BCI Research Scientist · Neural Signal ML Engineer

Reliable EEG decoding under session drift.

I build statistical methods and scientific software to measure EEG session drift, select transferable source data, and evaluate when adaptation or recalibration is warranted. I completed my Ph.D. in Computational Science at UMass Boston in August 2026.

Download BCI Resume Email Yiming View BCI Projects
Boston, MA · Open to relocate · Available immediately Target roles: BCI Research Scientist · Neural Signal ML Engineer
  • Motor-Imagery EEG
  • Cross-Session Transfer
  • Drift Diagnostics
  • Domain Adaptation
  • Python / R

Selected Evidence

Research, systems, recognition

Featured BCI Systems

Transfer, diagnose, replay

All BCI software

Cross-session DA experiment runner

CrossDA

Python package and CLI for running cross-session EEG domain-adaptation experiments across multiple source-session utilization strategies.

Role: Python package developer

Evidence: CLI + Python API; MAP, DWP, MMP, and BDP; auditable summary, detail, and session-role outputs

Details GitHub

Drift diagnostics dashboard

ShiftDx

Streamlit dashboard for MI-EEG drift diagnostics across multiple shift metrics, DA methods, feature families, and fixed-reference monitoring protocols.

Role: Dashboard developer

Evidence: Five drift metrics; fixed-reference monitoring; no-DA, DA, and retraining comparisons

Details GitHub Live Demo

Pseudo-online BCI desktop app

NeuroStream

Desktop app for sample-paced BCI replay with four motor-imagery pipelines, Euclidean Alignment, and live inference visualization.

Role: Application developer

Evidence: Four MI pipelines; 0.5 s progressive checkpoints; sample-paced pseudo-online replay

Details GitHub

Selected Publications

Evidence behind the software

All research

  1. Accepted for publication · Aug 2026

    A Confidence-Gated Source Selection Strategy for Cross-Session Transfer in Brain-Computer Interfaces

    Yiming Shen and David Degras · Frontiers in Human Neuroscience - Brain-Computer Interfaces · Article 1895016 · doi:10.3389/fnhum.2026.1895016

  2. Under review · Solo author

    Small Calibration Cohorts Do Not Reliably Select Motor-Imagery EEG Systems for New Participants

    Cross-participant evaluation of complete MI-EEG system choices under final accuracy and execution cost.

  3. Ph.D. dissertation · UMass Boston · Aug 2026

    Motor Imagery EEG Decoding for Brain-Computer Interfaces: Structured Representation, Transfer, and Drift

    Representation, source-session transfer, drift measurement, adaptation, and recalibration as one reliability problem.

Experience

Research and data engineering

Sep 2019 - Aug 2026

Doctoral Researcher · UMass Boston

Cross-session EEG transfer, drift diagnostics, statistical validation, and reproducible Python/R research software.

Jul 2014 - Aug 2016

Data Engineer · China Mobile IoT

Time-series sensor data, MySQL performance, monitoring dashboards, and automated reporting.

Contact

BCI and neural-signal roles

I am available for research scientist and neural signal machine-learning roles focused on reliable decoding under distribution shift.

Email Yiming Download Resume LinkedIn