This degree project (EELE-2939-WA) addresses the critical need for affordable fall detection systems for elderly individuals and those with medical conditions. With over 684,000 fatal falls annually in the US alone, this wearable device provides immediate detection and emergency response capabilities.

The system achieves reliable fall detection using threshold-based algorithms with a total project cost of only $59.73, making it significantly more affordable than commercial alternatives while maintaining professional-grade functionality.

• ESP32 Microcontroller: Wi-Fi enabled main processor for data processing and communication
• MPU-6050 MEMS Sensor: 6-axis accelerometer and gyroscope for motion detection via I2C protocol
• Threshold-Based Algorithm: Fall detection using magnitude of total acceleration |a| = 3g and angular velocity |v| = -100°/s
• Real-Time Processing: Continuous sensor monitoring with 100ms sampling intervals
• Web Server Integration: HTML interface for real-time status monitoring and emergency contact links

• Acceleration Analysis: Calculates magnitude of total acceleration: |a| = √(ax² + ay² + az²)
• Angular Velocity Monitoring: Tracks rotational motion using gyroscope data
• Threshold Detection: Triggers fall alert when |a| ≥ 3g or |v| ≤ -100°/s
• False Positive Prevention: Optimized thresholds based on experimental testing to minimize false alarms
• Immediate Response: Automatic alert generation with web interface notification

• Power System: 9V battery with KIS-3R33S voltage converter for stable 3.3V operation
• Wearable Enclosure: 3D printed case designed in FreeCAD using PLA material for comfort and durability
• Sensor Integration: MPU-6050 positioned for optimal motion detection sensitivity
• Compact Design: Lightweight form factor suitable for continuous wear
• Reliable Connectivity: Wi-Fi communication for real-time data transmission

• Controlled Testing: Systematic evaluation of fall detection accuracy under various conditions
• Threshold Optimization: Experimental determination of optimal detection parameters
• Real-World Scenarios: Testing with different types of falls and normal activities
• Performance Metrics: Validation of detection accuracy and response time
• Safety Verification: Comprehensive testing to ensure reliable emergency detection

• Real-Time Interface: HTML-based dashboard displaying current device status
• Status Monitoring: Live updates on device connectivity and sensor readings
• Emergency Links: Integrated emergency contact information and response protocols
• Remote Access: Web-based monitoring accessible from any connected device
• Alert System: Immediate notifications when fall events are detected

• Hardware: ESP32 microcontroller, MPU-6050 MEMS sensor, 9V battery, KIS-3R33S converter
• Programming: C++ for embedded systems and fall detection algorithms
• Communication: Wi-Fi protocol and I2C sensor interface
• Design Tools: FreeCAD for 3D modeling and case design
• Web Technologies: HTML for real-time monitoring interface
• Manufacturing: 3D printing with PLA material for device enclosure