Ardalan Askarian
Building intelligent systems at the intersection of AI and healthcare
M.Sc. Student in Applied Machine Learning | Software Engineer | Computer Vision Researcher
About Me
M.Sc. Student researching Computer Vision & Image Processing
I'm a Master's student at the University of Saskatchewan specializing in Applied Machine Learning, with a research focus on Computer Vision and Image Processing under Dr. Mark Eramian. I graduated with Honours in Computer Science (Software Engineering Option).
My research experience includes conducting a user study with 36,407 interaction events on SIFT-assisted image annotation systems, and co-authoring research on human-AI collaboration. I've also led full-stack development at BEAP Lab, building a smartwatch data processing and analytics platform.
As a Teaching Assistant since 2023, I've mentored 100+ students across six core CS courses including Operating Systems. I'm passionate about building intelligent systems that bridge the gap between AI research and real-world applications.
Experience Timeline
NSERC-funded research on SIFT-assisted image annotation. Conducted user study with 36,407 interaction events.
Led full-stack development of BEAP Engine for smartwatch data processing and analytics.
Mentor 100+ students across 6 core CS courses including CMPT 332 Operating Systems.
Technical Skills
Languages
Frameworks & Technologies
ML & Computer Vision
Tools & Platforms
Focus Areas
Featured Projects
A selection of my recent work
Fine-Tuning LLMs for Automated Bug Classification
✅ DONE RESEARCHComprehensive research project investigating fine-tuned Large Language Models for automated bug classification. Manually labeled 1,552 GitHub bug reports across React, VS Code, Scikit-learn, and TensorFlow repositories. Achieved 94.54% accuracy with GraphCodeBERT, significantly outperforming traditional ML approaches.
Transformer-based models vs traditional ML for bug classification with 7 categories
GraphCodeBERT: 94.54%, CodeBERT: 93.99%, DistilBERT: 92.90% accuracy
Ardalan Askarian, Princess Tayab, Timofei Kabakov, Marmik Patel
SIFT-Assisted Image Annotation Research
✅ NSERC USRAResearch conducted under Dr. Mark Eramian evaluating a Django-based annotation platform combining Scale-Invariant Feature Transform (SIFT) with human oversight. Conducted user study with 6 participants analyzing 36,407 interaction events to quantify AI suggestion impact on annotation workflows.
AI assistance increased annotation time by 71.6% without improving IoU or GTC quality metrics
Django, Python, SIFT, JavaScript, OpenCV
Ardalan Askarian, Dr. Mark Eramian - Imaging & AI Lab
Weather App
A native iOS weather application built with Swift, featuring real-time weather data integration and a clean, intuitive user interface following Apple's design guidelines.
Dentistry Website
A professional dental clinic website featuring appointment booking, service details, and integrated Google Maps. Clean design with focus on user experience.
Sports Scheduling App
Led front-end development for a team sport management app (CMPT 370) focusing on streamlined UX. Built with React Native, TypeScript, PostgreSQL, SQLite, and MongoDB using Agile/Scrum methodology.
Darkness Defenders
A tower-defense game developed in Unity where players defend their castle from invading forces. Features multiple enemy types, strategic tower placement, and progressively challenging gameplay mechanics.
Let's Work Together
Open to research collaborations and full-time opportunities
Email Me Directly
For research collaborations, project partnerships, and academic inquiries
Send Email