Cargando…

A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System

In order to overcome the current limitations in current threshold-based and machine learning-based fall detectors, an insole system and novel fall classification model were created. Because high-acceleration activities have a high risk for falls, and because of the potential damage that is associate...

Descripción completa

Detalles Bibliográficos
Autores principales: Cates, Benjamin, Sim, Taeyong, Heo, Hyun Mu, Kim, Bori, Kim, Hyunggun, Mun, Joung Hwan
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948845/
https://www.ncbi.nlm.nih.gov/pubmed/29673165
http://dx.doi.org/10.3390/s18041227
_version_ 1783322643771949056
author Cates, Benjamin
Sim, Taeyong
Heo, Hyun Mu
Kim, Bori
Kim, Hyunggun
Mun, Joung Hwan
author_facet Cates, Benjamin
Sim, Taeyong
Heo, Hyun Mu
Kim, Bori
Kim, Hyunggun
Mun, Joung Hwan
author_sort Cates, Benjamin
collection PubMed
description In order to overcome the current limitations in current threshold-based and machine learning-based fall detectors, an insole system and novel fall classification model were created. Because high-acceleration activities have a high risk for falls, and because of the potential damage that is associated with falls during high-acceleration activities, four low-acceleration activities, four high-acceleration activities, and eight types of high-acceleration falls were performed by twenty young male subjects. Encompassing a total of 800 falls and 320 min of activities of daily life (ADLs), the created Support Vector Machine model’s Leave-One-Out cross-validation provides a fall detection sensitivity (0.996), specificity (1.000), and accuracy (0.999). These classification results are similar or superior to other fall detection models in the literature, while also including high-acceleration ADLs to challenge the classification model, and simultaneously reducing the burden that is associated with wearable sensors and increasing user comfort by inserting the insole system into the shoe.
format Online
Article
Text
id pubmed-5948845
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-59488452018-05-17 A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System Cates, Benjamin Sim, Taeyong Heo, Hyun Mu Kim, Bori Kim, Hyunggun Mun, Joung Hwan Sensors (Basel) Article In order to overcome the current limitations in current threshold-based and machine learning-based fall detectors, an insole system and novel fall classification model were created. Because high-acceleration activities have a high risk for falls, and because of the potential damage that is associated with falls during high-acceleration activities, four low-acceleration activities, four high-acceleration activities, and eight types of high-acceleration falls were performed by twenty young male subjects. Encompassing a total of 800 falls and 320 min of activities of daily life (ADLs), the created Support Vector Machine model’s Leave-One-Out cross-validation provides a fall detection sensitivity (0.996), specificity (1.000), and accuracy (0.999). These classification results are similar or superior to other fall detection models in the literature, while also including high-acceleration ADLs to challenge the classification model, and simultaneously reducing the burden that is associated with wearable sensors and increasing user comfort by inserting the insole system into the shoe. MDPI 2018-04-17 /pmc/articles/PMC5948845/ /pubmed/29673165 http://dx.doi.org/10.3390/s18041227 Text en © 2018 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Cates, Benjamin
Sim, Taeyong
Heo, Hyun Mu
Kim, Bori
Kim, Hyunggun
Mun, Joung Hwan
A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System
title A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System
title_full A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System
title_fullStr A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System
title_full_unstemmed A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System
title_short A Novel Detection Model and Its Optimal Features to Classify Falls from Low- and High-Acceleration Activities of Daily Life Using an Insole Sensor System
title_sort novel detection model and its optimal features to classify falls from low- and high-acceleration activities of daily life using an insole sensor system
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948845/
https://www.ncbi.nlm.nih.gov/pubmed/29673165
http://dx.doi.org/10.3390/s18041227
work_keys_str_mv AT catesbenjamin anoveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT simtaeyong anoveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT heohyunmu anoveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT kimbori anoveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT kimhyunggun anoveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT munjounghwan anoveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT catesbenjamin noveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT simtaeyong noveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT heohyunmu noveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT kimbori noveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT kimhyunggun noveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem
AT munjounghwan noveldetectionmodelanditsoptimalfeaturestoclassifyfallsfromlowandhighaccelerationactivitiesofdailylifeusinganinsolesensorsystem