An Automated Fall Detection System Using Recurrent Neural Networks
|Luna Perejón, Francisco
Civit Masot, Javier
Amaya Rodríguez, Isabel
Durán López, Lourdes
Domínguez Morales, Juan Pedro
Civit Balcells, Antón
Linares Barranco, Alejandro
|Universidad de Sevilla. Departamento de Arquitectura y Tecnología de Computadores
|Falls are the most common cause of fatal injuries in elderly
people, causing even death if there is no immediate assistance. Fall detection
systems can be used to alert and request help when this type of accident
Falls are the most common cause of fatal injuries in elderly people, causing even death if there is no immediate assistance. Fall detection systems can be used to alert and request help when this type of accident happens. Certain types of these systems include wearable devices that analyze bio-medical signals from the person carrying it in real time. In this way, Deep Learning algorithms could automate and improve the detection of unintentional falls by analyzing these signals. These algorithms have proven to achieve high effectiveness with competitive performances in many classification problems. This work aims to study 16 Recurrent Neural Networks architectures (using Long Short-Term Memory and Gated Recurrent Units) for falls detection based on accelerometer data, reducing computational requirements of previous research. The architectures have been tested on a labeled version of the publicly available SisFall dataset, achieving a mean F1-score above 0.73 and improving state-of-the-art solutions in terms of network complexity.
|Luna Perejón, F., Civit Masot, J., Amaya Rodríguez, I., Durán López, L., Domínguez Morales, J.P., Civit Balcells, A. y Linares Barranco, A. (2019). An Automated Fall Detection System Using Recurrent Neural Networks. En AIME 2019: 17th Conference on Artificial Intelligence in Medicine (36-41), Poznan, Poland: Springer.