An intelligent IoT-based healthcare monitoring system that combines wearable sensors, machine learning, and mobile technology to detect falls in real-time and provide immediate emergency alerts. This comprehensive solution is designed to enhance safety for elderly individuals and people at risk of falls.
- Features
- System Architecture
- Components
- Project Status
- Technologies Used
- Installation
- Usage
- API Documentation
- Contributing
- Future Enhancements
- License
- Real-time Health Monitoring: Continuous tracking of heart rate, body temperature, and motion
- AI-Powered Fall Detection: Machine learning model trained on 370,000+ data points
- GPS Location Tracking: Precise location identification for emergency response
- Automated Alert System: Instant email notifications to emergency contacts
- Nearby Hospital Locator: Location-based identification of nearby healthcare facilities
- Health Data Translation: Gen AI-powered interpretation of health metrics
- Mobile Dashboard: Flutter-based mobile application for real-time monitoring
- Cloud Integration: Scalable cloud infrastructure for data processing
┌─────────────────┐ ┌──────────────┐ ┌─────────────────┐
│ Wrist Band │────│ ThingSpeak │────│ Cloud Backend │
│ (Sensors) │ │ Platform │ │ (ML + Alerts) │
└─────────────────┘ └──────────────┘ └─────────────────┘
│ │
│ ┌──────────────┐ │
└──────────────│ Flutter App │──────────────┘
│ (Mobile) │
└──────────────┘
Sensors Integrated:
- MAX30100: Heart rate and SpO2 sensor
- DS18B20: Digital temperature sensor
- MPU6050: 6-axis accelerometer and gyroscope
- Neo 6M GPS: Location tracking module
- NodeMCU (ESP8266): Main microcontroller
Data Pipeline:
- Real-time sensor data collection
- WiFi connectivity for data transmission
- Integration with ThingSpeak IoT platform
Model Specifications:
- Dataset Size: 370,000+ data points
- Classes: Fall vs Non-Fall detection
- Output Files:
model.pklandscaler.pkl - Accuracy: High precision binary classification
- Integration: Real-time processing of ThingSpeak data
Features:
- GPS coordinate processing
- Nearby hospital and healthcare center identification
- SMTP email alert system via Gmail
- Emergency contact notification
- Location-aware response system
Features:
- Advanced Gen AI integration for health data interpretation
- Health data translation and analysis
- BMI calculation and health insights
- User-friendly health metric explanations
- Personalized health recommendations
- Real-time health status assessment
Deployment Details:
- Platform: Render cloud deployment
- Services: ML model hosting, alert system backend
- API Endpoints: Real-time data processing
- Data Source: Live ThingSpeak integration
- Scalability: Auto-scaling cloud architecture
Features:
- User registration and profile management
- Real-time health dashboard
- Live sensor data visualization
- Fall detection status monitoring
- Heart rate charts and trends
- Gen AI health translations display
- Emergency contact management
- Intuitive user interface with real-time updates
| Component | Status | Progress |
|---|---|---|
| Hardware Wrist Band | ✅ Complete | 100% |
| ML Fall Detection | ✅ Complete | 100% |
| Alert System | ✅ Complete | 100% |
| Cloud Infrastructure | ✅ Complete | 100% |
| Gen AI Integration | ✅ Complete | 100% |
| Flutter Mobile App | ✅ Complete | 100% |
Overall Progress: 100% Complete (6/6 modules)
- ESP8266 (NodeMCU)
- MAX30100 Heart Rate Sensor
- DS18B20 Temperature Sensor
- MPU6050 Accelerometer/Gyroscope
- Neo 6M GPS Module
- Programming Languages: Python, C++ (Arduino), Dart (Flutter)
- IoT Platform: ThingSpeak
- Machine Learning: Python (Scikit-learn/TensorFlow)
- Cloud Platform: Render
- Mobile Framework: Flutter
- AI Integration: Gen AI API
- Communication: SMTP Gmail API
- Data Format: JSON, CSV
- Python 3.8+
- Arduino IDE
- Flutter SDK
- ThingSpeak account
- Gmail account for SMTP
- Render account for cloud deployment
- Connect all sensors to NodeMCU according to the wiring diagram
- Flash the Arduino code to NodeMCU
- Configure WiFi credentials and ThingSpeak API keys
- Assemble components into wristband housing
# Clone the repository
git clone https://github.com/Kunal70616c/Fall-Detection-and-Alert-System-Using-Body-Area-Network.git
cd Fall-Detection-and-Alert-System-Using-Body-Area-Network
# Install Python dependencies
pip install -r requirements.txt
# Configure environment variables
cp .env.example .env
# Edit .env with your API keys and credentials- Deploy ML model and alert system to Render
- Configure ThingSpeak channel integration
- Set up SMTP email credentials
- Test API endpoints
# Navigate to Flutter app directory
cd flutter_app
# Install dependencies
flutter pub get
# Run the app
flutter run- Setup: Wear the wristband and ensure proper sensor contact
- Mobile App: Download and install the Flutter mobile application
- Registration: Create user profile and add emergency contacts
- Monitoring: Real-time health data is automatically collected and displayed
- Fall Detection: System automatically detects falls and sends alerts
- Health Insights: View Gen AI-powered health translations and recommendations
# Example: Using the ML model
from fall_detection import FallDetectionModel
model = FallDetectionModel()
prediction = model.predict(sensor_data)
print(f"Fall Detected: {prediction}")POST /api/fall-detection
Body: Sensor data array (accelerometer, heart rate, temperature)
Response Format:
// When fall is detected
{
"status": "success",
"fall_detected": true,
"location": {
"latitude": 22.5726,
"longitude": 88.3639
}
}
// When no fall is detected
{
"status": "success",
"fall_detected": false
}POST /api/send-alert
Body: Location and user data
Returns: Alert status and nearby hospitals
POST /api/health-translation
Body: Health metrics and user data
Returns: AI-powered health insights and recommendations
We welcome contributions to improve this fall detection system!
- Fork the repository
- Create a feature branch (
git checkout -b feature/AmazingFeature) - Commit your changes (
git commit -m 'Add some AmazingFeature') - Push to the branch (
git push origin feature/AmazingFeature) - Open a Pull Request
- Advanced sensor integration
- Enhanced Gen AI capabilities
- Performance optimizations
- Additional mobile app features
- Testing and validation improvements
- Documentation enhancements
- Enhanced Gen AI health prediction models
- Advanced mobile app analytics
- Multi-language support
- Improved user interface design
- Multi-user family monitoring dashboard
- Integration with hospital emergency systems
- Advanced predictive health analytics
- Wearable device miniaturization
- Voice assistant integration
- Telemedicine platform integration
This project is licensed under the MIT License - see the LICENSE file for details.
Kunal Pal - Kunal70616c
Indranil Kundu - Orton1269
- ThingSpeak for IoT platform services
- Gen AI for health data interpretation
- Open source sensor libraries and communities
- Contributors and testers
- Flutter community for mobile development support
For support, email kunal.cs.dev@outlook.com or create an issue in this repository.
⭐ Star this repository if you found it helpful!
Made with ❤️ for safer living