mbwebster/self-supervised-bss-via-multi-encoder-ae
Official repository for "Blind Source Separation of Single-Channel Mixtures via Multi-Encoder Autoencoders".
This project helps scientists and bio-signal analysts separate mixed signals from single-channel recordings. For instance, if you have a single ECG signal containing both heart activity and respiration, this tool takes that mixed signal and outputs the individual, isolated source signals like pure heart activity and pure respiration. It's designed for researchers and practitioners working with biological or physical signal processing where multiple underlying signals are combined into one observed measurement.
Use this if you need to extract distinct, underlying source signals from a single-channel recording where multiple signals are intertwined.
Not ideal if your signals are already perfectly clean and isolated, or if you have multiple recording channels for each individual source.
Stars
18
Forks
3
Language
Jupyter Notebook
License
MIT
Category
Last pushed
Dec 13, 2025
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/mbwebster/self-supervised-bss-via-multi-encoder-ae"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
mne-tools/mne-python
MNE: Magnetoencephalography (MEG) and Electroencephalography (EEG) in Python
braindecode/braindecode
Deep learning software to decode EEG, ECG or MEG signals
NeuroTechX/moabb
Mother of All BCI Benchmarks
neuromodulation/py_neuromodulation
Real-time analysis of intracranial neurophysiology recordings.
IoBT-VISTEC/MIN2Net
End-to-End Multi-Task Learning for Subject-Independent Motor Imagery EEG Classification (IEEE...