Online Fall Detection using Recurrent Neural Networks

TL;DR

This paper explores the use of Recurrent Neural Networks with LSTM units for real-time fall detection using wearable devices, aiming to improve accuracy and responsiveness in emergency situations.

Contribution

It introduces an RNN-based algorithm for online fall detection utilizing wearable sensor data, demonstrating its effectiveness on a public dataset.

Findings

Achieved high detection accuracy on SisFall dataset

Outperformed previous methods in real-time fall detection

Validated the approach with extended dataset annotations

Abstract

Unintentional falls can cause severe injuries and even death, especially if no immediate assistance is given. The aim of Fall Detection Systems (FDSs) is to detect an occurring fall. This information can be used to trigger the necessary assistance in case of injury. This can be done by using either ambient-based sensors, e.g. cameras, or wearable devices. The aim of this work is to study the technical aspects of FDSs based on wearable devices and artificial intelligence techniques, in particular Deep Learning (DL), to implement an effective algorithm for on-line fall detection. The proposed classifier is based on a Recurrent Neural Network (RNN) model with underlying Long Short-Term Memory (LSTM) blocks. The method is tested on the publicly available SisFall dataset, with extended annotation, and compared with the results obtained by the SisFall authors.