R Package: eegwhiten
R package for whitening EEG channels or feature matrices with reusable models, diagnostics, cross-session recentering, and Riemannian tangent-space helpers.
Milestone: Mar 2022
Portfolio
EEG / BCI software ecosystem
Most of these projects grew out of the same practical problem: EEG/BCI models are easy to train on one session and hard to trust on the next one. I started by building tools for stable signal representations, then added methods for aligning shifted sessions, then built benchmark runners and dashboards to see when adaptation helps and when recalibration is still needed. The simulation and visualization tools support the same story from the other side: stress-test the geometry, explain the methods, and make the failure modes easier to inspect.
When a tool has both R and Python versions, I group it here by the problem it solves and leave implementation details to the project pages.
01
Build stable representations
Whitening and feature-extraction tools that make EEG trials comparable before classification or transfer.
R Package: BCIFeatR
R toolkit for train/test-safe EEG feature extraction across spatial-filter, covariance, spectral, dynamical, and avalanche feature families.
Milestone: May 2023
02
Adapt across sessions
Domain-adaptation libraries and experiment runners for moving from one session to another without pretending the data are stationary.
R Package: DA4BCI
R toolkit for aligning EEG feature distributions across sessions or subjects and evaluating source-target shift before and after adaptation.
Milestone: Nov 2022
Python Package: DA4BCI-Python
Python backend for EEG/BCI domain adaptation, shift metrics, SPD geometry, preprocessing, and drift detection.
Milestone: May 2024
Python Package: CrossDA
Python package and CLI for running cross-session EEG domain-adaptation experiments across multiple source-session utilization strategies.
Milestone: Apr 2025
03
Compare and diagnose results
Dashboards that turn cross-session benchmark output into source-selection, adaptation, and recalibration decisions.
Web App: MSDA-Bench
Interactive benchmark dashboard for comparing source-session utilization strategies across MAP, DWP, MMP, and BDP pipelines.
Milestone: Oct 2025
Web App: ShiftDx
Streamlit dashboard for MI-EEG drift diagnostics across multiple shift metrics, DA methods, feature families, and fixed-reference monitoring protocols.
Milestone: Mar 2026
04
Stress-test and explain methods
Simulation and visual-explanation tools for checking covariance geometry, augmentation safety, and method intuition.
R Package: TensorEEG
R package for synthetic EEG tensor simulation, SPD covariance augmentation, fidelity auditing, and manifest-based replay.
Milestone: Dec 2023
Python Package: TensorEEG-py
Python package mirroring TensorEEG's simulation, augmentation, SPD geometry, fidelity audit, and manifest replay APIs.
Milestone: Nov 2024
Web App: ShiftLens
Static browser app for teaching and inspecting domain-adaptation geometry with 2-D toy data, method animations, metrics, and export tools.
Milestone: Jun 2026
+
Other technical builds
Selected applied or exploratory projects outside the main EEG/BCI software chain.
Desktop App: NeuroStream
Desktop app for sample-paced BCI replay with four motor-imagery pipelines, Euclidean Alignment, and live inference visualization.
Kaggle Silver Medal: HMS - Harmful Brain Activity Classification
Rank: 98/2767 (Top 4%) | Silver Medal Developed a deep learning pipeline using EfficientNet and Weighted Ensembling to classify seizures and harmful brain patterns from EEG signals.