A package for processing signals recorded using wearable sensors, such as Electrocardiogram (ECG), Photoplethysmogram (PPG), Electrodermal activity (EDA) and 3-axis acceleration (ACC).

Systole: A python package for cardiac signal synchrony and analysis

The model and the code of The China Physiological Signal Challenge 2018 champion

Self-contained Jupyter notebook that walks through loading raw ECG, designing digital filters, visualising spectra, cleaning noise and extracting heart-rate features—perfect for teaching bio-signal processing.

Matlab GUI to load, plot, analyze and filter real ECG signal and model your own ECG.

Familiarization with Higher Order Statistics (Spectra) and ARMA (Autoregressive Moving Average) models. Time Frequency Analysis techniques (Short Time Fourier, Hilbert-Huang and Wavelet Transform) are implemented in ECG signals.

Candy size Electrocardiography BioAmp sensor from Upside Down Labs!

Electrocardiogram Viewer for Holter Monitors

A deep learning library for XAI-ECG analysis

A Method to Improve Any ECG Denoising Technique In limb leads

PerHealth'21 - PulSync: The Heart Rate Variability as a Unique Fingerprint for the Alignment of Sensor Data Across Multiple Wearable Devices

AI-based heart rate variability analysis from ECG and mobile PPG — research project published in TASK Quarterly 2026.

Master's thesis - Assessment of cognitive load in extreme environment

Signal processing toolbox for cardiac potential recordings.

ECG Data-Set and Sample Code

Interpretable Block-Term Tensor Network (BTTN) for predicting future-onset (incident) atrial fibrillation from a single sinus-rhythm 12-lead ECG on MIMIC-IV-ECG: the glass-box (time x lead) factor parameters ARE the explanation, with a measured-faithfulness framework, at parity with a CNN. Patient-grouped CV, patient-bootstrap CIs.

Android application with a simple GUI that can be able to connect to a Bluetooth Low Energy device. The goal is to receive data from an ECG sensor, apply a filter and visualize the Electrocardiogram.

Chance-corrected benchmark of ECG representations (raw, autoencoder, hand-crafted, foundation models) for unsupervised arrhythmia clustering on PTB-XL and MIT-BIH, with a supervised ceiling and deployment-robustness (imbalance, federation) analysis.

Neural Network Lecture Projects.

HumanVector turns biological age from one number into a directional state space: controlled ECG perturbations, external transport, and a cross-scale evidence atlas.