-Extracted and processed 6,000 frames of image data-Tested and compared various deep learning models using metrics such as F1 score, precision and recall-Used computer vision model YOLOV9 for object detection and classification-Used depth estimation model DPT to calculate relative distances between objects-Developed automated data pipeline between YOLOV9 and DPT- Coordinating with research team on weekly goals, presentations and composition of final research paper

- Initiated and led sales analysis project at local family-owned restaurant - Extracted and combined datasets from various service providers (Grubhub, DoorDash, Square) to facilitate detailed analysis - Coordinated with service providers to resolve data discrepancies and obtain missing data - Utilized Jupyter Notebooks and Pandas to combine, clean, and transform raw data into a set of 13,902 total sales - Leveraged Matplotlib to create histograms, line plots, and pie charts visualizing 9 months of sales data - Identified and compiled key statistics (such as total sales, peak sales times, and most lucrative service providers) in a comprehensive report, which was presented and interpreted to stakeholders - Proposed a strategy to reduce annual losses by $70,000, increasing efficiency and availability of manager

-Studied Python simulation of Bose-Einstein condensate-Learned about optical elements, circuit software, and circuit diagrams in order to analyze a laser power lockbox