Pre-impact fall detection

Optimal sensor positioning based on a machine learning paradigm

Dario Martelli, Fiorenzo Artoni, Vito Monaco, Angelo Maria Sabatini, Silvestro Micera

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

The aim of this study was to identify the best subset of body segments that provides for a rapid and reliable detection of the transition from steady walking to a slipping event. Fifteen healthy young subjects managed unexpected perturbations during walking. Whole-body 3D kinematics was recorded and a machine learning algorithm was developed to detect perturbation events. In particular, the linear acceleration of all the body segments was parsed by Independent Component Analysis and a Neural Network was used to classify walking from unexpected perturbations. The Mean Detection Time (MDT) was 351±123 ms with an Accuracy of 95.4%. The procedure was repeated with data related to different subsets of all body segments whose variability appeared strongly influenced by the perturbation-induced dynamic modifications. Accordingly, feet and hands accounted for most data information and the performance of the algorithm were slightly reduced using their combination. Results support the hypothesis that, in the framework of the proposed approach, the information conveyed by all the body segments is redundant to achieve effective fall detection, and suitable performance can be obtained by simply observing the kinematics of upper and lower distal extremities. Future studies are required to assess the extent to which such results can be reproduced in older adults and in different experimental conditions.

Original languageEnglish
Article numbere92037
JournalPLoS One
Volume9
Issue number3
DOIs
Publication statusPublished - Mar 21 2014

Fingerprint

artificial intelligence
walking
Walking
Learning systems
Kinematics
kinematics
Biomechanical Phenomena
Sensors
Independent component analysis
Learning algorithms
Neural networks
neural networks
Foot
Lower Extremity
Healthy Volunteers
hands
Hand
Machine Learning

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Pre-impact fall detection : Optimal sensor positioning based on a machine learning paradigm. / Martelli, Dario; Artoni, Fiorenzo; Monaco, Vito; Sabatini, Angelo Maria; Micera, Silvestro.

In: PLoS One, Vol. 9, No. 3, e92037, 21.03.2014.

Research output: Contribution to journalArticle

Martelli, Dario ; Artoni, Fiorenzo ; Monaco, Vito ; Sabatini, Angelo Maria ; Micera, Silvestro. / Pre-impact fall detection : Optimal sensor positioning based on a machine learning paradigm. In: PLoS One. 2014 ; Vol. 9, No. 3.
@article{53450fff02004738beb3b790afce0017,
title = "Pre-impact fall detection: Optimal sensor positioning based on a machine learning paradigm",
abstract = "The aim of this study was to identify the best subset of body segments that provides for a rapid and reliable detection of the transition from steady walking to a slipping event. Fifteen healthy young subjects managed unexpected perturbations during walking. Whole-body 3D kinematics was recorded and a machine learning algorithm was developed to detect perturbation events. In particular, the linear acceleration of all the body segments was parsed by Independent Component Analysis and a Neural Network was used to classify walking from unexpected perturbations. The Mean Detection Time (MDT) was 351±123 ms with an Accuracy of 95.4{\%}. The procedure was repeated with data related to different subsets of all body segments whose variability appeared strongly influenced by the perturbation-induced dynamic modifications. Accordingly, feet and hands accounted for most data information and the performance of the algorithm were slightly reduced using their combination. Results support the hypothesis that, in the framework of the proposed approach, the information conveyed by all the body segments is redundant to achieve effective fall detection, and suitable performance can be obtained by simply observing the kinematics of upper and lower distal extremities. Future studies are required to assess the extent to which such results can be reproduced in older adults and in different experimental conditions.",
author = "Dario Martelli and Fiorenzo Artoni and Vito Monaco and Sabatini, {Angelo Maria} and Silvestro Micera",
year = "2014",
month = "3",
day = "21",
doi = "10.1371/journal.pone.0092037",
language = "English",
volume = "9",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "3",

}

TY - JOUR

T1 - Pre-impact fall detection

T2 - Optimal sensor positioning based on a machine learning paradigm

AU - Martelli, Dario

AU - Artoni, Fiorenzo

AU - Monaco, Vito

AU - Sabatini, Angelo Maria

AU - Micera, Silvestro

PY - 2014/3/21

Y1 - 2014/3/21

N2 - The aim of this study was to identify the best subset of body segments that provides for a rapid and reliable detection of the transition from steady walking to a slipping event. Fifteen healthy young subjects managed unexpected perturbations during walking. Whole-body 3D kinematics was recorded and a machine learning algorithm was developed to detect perturbation events. In particular, the linear acceleration of all the body segments was parsed by Independent Component Analysis and a Neural Network was used to classify walking from unexpected perturbations. The Mean Detection Time (MDT) was 351±123 ms with an Accuracy of 95.4%. The procedure was repeated with data related to different subsets of all body segments whose variability appeared strongly influenced by the perturbation-induced dynamic modifications. Accordingly, feet and hands accounted for most data information and the performance of the algorithm were slightly reduced using their combination. Results support the hypothesis that, in the framework of the proposed approach, the information conveyed by all the body segments is redundant to achieve effective fall detection, and suitable performance can be obtained by simply observing the kinematics of upper and lower distal extremities. Future studies are required to assess the extent to which such results can be reproduced in older adults and in different experimental conditions.

AB - The aim of this study was to identify the best subset of body segments that provides for a rapid and reliable detection of the transition from steady walking to a slipping event. Fifteen healthy young subjects managed unexpected perturbations during walking. Whole-body 3D kinematics was recorded and a machine learning algorithm was developed to detect perturbation events. In particular, the linear acceleration of all the body segments was parsed by Independent Component Analysis and a Neural Network was used to classify walking from unexpected perturbations. The Mean Detection Time (MDT) was 351±123 ms with an Accuracy of 95.4%. The procedure was repeated with data related to different subsets of all body segments whose variability appeared strongly influenced by the perturbation-induced dynamic modifications. Accordingly, feet and hands accounted for most data information and the performance of the algorithm were slightly reduced using their combination. Results support the hypothesis that, in the framework of the proposed approach, the information conveyed by all the body segments is redundant to achieve effective fall detection, and suitable performance can be obtained by simply observing the kinematics of upper and lower distal extremities. Future studies are required to assess the extent to which such results can be reproduced in older adults and in different experimental conditions.

UR - http://www.scopus.com/inward/record.url?scp=84899097035&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84899097035&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0092037

DO - 10.1371/journal.pone.0092037

M3 - Article

VL - 9

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 3

M1 - e92037

ER -