    The use of artificial intelligence (AI) in the UAE banking sectors has created an urgent demand for project managers with specialised skills to lead these complex initiatives effectively. While AI adoption accelerates across UAE banks, a limited understanding of the specific skills and capabilities required for successful project implementation remains. The current research aims to investigate the relationship between defining project manager competencies and AI project success in UAE banking. The research employed a quantitative cross-sectional design, collecting data from 76 project managers across UAE banks through a structured questionnaire. Statistical analysis revealed strong relationships between project manager competencies and AI project success. Leadership abilities emerged as the strongest predictor (d = 0.782, p < 0.001), followed by technical skills (d = 0.724) and communication competencies (d = 0.698). Competencies explained 71.2% of the variance in stakeholder success (R² = 0.712). Organisational size significantly moderated competency-success relationships, with stronger effects in larger banks (effect size = 0.456). All hypothesised relationships demonstrated significant positive effects with good model fit indices (CFI = 0.942, RMSEA = 0.058). The study provides empirical evidence that project manager competencies significantly influence AI project outcomes in UAE banking. The key recommendations incorporate developing integrated competency frameworks, contextualising training programs based on organisational characteristics, implementing comprehensive assessment centres, and establishing mentoring programs. These findings have critical implications for banking institutions in selecting, developing, and supporting project managers leading AI initiatives. Keywords: project management, artificial intelligence, banking sector, UAE, competencies, project success
  • Thumbnail Image
    Item type:Item,
    A Dynamic Model Integrating Passenger Satisfaction Analytics and Pedestrian Simulation for Optimizing Metro Station Performance and Enhancing Passenger Experience
    (The British University in Dubai (BUiD), 2025-12) ALSALEEM, MOAMIN HAMEED; Prof Abu-Hijileh, Bassam
    This study develops a fully dynamic model to systematically assess metro station performance and passenger satisfaction, integrating the American Customer Satisfaction Index (ACSI) model with Structural Equation Modelling (SEM), Partial Least Squares (PLS) regression, and agent-based pedestrian simulation. A conceptual framework, consisting of 28 key indicators for SEM, refines passenger satisfaction indicators (PSI) through PLS regression to explore relationships between satisfaction drivers and metro performance. Importance-Performance Analysis (IPA) is also employed to identify key satisfaction factors. The research uniquely integrates SEM-PLS results with pedestrian simulation. ACSI SEM-PLS provides insights into passenger satisfaction, which are then used in ped simulation to predict the impact of projected ridership growth (3%, 5%, and 7% from 2030-2040) on station key performance indicators (KPIs). This combined approach offers a full understanding of passenger perceptions and operational dynamics. The study finds that current infrastructure will not support the anticipated ridership increase, leading to declines in station KPIs in efficiency (Space Density SD) and passenger experience (Passenger Density PS, Passenger Speed PS, Travel Time TT and Passenger Dissatisfaction Level PDL). To address these gapes, the study presents URBM model, which integrates improvements like expanded ticketing, improved circulation, and other strategies. These enhancements lead to significant gains across various KPIs metrics: SD improves by 44-56%, PD increases by 70-80%, PS rises by 53-70%, TT decreases by 11-16%, and PDL is reduced by 37-41%. The research contributes to knowledge by developing a KPI-driven framework that synthesizes satisfaction analytics with simulation modelling, thereby advancing methodological approaches in metro station design.
  • Thumbnail Image
    Item type:Item,
    Exploring User Experience (UX) Design organizational maturity
    (The British University in Dubai, 2018-12) ALSAWALQA, MOHAMMED; Dr Ncube, Cornelius
    Designing for the best user experience when people are interacting with the digital world had been evolving through the years as many different methods emerged helping users interact in the most pleasurable, efficient, useful, and meaningful way. Many organizations suffer from low profits and become largely unsuccessful due to neglecting user’s needs and in the competitive online platforms novel technologies are driving the user experience to new heights and with-it high gains in short periods of time. The developed markets have had UX methods well-established for a while and billion-dollar brands that is user-driven are evidence for the value UX design could add to the bottom line. In the aim to understand the roots of UX design and what backgrounds UX practitioners need to have, this research brings a brief account of the different disciplines that contributed to modern UX design methods and practices from ergonomics, human computer interaction, cognitive psychology, any many more. The main goal was to explore the UX profession which depends mainly on the designers and the construction of specialized UX teams in organizations. Labeling any organization as UX-mature drove the research to analyze the available UX maturity models and develop a tailor-made model based on the data gathered through two questionnaires and interviews with UX experts and several case studies showing the value of good UX design.