Saved in:
Bibliographic Details
Main Authors: Cartocci, Nicholas, Gkikakis, Antonios E., Pitzalis, Roberto F., Pera, Fabio, Settino, Maria Teresa, Caldwell, Darwin G., Ortiz, Jesús
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.24507
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866909629215145984
author Cartocci, Nicholas
Gkikakis, Antonios E.
Pitzalis, Roberto F.
Pera, Fabio
Settino, Maria Teresa
Caldwell, Darwin G.
Ortiz, Jesús
author_facet Cartocci, Nicholas
Gkikakis, Antonios E.
Pitzalis, Roberto F.
Pera, Fabio
Settino, Maria Teresa
Caldwell, Darwin G.
Ortiz, Jesús
contents Fall-caused injuries are common in all types of work environments, including offices. They are the main cause of absences longer than three days, especially for small and medium-sized businesses (SMEs). However, data, data amount, data heterogeneity, and stringent processing time constraints continue to pose challenges to real-time fall detection. This work proposes a new approach based on a recurrent neural network (RNN) for Fall Detection and a Kolmogorov-Arnold Network (KAN) to estimate the time of impact of the fall. The approach is tested on SisFall, a dataset consisting of 2706 Activities of Daily Living (ADLs) and 1798 falls recorded by three sensors. The results show that the proposed approach achieves an average TPR of 82.6% and TNR of 98.4% for fall sequences and 94.4% in ADL. Besides, the Root Mean Squared Error of the estimated time of impact is approximately 160ms.
format Preprint
id arxiv_https___arxiv_org_abs_2505_24507
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle How can AI reduce fall injuries in the workplace?
Cartocci, Nicholas
Gkikakis, Antonios E.
Pitzalis, Roberto F.
Pera, Fabio
Settino, Maria Teresa
Caldwell, Darwin G.
Ortiz, Jesús
Signal Processing
Fall-caused injuries are common in all types of work environments, including offices. They are the main cause of absences longer than three days, especially for small and medium-sized businesses (SMEs). However, data, data amount, data heterogeneity, and stringent processing time constraints continue to pose challenges to real-time fall detection. This work proposes a new approach based on a recurrent neural network (RNN) for Fall Detection and a Kolmogorov-Arnold Network (KAN) to estimate the time of impact of the fall. The approach is tested on SisFall, a dataset consisting of 2706 Activities of Daily Living (ADLs) and 1798 falls recorded by three sensors. The results show that the proposed approach achieves an average TPR of 82.6% and TNR of 98.4% for fall sequences and 94.4% in ADL. Besides, the Root Mean Squared Error of the estimated time of impact is approximately 160ms.
title How can AI reduce fall injuries in the workplace?
topic Signal Processing
url https://arxiv.org/abs/2505.24507