Feet fidgeting detection based on accelerometers using decision tree learning and gradient boosting

Esseiva, Julien (School of Management Fribourg, HES-SO // University of Applied Sciences Western Switzerland) ; Caon, Maurizio (School of Management Fribourg, HES-SO // University of Applied Sciences Western Switzerland) ; Mugellini, Elena (School of Management Fribourg, HES-SO // University of Applied Sciences Western Switzerland) ; Abou Khaled, Omar (School of Management Fribourg, HES-SO // University of Applied Sciences Western Switzerland) ; Aminian, Kamiar (Ecole Polytechnique Fédérale de Lausanne (EPFL), Lausanne, Switzerland)

Detection of fidgeting activities is a field which has not been much explored as of now. Studies have shown that fidgeting has a beneficial impact on people's healthiness as it burns a significant amount of energy. Being able to detect when someone is fidgeting would allow to study more closely the health impact of fidgeting. The purpose of this work is to propose an algorithm being able to detect feet fidgeting period of subjects while sitting using 3D accelerometers on both shoes. Initial results on data from 5 subjects collected during this work shows an accuracy of 95% for a classification between sitting with fidgeting and sitting without fidgeting.


Keywords:
Faculty:
Economie et Services
School:
HEG-FR
Subject(s):
Economie/gestion
Publisher:
Cham, Springer
Date:
2018-04
Cham
Springer
Pagination:
Pp. 75-84
Published in:
Bioinformatics and Biomedical Engineering : 6th International Work-Conference, IWBBIO 2018, Granada, Spain, April 25–27, 2018, Proceedings, Part I
Author of the book:
Rojas, Ignacio ; (ed.) ; University of Granada, Spain
Ortuño, Francesco ; (ed.) ; University of Granada, Spain
DOI:
ISBN:
978-3-319-78758-9
External resources:
Appears in Collection:

Note: The status of this file is: restricted


 Record created 2018-10-23, last modified 2018-12-20

Fulltext:
Download fulltext
PDF

Rate this document:

Rate this document:
1
2
3
 
(Not yet reviewed)