An intelligent IoT solution that provides continuous cardiovascular monitoring for diabetic patients through non-invasive sensors. The system combines hardware sensors, real-time data processing, and machine learning analytics to detect anomalies and track vital sign trends.
- Multi-sensor integration (ECG, Temperature, Heart Rate, SpO2)
- Real-time vital signs monitoring and visualisation
- Machine Learning-powered analysis:
- Anomaly detection using Isolation Forest
- Trend analysis with Exponential Smoothing
- Health state classification using Random Forest
- Secure data storage with MongoDB
- Interactive web dashboard built with Streamlit
- Dual-controller system (Arduino + Raspberry Pi)
- Python-based data processing and analysis
- Web-based visualisation and monitoring interface
- Secure data transmission and storage
- Hardware: Arduino, Raspberry Pi, MAX30102, GY-906, ECG sensors
- Backend: Python, MongoDB
- Frontend: Streamlit
- ML Libraries: scikit-learn, numpy, pandas
Click on the thumbnail below to view the Application Demonstration video
Click on the thumbnail below to view the Oxisensor Testing demonstration video
Click on the thumbnail below to view the Tempsensor Testing demonstration video
Click on the thumbnail below to view the Unfiltered ECG demonstration video
Click on the thumbnail below to view the Arduino ECG demonstration video
