Research
Wearable ECG AI
Research-oriented work on continuous ECG analysis with machine learning models that are feasible to run at the edge.
- Stack
- Python
- Machine Learning
- Signal Processing
- Edge AI
This case study is a work in progress. The overview below is accurate; architecture details, implementation notes and results will be added once they’ve been written up and verified.
Overview
Wearable ECG AI is a research-oriented project on analysing continuous ECG signals with machine learning, with a specific constraint: the approach should be feasible on edge hardware such as a wearable device, rather than depending on a large model in the cloud.
Research focus
- Continuous signals — working with long-running ECG streams rather than short, clean clips
- Signal processing — preparing raw signals before any model sees them
- Edge feasibility — treating model size and compute cost as design constraints from the start
This is research work, not a medical product, and it makes no clinical claims.