Bio-signal Analysis with Deep Learning
Pipeline illustration of real-time biosignal monitoring.Project Snapshot
Biosignals such as ECG and PPG carry critical information about cardiovascular health, fatigue, and stress. This project explored deep CNN/LSTM architectures that can ingest multi-channel biosignals, remove noise, and deliver actionable predictions in real time.
Deliverables
- Signal preprocessing scripts for wearable deployments
- CNN + bidirectional LSTM models tuned for arrhythmia classification, sleep staging, and stress detection
- Real-time health monitoring prototypes that stream predictions to clinician dashboards
Legacy
The techniques pioneered here now support many of BCML’s digital healthcare initiatives, from Nailfold Capillaroscopy analytics to remote patient monitoring platforms.
Description
Bio-signal is very important in health care area. So we analyze various bio-signal data such as ECG(electrocardiography), PPG(Photoplethysmography). We are studying and using deep learning to process bio-signal data well. Furthermore, We are working to develop real-time health monitoring technology.
Cheolsoo Park
Professor
His research interests include machine learning, adaptive signal processing, computational neuroscience, and wearable technology.