A Novel On-Wrist Fall Detection System
Using Supervised Dictionary Learning
Technique
Farah Othmen
1,2,3(B) , Mouna Baklouti
2,3(B) , Andr´ e Eugenio Lazzaretti
4(B) ,
Marwa Jmal
3(B) , and Mohamed Abid
2(B)
1 Ecole Polytechnique de Tunisie, Universite de Carthage, La Marsa, Tunisia
farah.othmen@ept.rnu.tn
2 Telnet Innovation Labs, Telnet Holding, Ariana, Tunisia
mouna.baklouti@enis.tn, med.abid@enis.tn
3 CES Lab, National School of Engineers of Sfax, University of Sfax, Sfax, Tunisia
Marwa.Jmal@groupe-telnet.net
4 Federal University of Technology, Paran´ a (UTFPR), Curitiba, Brazil
lazzaretti@utfpr.edu.br
Abstract. Wrist-based fall detection system provides a very comfortable and multi-modal healthcare solution, especially for elderly risking
falls. However, the wrist location presents a very challenging and unstable spot to distinguish falls among other daily activities. In this paper,
we propose a Supervised Dictionary Learning approach for wrist-based
fall detection. Three Dictionary learning algorithms for classification are
invoked in this study, namely SRC, FDDL, and LRSDL. To extract
the best descriptive representation of the signal data we followed different preprocessing scenarios based on accelerometer, gyroscope, and
magnetometer. A considerable overall performance was obtained by the
SRC algorithms reaching respectively 99.8%, 100%, and 96.6% of accuracy, sensitivity, and specificity using raw data provided by a triaxial
accelerometer, accordingly overthrowing previously proposed methods
for wrist placement.
Keywords: Fall detection · Supervised Dictionary Learning · Machine
learning · Wrist-based wearable · Signal processing
1 Introduction
The elderly population rate has witnessed dramatic growth over the last decades
and is projected to be still increasing throughout the upcoming years to reach
35% by the year 2050, and thus, jointly increasing the population dependency
This research and innovation work is supported by MOBIDOC grants from the EU and
National Agency for the Promotion of Scientific Research under the AMORI project
and in collaboration with Telnet Innovation Labs.
c
The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 184–196, 2020.
https://doi.org/10.1007/978-3-030-51517-1_15
Using Supervised Dictionary Learning
Technique
Farah Othmen
1,2,3(B) , Mouna Baklouti
2,3(B) , Andr´ e Eugenio Lazzaretti
4(B) ,
Marwa Jmal
3(B) , and Mohamed Abid
2(B)
1 Ecole Polytechnique de Tunisie, Universite de Carthage, La Marsa, Tunisia
farah.othmen@ept.rnu.tn
2 Telnet Innovation Labs, Telnet Holding, Ariana, Tunisia
mouna.baklouti@enis.tn, med.abid@enis.tn
3 CES Lab, National School of Engineers of Sfax, University of Sfax, Sfax, Tunisia
Marwa.Jmal@groupe-telnet.net
4 Federal University of Technology, Paran´ a (UTFPR), Curitiba, Brazil
lazzaretti@utfpr.edu.br
Abstract. Wrist-based fall detection system provides a very comfortable and multi-modal healthcare solution, especially for elderly risking
falls. However, the wrist location presents a very challenging and unstable spot to distinguish falls among other daily activities. In this paper,
we propose a Supervised Dictionary Learning approach for wrist-based
fall detection. Three Dictionary learning algorithms for classification are
invoked in this study, namely SRC, FDDL, and LRSDL. To extract
the best descriptive representation of the signal data we followed different preprocessing scenarios based on accelerometer, gyroscope, and
magnetometer. A considerable overall performance was obtained by the
SRC algorithms reaching respectively 99.8%, 100%, and 96.6% of accuracy, sensitivity, and specificity using raw data provided by a triaxial
accelerometer, accordingly overthrowing previously proposed methods
for wrist placement.
Keywords: Fall detection · Supervised Dictionary Learning · Machine
learning · Wrist-based wearable · Signal processing
1 Introduction
The elderly population rate has witnessed dramatic growth over the last decades
and is projected to be still increasing throughout the upcoming years to reach
35% by the year 2050, and thus, jointly increasing the population dependency
This research and innovation work is supported by MOBIDOC grants from the EU and
National Agency for the Promotion of Scientific Research under the AMORI project
and in collaboration with Telnet Innovation Labs.
c
The Author(s) 2020
M. Jmaiel et al. (Eds.): ICOST 2020, LNCS 12157, pp. 184–196, 2020.
https://doi.org/10.1007/978-3-030-51517-1_15