Developed an AI-powered, IoT-enabled health monitoring system designed to assist bedridden cardiomyopathy patients through continuous, real-time monitoring of heart activity, temperature, and vital signs.
Key Features & Contributions:
Integrated ECG, MAX30102, and MLX90614 sensors with an ESP-32 microcontroller for seamless data collection.
Implemented unsupervised machine learning models achieving 87% accuracy in detecting abnormalities and predicting myocardial infarctions up to 9 minutes in advance.
Designed a mobile dashboard and cloud connectivity (Firebase) for patients and doctors to review health data remotely.
Enabled automated medication reminders and potential integration with other health devices for comprehensive care.
Applied 3D printing for ergonomic device housing and ensured low-cost hardware implementation.
Impact:
This project advances Goal 3 of the UN SDGs – Good Health & Well-being, improving early detection, emergency response, and quality of life for cardiomyopathy patients through technology-driven healthcare solutions.
Technologies:
Biomedical Sensors, IoT, ICT, Unsupervised ML, C++, Cloud Computing, 3D Printing.