Curriculum Vitae

B.S. Mathematics and Computer Science

GPA 4.0

Gumbel-Based Active Sparse Mobile Crowd Sensing with Time Series Transformer

Ensemble Learning with Early Fusion of Kernel-Transformed and Classical Electrocardiogram Features for Chagas Disease Detection

Patched Forecasting with Gumbel-Based Selector for Sparse Mobile Crowd Sensing

Elk Preservation Application

• Architected and deployed the backend for a PERC wildlife webapp supporting elk conservation, with a PostgreSQL database for image metadata and cloud object storage for image assets (GCloud Run, Scheduler, Secrets, SQL, Storage).
• Integrated a Firebase-hosted React application with the backend API, enabling ranchers to upload wildlife photos.
• Fine-tuning a ViT classification model on pretrained YOLOv9 object detection to estimate elk counts from images, supporting fair compensation for elk-related land damages.

Child Care Quality Dataset

• Developed and cleaned a new AI/ML benchmark dataset of child care quality ratings, scraped via Playwright from the Georgia Department of Early Care and Learning.
• Developing a causal discovery graph via FPM and PC alongside a DiCE counterfactual framework to prune, identify, and rank key determinants of high-quality child care across 245 provider attributes.

Healthcare Reinforcement Learning Research

• Conducted an empirical study on the consistency of Set-Valued Policies and Dead-End Discovery frameworks for clinician-in-the-loop treatment recommendation.
• Designed and evaluated a partial ordering of recommended actions giving clinicians actionable recommendations for sepsis patients, evaluated on MIMIC-III.

Summer Oxford Research Scholars

• Developed a Learned Gumbel-Noise Active Sparse Mobile Crowd Sensing framework in PyTorch using a Time Series Transformer and a custom active sensor selection layer, reducing reconstruction error of missing sensor data by up to 28% against traditional Time Series Transformers.
• Published and presented a first-authored paper and poster at IPCCC '25.

ECG Classification Research

• Developed an ensemble learning framework via AutoGluon, ECG-FM, FFT, and Wavelet Transform for classification of 12-lead electrocardiograms.
• Placed 39th in the 2025 George B. Moody PhysioNet Challenge.
• Published and presented a first-authored paper at CinC '25.