Winnipeg, Manitoba, Canada • 431-556-7336 • dod2@myumanitoba.ca
I’m a Data Science co‑op student at the University of Manitoba with experience in applied machine learning and computer vision. My current work focuses on medical machine learning and explainable AI as a student researcher at PASSIO Lab - North Carolina A&T State University, building on prior research experience in the Database and Data Mining Lab - University of Manitoba. I’m actively seeking co‑op opportunities for this fall.
Preprint: https://arxiv.org/abs/2603.11680
Preprint: https://arxiv.org/abs/2604.23385
Summer Co-op position assisting with plant science research. Responsibilities included data annotation, analysis, computer vision tasks for plant science applications, and general lab support.
Research in medical machine learning, with a particular emphasis on cardiology. Perform feature extraction from electrocardiogram (ECG) signals; apply feature selection, dimensionality reduction for visualization, classification, unsupervised clustering, disease phenotype modeling, explainable AI (XAI), self-supervised learning, and fine-tuning of ECG foundation models.
Researched on Breast Cancer Detection and LLM Quantization. Collaborated on two research projects (1) developed data pipelines and machine learning techniques for breast cancer detection using mammogram scans, and (2) explored large language model (LLM) quantization to improve memory efficiency and inference performance. Utilized PyTorch, albumentations, pydicom, C-based scripts for weight extraction, and deep learning architectures such as ResNet-50 and Vision Transformers (ViT).
Worked on Twake Calendar frontend tasks using TypeScript and joined meetings across teams (Java, JavaScript, DevOps, QA, and Mobile Flutter) to understand open-source product workflows.
Coursework and research focused on machine learning, data science, and applied computing/statistics.
Python, Java, R, C/C++, JavaScript, Shell Script, SQL, HTML/CSS, Markdown, LaTeX.
Git, Jupyter Notebooks, PyTorch, Optuna, RAG, LangChain, Slurm, Microsoft Azure, Google Cloud Platform, Caddy Web Server, Tableau, RapidMiner, Microsoft Office.
PCA, t-SNE, Random Forest, SVM, KNN, K-Means, GMM, HDBSCAN, Neural Nets (MLPs, CNNs, Transformers).
Gradient Descent, Backtracking, Simulated Annealing, Genetic Algorithms, Constraint Programming.
Detail-oriented, efficient, adaptable, technical writing, eager to learn new technologies.