AI-powered healthcare platform with ECG analysis, voice symptom collection, and doctor portal

An advanced ECG anomaly detection system using deep learning. This repository contains a CNN autoencoder trained on the PTBDB dataset to identify abnormal heart rhythms. It employs various loss functions for model optimization and provides comprehensive visualizations of the results.

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 Signal & Image Processing Lab Projects.

A production-grade deep learning framework for zero-shot ECG classification that achieves state-of-the-art generalization through morphology-rhythm disentanglement and efficient long-range sequence modeling with Mamba/SSM.

Zero-Shot ECG Generalization using Morphology-Rhythm Disentanglement and Mamba State Space Models. Features a production-ready Clinical Dashboard

A MATLAB-based ECG Emotion Recognition system using the DREAMER dataset. Performs preprocessing, R-peak detection, HRV feature extraction, FFT analysis, and percentile-based emotion classification.

A comprehensive healthcare data and medical image processing application for managing patient health data, analyzing biomedical signals, processing medical images, and creating interactive visualizations.

A desktop application for visualizing multi-channel biological signals (ECG, EMG, EEG). Built with PyQt5, it supports reading from CSV/MAT files, real-time playback simulation, and interactive signal manipulation.

Spectral analysis of ECG signals based on Fast Fourier Transform and Power Spectral Density

Interactive data visualization dashboard built with Dash and Plotly, featuring military equipment transfers, ECG signal analysis, healthcare documentation NLP, and military base mapping.

Newton–Puiseux for CVNNs: complete toolkit for uncertainty mining, confidence calibration and local symbolic-numeric analysis on ECG (MIT-BIH) and wireless IQ data (RadioML 2016.10A).

This project presents a system for automatic detection and segmentation of QRS complexes in ECG signals, combined with a mobile application for interactive cardiac analysis and reporting.

AI-Driven Cardiac Monitoring System for ECG analysis, heart rate variability, and arrhythmia detection using Flask, NeuroKit2, and Machine Learning.

ECG signal processing pipeline for Atrial Fibrillation detection and Heart Rate Variability (HRV) analysis using the MIT-BIH Atrial Fibrillation Database.

Heartbeat detection from ECG signals using filtering and R-peak analysis in MATLAB.

EKG Vision - A modern Flutter application for medical professionals to analyze ECG/EKG scans with AI-powered detection. Features secure doctor authentication, patient management, real-time ECG analysis, and a responsive UI with light/dark themes. Built with Flutter for cross-platform compatibility and Python Flask backend for robust data processing

📊 Build a multi-domain analytics dashboard with 50+ interactive visualizations combining military, biomedical, and healthcare data.

Non-invasive glucose monitoring using ECG signal analysis and machine learning for diabetes management research

A machine learning project leveraging ECG data to detect and classify cardiac arrhythmias. Features two models: a binary classifier for anomaly detection (Normal vs. Arrhythmia) and a multi-class classifier for specific arrhythmia types. Utilizes Random Forest, XGBoost, and other supervised algorithms with Boruta feature selection.