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

Today's article comes from the IEEE Access journal. The authors are Bhatti et al., from the National University of Sciences and Technology (NUST), in Pakistan. In this paper, they present a deep learning-based system that is capable of identifying falls with an average inference time of 20ms.

DOI: 10.1109/ACCESS.2025.3641198