This role represents my Engineering Science undergraduate thesis project co-supervised by Prof. Deepa Kundur and Prof. Mohammad Al Janaideh. I published the paper "Multi-Head Attention Machine Learning for Fault Classification in Mixed Autonomous and Human-Driven Vehicle Platoons" at the 2023 IEEE International Conference on Robotics and Automation (ICRA) as the first author. I was able to travel to London in the summer to attend ICRA2023 in person and present my work as a conference research poster. To support my attendance, I was awarded a RAS Student Travel Grant valued at $1300.

Designed and implemented a data analysis and visualization tool that provides insights on service runtime logs. Leveraged Python, Scala, SQL, and TypeScript using various AWS technologies such as RedShift, EMR, and Lambda. Reduced theoretical time-to-resolution for a historical high-severity ticket from the scale of dev-hours to dev-minutes and identified a group of clients producing potential inefficiencies within the system.

Designed and deployed machine learning technologies to accelerate the IC design process for senior designers. Worked on an ML-based regression tool to predict parasitic capacitances during the schematic design phase, which was created with a PyQt user interface, supported by a Python and SQL backend, and natively integrates with Cadence Virtuoso CAD software. Tested and validated the tool's performance through iterative consultation with senior IC designers.

Co-authored research literature survey of over 700 published research articles in the field of computational pathology. Highlights recent trends with a taxonomy of papers and a comprehensive discussion on the future direction of the field. Published in "Journal of Pathology Informatics" as "Computational Pathology: A Survey Review and The Way Forward". See article at https://www.sciencedirect.com/science/article/pii/S2153353923001712?fbclid=IwAR3MpvVBFaZBBP-RstkF7PcTrO96tg9o2BdscnZHJo93tvqYXVNDc6Xk81g