Mobeen Mehdi

Thesis Summary:

• Leveraged the Cleveland dataset to conduct a comprehensive analysis of feature selection techniques in cardiovascular heart disease prediction.
• Applied ensemble learning techniques, specifically bagging models, to enhance predictive accuracy and robustness of cardiovascular risk prediction models.
• Employed machine learning algorithms to evaluate and compare the effectiveness of feature subsets in predicting cardiovascular heart diseases, using metrics like AUC-ROC and calibration plots.
• Investigated the interpretability and clinical relevance of selected features to refine predictive models and improve understanding of cardiovascular risk factors.
• Advanced research contributing to the optimization of healthcare diagnostics through rigorous validation and integration of bagging models in predictive analytics for cardiovascular health assessment.
• Proposed implications for future research, emphasizing the potential of ensemble learning in personalized medicine and healthcare decision support systems.

• Professional Development Studies: Big Data, 2020

• Final Year Project
• Collaborated in a team of two to develop a mobile application prototype similar to Food Panda, focusing on food ordering and delivery services.
• Designed and implemented an intuitive user interface and interactive user experience (UI/UX) to facilitate seamless browsing, ordering, and payment functionalities.
• Developed backend server-side logic using modern frameworks to manage user accounts, restaurant listings, and order processing.
• Integrated real-time order tracking and notifications to enhance customer satisfaction and operational efficiency for delivery partners.
• Conducted usability testing and gathered feedback as a team to iteratively improve application features, ensuring optimal performance and user engagement.
• Presented joint findings and recommendations for future enhancements, emphasizing scalability and market competitiveness in the food delivery sector.