Experience

Research Assistant

Developing AI-based, non-invasive disease screening methods for low-resource settings.

Research Assistant (remote)

Contributed to a project on sustainable agriculture in Saudi Arabia by reviewing literature on climate change impacts and precision agriculture, curating datasets from the FAO and the World Bank, and supporting machine-learning model development.

Undergraduate Researcher

Thesis: DiabSense: Early Diagnosis of Non-insulin-dependent Diabetes Mellitus using Smartphone based Human Activity Recognition and Diabetic Retinopathy Analysis with Graph Neural Network.

• Proposed a system that prompts type 2 diabetic patients to undergo early clinical diagnosis.
• Developed, fine-tuned, and assessed a Graph Convolutional Network (Vision GNN) and a CNN-based model (EfficientNet-B5) to grade the severity of Diabetic Retinopathy (DR) from fundus images.
• Leveraged passive sensing data from smartphone accelerometer for Human Activity Recognition (HAR) with a Graph Attention Network and fused HAR with DR grading into a unified framework.

Undergraduate Teaching Assistant