Electrocardiography
Beat-to-beat timing, robust R-peak detection on noisy ambulatory recordings and morphology features.
From raw sensor data to trustworthy physiology.
Raw sensor output is not physiology. We process multi-sensor data for clinical studies, device validation and digital health products, with signal quality as a first-class step.
What we deliver
Biosignal processing, end to end.
Photoplethysmography
Wrist and finger pulse signals, with quality assessment, motion-artifact handling and reconstruction of short noisy windows.
Electroencephalography
Cortical activity, including sleep-relevant spectral analysis.
Electrodermal activity
Sympathetic arousal, separated into tonic and phasic components.
Breathing rate and pattern
Often derived alongside cardiac signals, including from smartwatch PPG and accelerometry.
Movement and posture
Activity classification, posture and gait.
Open source
Tools our team wrote and maintains.
Our pipelines build on open-source Python libraries from our research group, so methods stay transparent and reproducible.
GitHub
E2E-PPG
End-to-end PPG pipeline: quality assessment, motion-artifact handling, reconstruction, peak detection and HR/HRV extraction.
GitHubpyPPGqa
Deep learning PPG quality assessment for reliable heart rate and HRV.
GitHubecg2rr
LSTM-based ECG R-peak detection for robust RR-interval extraction from noisy recordings.
GitHubpyEDA
Electrodermal activity preprocessing and feature extraction, including tonic and phasic components.
How we analyze it
- Signal quality assessment that labels each segment reliable or unreliable
- Motion-artifact removal and reconstruction
- Deep learning peak detection that holds up at high artifact levels
- Feature extraction with reporting matched to recording length
What you receive
- Clean signals and quality labels
- Validated features and physiological parameters
- A transparent, reproducible pipeline built on our open-source tools
- Publication-ready methods and figures
Evidence
Selected peer-reviewed work by our team.
- Feli et al. End-to-end PPG processing pipeline for wearables: from quality assessment and motion artifacts removal to HR/HRV feature extraction. IEEE BIBM, 2023. doi:10.1109/BIBM58861.2023.10385998
- Kasaeyan Naeini et al. A deep learning-based PPG quality assessment approach for heart rate and heart rate variability. ACM Transactions on Computing for Healthcare, 2023. doi:10.1145/3616019
- Feli et al. An energy-efficient semi-supervised approach for on-device photoplethysmogram signal quality assessment. Smart Health, 2023. doi:10.1016/j.smhl.2023.100390
- Afandizadeh Zargari et al. An accurate non-accelerometer-based PPG motion artifact removal technique using CycleGAN. ACM Transactions on Computing for Healthcare, 2023. doi:10.1145/3563949
- Feli et al. Multitask learning approach for PPG applications: case studies on signal quality assessment and physiological parameters estimation. Computers in Biology and Medicine, 2025. doi:10.1016/j.compbiomed.2025.109798
- Laitala et al. Robust ECG R-peak detection using LSTM. ACM SAC, 2020. doi:10.1145/3341105.3373945
- Kazemi et al. Respiration rate estimation via smartwatch-based photoplethysmography and accelerometer data: a transfer learning approach. Proc. ACM IMWUT, 2025. doi:10.1145/3712280
- Aqajari et al. pyEDA: an open-source Python toolkit for pre-processing and feature extraction of electrodermal activity. Procedia Computer Science, 2021. doi:10.1016/j.procs.2021.03.021
Read more on our blog: Biosignal processing at Centralive.