Real-Time Monitoring and Fall Detection for Alzheimer’s/Dementia Patients Using Internet of Thing (IoT) Technology

Abstract

Alzheimer's disease and dementia significantly impair cognitive and physical abilities, increasing the risk of falls among elderly patients. Falls often result in severe injuries, further deteriorating patient health and imposing challenges on caregivers. This study presents a real-time monitoring and fall detection system utilizing Internet of Things (IoT) technology to enhance patient safety and caregiver response. The system integrates wearable sensors, including the MPU6050 accelerometer and gyroscope, along with GPS tracking via the Blynk application. It continuously monitors patient movements and provides instant alerts with precise location data to caregivers in the event of a fall.  The system was tested for various activity statuses, including no movement, walking, jogging, running, and falls. The results demonstrated accurate differentiation between normal activities and fall events based on accelerometer and gyroscope readings. When a fall was detected, the system successfully triggered immediate notifications and shared GPS coordinates, enabling prompt intervention. The real-time data visualization in the Blynk application further enhanced usability for caregivers. By addressing the limitations of existing monitoring systems and leveraging IoT advancements, this project improves patient safety, promotes independent living, and reduces caregiver burden.