sdimi / Step2heart
🏋️ Extract generalizable physiological representations from sensor time-series data with self-supervision (code for CHIL 2021, NeurIPS-W 2020 papers)
☆18Updated last year
Alternatives and similar repositories for Step2heart:
Users that are interested in Step2heart are comparing it to the libraries listed below
- Contrastive Learning (SimCLR) for Human Activity Recognition☆74Updated 4 years ago
- Self-supervised learning for wearables using the UK-Biobank (>700,000 person-days)☆126Updated 6 months ago
- Improving Human Activity Recognition through Self-training with Unlabeled Data☆40Updated 3 years ago
- 💪 Predict lab-measured cardio fitness (VO2max) through wearables in free-living environments (code for Nature Digital Medicine '22 pape…☆21Updated last year
- COCOA: Cross Modality Contrastive Learning for Sensor Data☆25Updated 2 years ago
- [ICML 2021] Self-supervised pre-training of AI models on ECG data with CLOCS☆52Updated 2 years ago
- Generating ActiGraph Counts from Raw Acceleration Recorded by an Alternative Monitor☆30Updated 5 years ago
- ☆16Updated 2 years ago
- Implementations of various published works on self-supervised learning approaches to biosignal feature extraction.☆53Updated last year
- (ICLR'25) PaPaGei: Open Foundation Models for Optical Physiological Signals☆70Updated 2 months ago
- SiamAF: Learning Shared Information from ECG and PPG Signals for Robust Atrial Fibrillation Detection☆24Updated 11 months ago
- A Systematic Review: Self-Supervised Contrastive Learning for Medical Time Series☆27Updated 9 months ago
- CAPTURE-24: Human activity recognition with activity trackers☆36Updated 5 months ago
- A repository for unified analysis of accelerometer-based human activity recognition.☆36Updated 2 years ago
- ☆22Updated 2 years ago
- Encoding human activity by considering salient sensors and time points.☆40Updated 2 years ago
- ☆60Updated 2 years ago
- [Nature Communications 2021] Continual learning of AI models on ECG data with CLOPS☆20Updated 2 years ago
- ☆64Updated last year
- PhysioNet/Computing in Cardiology Challenges☆37Updated last month
- Source code for paper: UniTS: Short-Time Fourier Inspired Neural Networks for Sensory Time Series Classification☆20Updated 3 years ago
- Classify ECG signals into predefined categories based on heartbeat abnormality by transforming time series to images☆23Updated 4 years ago
- ECGDL: A framework for comparative study of databases and computational methods for arrhythmia detection from single-lead ECG☆17Updated last year
- Implementation of the InterpretTime framework☆45Updated 2 years ago
- Using self-supervised learning to extract features from PPG signals☆18Updated 2 years ago
- ActiveHARNet: Towards On-Device Deep Bayesian Active Learning for Human Activity Recognition☆12Updated 4 years ago
- Official implementation of our MICCAI 2022 paper "mulEEG: A Multi-View Representation Learning on EEG Signals"☆34Updated 2 years ago
- Code for our AAAI-2021 paper "Latent Independent Excitation for Generalizable Sensor-based Cross-Person Activity Recognition".☆38Updated 3 years ago
- Are you ready to FLIRT with your wearable data?☆72Updated last year
- Interpretable Pre-Trained Transformers for Heart Time-Series Data☆36Updated 5 months ago