Fall Detection System for Elderly People using IoT and Machine Learning technology
Khalid Nafil, Abdellatif Kobbane, Abdoul-Bagui Mohamadou, Anass Saidi, Banouk Yahya, Lamnaouer Oussama · 2023
For the senior population, falls are a severe issue since they can result in life-threatening injuries or even death. The probability of a successful recovery can be considerably increased by prompt intervention following a fall, yet it can be difficult for caregivers to be aware of a fall as soon as it occurs. We describe a wearable gadget that employs a few sensors to detect falls and alert designated caregivers via a mobile app in order to solve this problem. Our system’s IoT design is built on sensors that transmit data to the cloud, where machine learning algorithms analyze the information to determine whether a fall has taken place. The device measures body acceleration and angular velocity, and the machine learning algorithms use this data to recognize when the wearer has fallen. If a fall is detected, the system sends relevant information to caregivers, such as the time of the fall, enabling a prompt and informed response. Our solution has several benefits compared to other fall detection methods. First, it is wearable, so it does not require the elderly individuals to carry a separate device or manually trigger an alarm. Second, it is automatic, which reduces the risk of false alarms and increases the likelihood of timely response. Finally, it uses machine learning algorithms to analyze the Big Data gathered from the different sensors, which enables it to adapt to the wearer’s individual movements and behavior, making it more accurate and reliable. Furthermore, our wearable device has the potential to significantly improve the quality of life for elderly individuals and provide peace of mind for their loved ones. By reducing the time between falls and responses, our device can increase the likelihood of successful recovery and help prevent potential fatalities.