Research Assistant
CurrentTasked with the development, assessment, and utilization of advanced statistical machine learning methodologies to decipher intricate patterns from vast and varied data collections. I tapped into both conventional and emergent techniques spanning supervised, unsupervised, and deep learning realms to tackle intricate problems such as data categorization, outlier detection, and prediction. I also played a pivotal role in partnering with software developers to introduce state-of-the-art solutions to our operational environment while maintaining close coordination with division leaders.Key Responsibilities:• Engineered and upheld software frameworks that catered to a broad spectrum of analytical needs, encompassing data acquisition, transformation, advanced machine learning, and statistical evaluations.• Spearheaded innovative investigations into statistical machine learning methodologies, revealing concealed correlations within extensive and multifaceted data sources.• Employed avant-garde models and the latest research insights, harnessing concurrent and parallel algorithms to navigate the intricate challenges at the vanguard of the machine learning field.Achievements:• Published seven research projects at international conferences, showcasing expertise in convolutional neural networks, vision transformers, and recurrent neural networks for applications in computer vision, robotics, and automation at IEEE and SPIE.• SPIE DCS 2023 - Best Student Paper award (First Author) "Enhancing Ethical Data Partitioning with L1-norm Principal Component Analysis."• IEEE Metrocon 2022 - Graduate Student Poster Competition - 1st place - “Improved Neural Network Arrhythmia Classification Through Integrated Data Augmentation”Courses TA:Engineering Tools - Fall 2023Electromagnetics - Fall 2024
