Beyond Falls: A Hybrid CNN–LSTM–Attention Framework for Pre-, Transition-, and Post-Fall Detection With Wearable Inertial Sensors

Falls are a leading cause of injury, disability, and mortality among older adults, with significant physical, psychological, and economic consequences. This paper presents a deep learning–based real-time fall detection system capable of identifying falls during pre-impact, post-impact, and tr...

Descrición completa

Detalles Bibliográficos

Principais autores:	Faraz Ahmad Bhatti, Qaiser Riaz, Bjorn Kruger
Formato:	Artigo
Idioma:	Inglês
Publicado:	IEEE 2025-01-01
Series:	IEEE Access
Assuntos:	Deep learning for fall detection fall prevention multi-class falls multi-class human activity recognition (HAR) inertial measurement units (IMUs) inertial sensors
Acceso en liña:	https://ieeexplore.ieee.org/document/11283000/
Tags:	Engadir etiqueta Sen Etiquetas, Sexa o primeiro en etiquetar este rexistro!