I build signal-processing and machine-learning systems for messy biological data: EEG state-space models, voltage-imaging event detection, and the research software that keeps experiments honest. I am a Ph.D. student in Electrical and Computer Engineering at the University of Florida.
The highest-signal project pages that explain what I am building and why it matters.
A proposal for a transformer alternative: use a learned radial geometry for local context, a finite bank of persistent supports for reusable structure, and a lightweight online readout for adaptation after distribution shift.
Pipeline that maps noisy multichannel time-series observations to compact latent trajectories with a Hierarchical Linear Dynamical System (HLDS), then evaluates those trajectories for classification, separability, and stability.
Pipeline for 2D voltage imaging videos that flags ‘events’ (fast, localized changes) using statistical detectors inspired by radar signal processing, producing maps and summaries for downstream analysis.
Reusable experiment scaffolding for time-series ML: standardized configs, runs, metrics, and plots so model comparisons are fair and repeatable.
Standalone projects with their own public homes, separate from the research archive.
A training console for athletes and coaches: programs, diet tracking, progress reports, and coach review in one place.
A practice platform for STEM students built to find the exact idea you missed: attempt a problem, get targeted feedback, repair the gap, and prove it in a new context.
EEG work gets more informative when temporal structure is part of the model instead of something the pipeline averages away.
Papers, citations, code, and the official University of Florida references for this work.
