Skip to content
View DDFsco's full-sized avatar

Block or report DDFsco

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don’t include any personal information such as legal names or email addresses. Markdown is supported. This note will only be visible to you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DDFsco/README.md

Shuhao Cao — Neurotech Systems Engineer

I build real-time systems and AI pipelines for neuroscience research.

Currently at University of Michigan → Carnegie Mellon (Computational Biology, SCS). Two years embedded in neuroscience labs working on closed-loop neural systems, fMRI infrastructure, and ML for neural decoding.


What I Build

Real-Time Neural Systems Closed-loop VR for head-fixed rodents · sub-16ms feedback · <1ms timing jitter Hardware sync across electrophysiology, behavioral tracking, and stimulus delivery

Scientific Data Pipelines fMRI preprocessing at scale · 70% processing time reduction · CI/CD with DVC Reproducible neuroimaging workflows for cross-sectional and longitudinal cohorts

ML for Neural Data CNN brain-state decoder · 94% F1 on cortical surface activation maps SLEAP pose estimation · kinematic extraction across 100+ behavioral sessions


Projects

Project Description
RythMice Open-source behavioral analysis toolkit for rodent locomotion studies
FMRI-image-ML-classifier CNN decoder for cognitive state classification from fMRI cortical maps

Stack

Python C# (Unity) PyTorch MATLAB Docker GitHub Actions DVC AWS
fMRI / SPM / CONN SLEAP Biopac LabJack Linux


Contact

LinkedIn · echoc@andrew.cmu.edu

Pinned Loading

  1. FMRI-image-ML-classifier FMRI-image-ML-classifier Public

    Jupyter Notebook 1

  2. RythMice RythMice Public

    Wheel/treadmill analysis(CLI + GUI), click-train stimuli, and session plans for rodent locomotion rhythm studies (LabJack-compatible traces).

    Python 1