Web App: ShiftDx
Streamlit dashboard for MI-EEG drift diagnostics across 5 shift metrics, 10 DA methods, and fixed-reference cross-session monitoring.
Stack: Python, Streamlit, Plotly, pandas, statsmodels, scikit-learn, DA4BCI, CrossPython, MOABB
EEG/BCI Data Scientist · Computational Neuroscience · Scientific ML
Reliable EEG decoding under session drift.
I am a Ph.D. Candidate at UMass Boston working with Prof. David Degras. I develop statistical learning methods, domain adaptation workflows, and R/Python tools for nonstationary EEG and time-series data.
Open to Data Scientist, Research Scientist, and Computational Neuroscientist roles starting Summer 2026 Best fit: EEG/BCI, time-series modeling, computational neuroscience, domain adaptation, statistical learning, and scientific ML tooling.
EEG / BCI Time-Series Modeling Statistical Learning Domain Adaptation Drift Diagnostics R / Rcpp Python
Featured Software & Systems
Runnable work, not only paper abstracts
Python Package: DA4BCI
Python toolkit for EEG/BCI domain adaptation with 10 methods, shift metrics, visualization utilities, and matched benchmark support.
Stack: Python, NumPy, SciPy, scikit-learn-style workflows, EEG/BCI benchmarking
Desktop App: NeuroStream
Desktop app for sample-paced BCI replay with four motor-imagery pipelines, Euclidean Alignment, and live inference visualization.
Stack: Python, MOABB, pyriemann, MNE-Python, scikit-learn, tkinter, matplotlib
R Package: BCIFeatR
R toolkit for EEG feature engineering with 9 extraction methods, Riemannian utilities, and deterministic train/test transforms.
Stack: R, EEG feature extraction, Riemannian geometry, CSP/FBCSP, reproducible train/test APIs
Web App: MSDA-Bench
Streamlit dashboard for cross-session EEG domain-adaptation benchmarks, with 10 analysis views across 6 source-utilization pipelines.
Stack: Python, Streamlit, Plotly, pandas, NumPy, SciPy, cross-session EEG benchmarks
Research
Cross-session reliability in EEG decoding
I study why EEG pipelines fail across sessions and how to diagnose, benchmark, and adapt them without hand-wavy heuristics.
Methods
Drift diagnostics and adaptation decisions
My work links measurable distribution shift to practical choices about pooling, source selection, retraining, and feature recalibration.
Engineering
Reproducible scientific ML tooling
I build R and Python packages that make EEG feature extraction, domain adaptation, and benchmark auditing easier to rerun and inspect.
Research Program
Selected dissertation work
Cross-Session BCI Transfer: A Matched Comparison of Global and Selective Pooling
A matched comparison of global and selective source-session pooling strategies for cross-session EEG transfer.
Drift-Feature-Performance Decomposition in MI-EEG via Structured Geometric Modeling
A geometric framework for separating raw sensor drift from feature-space distortions in MI-EEG decoding.
Balancing Performance and Stability in Motor Imagery EEG Decoding: A Linear-First Approach
A linear-first decision rule for balancing MI-EEG decoding accuracy, stability, and computational cost.
Writing
Latest notes
Practical Guide: Distribution Distance Metrics for EEG Domain Adaptation
A practical note on Wasserstein, MMD, and Energy Distance for quantifying session-to-session shift in EEG pipelines.
From Matrix ICA to Tensor ICA: Architectures and Decomposition Choices
A concise bridge from classical ICA to multilinear/tensor ICA design choices.
ICA Objective Functions in One Place: Kurtosis, Negentropy, MI, and MLE
A compact map of the main ICA objective functions and their algorithmic implications.
Research Note: Markov-Switching State-Space Models for Neural Decoding
A working note on using regime-switching linear state-space models for non-invasive brain-signal decoding.
Project Archive
More technical builds
R Package: TensorEEG
R Package Developer A physics-constrained simulation engine for generating synthetic 3rd-order EEG tensors ($Time imes Sp...
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 cla...
R Package: DA4BCI
R Package Developer Implemented geometric data augmentation techniques on the Riemannian manifold to improve Motor Imagery...
R Package: eegwhiten
R Package Developer A comprehensive toolkit implementing various whitening transformations (PCA, ZCA, Cholesky) for EEG si...
Contact
Interested in reliable modeling for EEG, time-series, or scientific ML systems?
I am open to computational neuroscientist, research scientist, data scientist, and scientific ML roles where rigorous evaluation, EEG/BCI systems, and production-quality research tooling matter.