Projects

Published a paper using Random Forest and XGBoost to predict heart attacks. Integrated Explainable AI methods to enhance transparency and clinical interpretability.

Proposed a hyperparameter tuning method combining Multi-Information Source Optimization and Augmented Gaussian Processes to reduce resource usage by up to 70%.

An upcoming journal paper exploring novel classification methods for ecological datasets using image processing and ML, supporting biodiversity conservation.

Developed a React-based task management app with features like calendars, Kanban boards, and real-time syncing to boost productivity.

This paper explores how data science and machine learning can streamline supply chain operations, from inventory forecasting to delivery routing.

This research utilizes the Framingham dataset to model cardiovascular disease risk using statistical methods and ML, aiming to improve prevention strategies.