Machine Learning and Cloud Enabled Fall Detection System using Data from Wearable Devices: Deployment and Evaluation
Italo Araújo, Marciel Barros Pereira, Wendley Silva, Igor Linhares, Vitor Marx, André M. Andrade, Rossana M. C. Andrade, Miguel Castro · 2022
In recent years, the popularization of devices to monitor people in combination with Machine Learning (ML) in the context of Internet of Things (IoT) has grown significantly. Then, the number of applications to solve many health issues that require data collection and processing has increased. One of the common concerns by Health institutions is human falls, which can lead to severe health damages or death. Thus, it is crucial to detect quickly when a fall occurs, to reduce the possible sequels. One way to identify potential falls is using data collected from wearable devices as input of an IoT system using ML models, which is the solution proposed in this work using Cloud computing. Thus, we present this solution and its deployment and evaluation that consists of three modules: data acquisition and transfer, intelligent cloud application, and notification service. The best result of the ML models presented is 94.4% of accuracy, considering a low rate of false negatives of 4.3%.