Full-stack real-time EEG analytics and device-ready BCI research platform

This project is for Electrocardiogram(ECG) signal algorithms design and validation, include preprocessing, QRS-Complex detection, embedded system validation, ECG segmentation, label your machine learning dataset, and clinical trial...etc.

Atrial Fibrillation Detection Blood Pressure Monitor (Oscillometric Method)

This project is MAX3010x library for STM32F4

This project was completed in 2018 as a part of my postgraduate studies in Biomedical Engineering

Project to test the accuracy of multiple algorithms published in articles to the EEG binary motor imagery problem

ECG signal conditioning by Morphological Filtering - Biomedical Signal Processing project

Respiration-rate-and-heart-rate-detection is a project developed for the Biomedical Signal Processing exam at the University of Milan (academic year 2020-2021). It implements an algorithm to analyze accelerometric signals collected with a smartphone positioned on the thorax while supine.

MD-ViSCo: A Unified Model for Multi-Directional Vital Sign Waveform Conversion. IEEE JBHI 2026.

Exploring the relationship between PPG signals and Type 2 Diabetes.

This project uses Python to process electrocardiogram (ECG or EKG) signals and calculate heart rate (HR) through biomedical signal processing techniques. It includes noise filtering and R-peak detection for accurate HR analysis. The project features a user-friendly graphical interface to visualize ECG data and heart rate results.

It features tutorials on using the EEGLAB toolbox and MNE-Python, guiding users through the basics of EEG data handling, pre-processing, and artifact removal.

EEG-based emotion recognition with convolutional neural networks and hyperparameter optimization on the DEAP and SEED benchmarks.

Code for the paper "Removing Noise from Extracellular Neural Recordings Using Fully Convolutional Denoising Autoencoders"

KneeCare is a multi-modal AI and IoT platform for Knee Osteoarthritis (KOA) monitoring, combining X-ray KL grading with real-time wearable vibroarthrography (VAG) sensing for smart prediction and recovery tracking.

Codes from my MATLAB Digital Signal Processing course

Проект машинного обучения для анализа электрокардиограмм (ЭКГ) с использованием сиамских нейронных сетей для обучения с малым количеством примеров (few-shot learning). Этот проект реализует подход глубокого обучения для анализа сигналов ЭКГ и обнаружения сердечных аномалий.

Biomedical Image Analysis with TensorFlow and DLTK

WaveformNet is a deep learning project with 1D and 2D CNN models for classifying ECG signals into multiple arrhythmia types. The 1D model analyzes raw waveforms, while the 2D model processes transformed inputs, enabling a comparative approach to AI-based cardiac monitoring.