Vifall: real-time vital signs monitoring, fall detection, and notification systems using iot-based wearabale technology for elderly care:
Camille Tracy T. Taberna, Aljhun M. Abella, Justine Mae B. De Guzman, Rowell Mayabason, Evita Joyce B. Ngo, and Matthew Aaron A. Pagente.--
- Manila: Technological University of the Philippines, 2025.
- xv, 229pages: 29cm.
Bachelor's thesis
College Of Engineering.--
Includes bibliographic references and index.
This research presents ViFall, an innovative IoT-based wearable system designed for real-time vital signs monitoring and fall detection, aimed at enhancing elderly care. The system utilizes an Arduino-powered device equipped with photoplethysmography (PPG) sensors to continuously monitor vital signs, which include heart rate and blood oxygen levels. In addition, an accelerometer and gyroscope are used to detect falls based on differences in movement patterns, giving a reliable fall detection mechanism. To ensure real-time communication, a GSM module is added into the device for fast sending of alerts
to caregivers or family members through missed calls when a fall happens. A threshold- based algorithm running on the Arduino processes the sensor data, while the NodeMCU is
used for wireless connectivity, ensuring smooth data transmission to remote monitoring systems. Additionally, an Android application has been developed, offering users a platform for continuous monitoring of vital signs and logging the abnormalities and falls detected into the notifications section. The system’s performance is evaluated in accordance with ISO/IEEE 11073 – 10471 software quality standards, ensuring the solution meets key quality attributes such as functionality, usability, and reliability. This comprehensive testing proved its capability to give dependable real-time vital signs monitoring and fall detection for elderly individuals, helping improve safety and allowing caregivers or family members to respond promptly to emergencies. The system achieved high performance on all metrics, with an accuracy of 93.47% showing high capability to identify fall and non-fall events. A precision of 98.18%, tells that almost all detected falls are real falls. The recall of 90.00% shows that the system successfully identified many of the actual falls, but still need more improvements. The specificity of 97.88% means the
system has a strong ability to identify non-fall events with minimal false alarms. The F1- Score of 93.91% suggests a good balance between precision and recall, meaning the system maintains solid performance in both detecting falls and minimizing false positives. For vital signs monitoring, based on tests conducted with 15 participants, the system achieved an average Root Mean Square Error (RMSE) of 2.41 for SpO2 and 2.53 for heart rate, indicating a high level of accuracy in continuous health tracking. Overall, ViFall offers an efficient and reliable tool for elderly care, with the use of IoT and wearable technology to enhance health monitoring and emergency response.