Cargando…

SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning

This paper presents SmartFall, an Android app that uses accelerometer data collected from a commodity-based smartwatch Internet of Things (IoT) device to detect falls. The smartwatch is paired with a smartphone that runs the SmartFall application, which performs the computation necessary for the pre...

Descripción completa

Detalles Bibliográficos
Autores principales: Mauldin, Taylor R., Canby, Marc E., Metsis, Vangelis, Ngu, Anne H. H., Rivera, Coralys Cubero
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6210545/
https://www.ncbi.nlm.nih.gov/pubmed/30304768
http://dx.doi.org/10.3390/s18103363
_version_ 1783367140287447040
author Mauldin, Taylor R.
Canby, Marc E.
Metsis, Vangelis
Ngu, Anne H. H.
Rivera, Coralys Cubero
author_facet Mauldin, Taylor R.
Canby, Marc E.
Metsis, Vangelis
Ngu, Anne H. H.
Rivera, Coralys Cubero
author_sort Mauldin, Taylor R.
collection PubMed
description This paper presents SmartFall, an Android app that uses accelerometer data collected from a commodity-based smartwatch Internet of Things (IoT) device to detect falls. The smartwatch is paired with a smartphone that runs the SmartFall application, which performs the computation necessary for the prediction of falls in real time without incurring latency in communicating with a cloud server, while also preserving data privacy. We experimented with both traditional (Support Vector Machine and Naive Bayes) and non-traditional (Deep Learning) machine learning algorithms for the creation of fall detection models using three different fall datasets (Smartwatch, Notch, Farseeing). Our results show that a Deep Learning model for fall detection generally outperforms more traditional models across the three datasets. This is attributed to the Deep Learning model’s ability to automatically learn subtle features from the raw accelerometer data that are not available to Naive Bayes and Support Vector Machine, which are restricted to learning from a small set of extracted features manually specified. Furthermore, the Deep Learning model exhibits a better ability to generalize to new users when predicting falls, an important quality of any model that is to be successful in the real world. We also present a three-layer open IoT system architecture used in SmartFall, which can be easily adapted for the collection and analysis of other sensor data modalities (e.g., heart rate, skin temperature, walking patterns) that enables remote monitoring of a subject’s wellbeing.
format Online
Article
Text
id pubmed-6210545
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-62105452018-11-02 SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning Mauldin, Taylor R. Canby, Marc E. Metsis, Vangelis Ngu, Anne H. H. Rivera, Coralys Cubero Sensors (Basel) Article This paper presents SmartFall, an Android app that uses accelerometer data collected from a commodity-based smartwatch Internet of Things (IoT) device to detect falls. The smartwatch is paired with a smartphone that runs the SmartFall application, which performs the computation necessary for the prediction of falls in real time without incurring latency in communicating with a cloud server, while also preserving data privacy. We experimented with both traditional (Support Vector Machine and Naive Bayes) and non-traditional (Deep Learning) machine learning algorithms for the creation of fall detection models using three different fall datasets (Smartwatch, Notch, Farseeing). Our results show that a Deep Learning model for fall detection generally outperforms more traditional models across the three datasets. This is attributed to the Deep Learning model’s ability to automatically learn subtle features from the raw accelerometer data that are not available to Naive Bayes and Support Vector Machine, which are restricted to learning from a small set of extracted features manually specified. Furthermore, the Deep Learning model exhibits a better ability to generalize to new users when predicting falls, an important quality of any model that is to be successful in the real world. We also present a three-layer open IoT system architecture used in SmartFall, which can be easily adapted for the collection and analysis of other sensor data modalities (e.g., heart rate, skin temperature, walking patterns) that enables remote monitoring of a subject’s wellbeing. MDPI 2018-10-09 /pmc/articles/PMC6210545/ /pubmed/30304768 http://dx.doi.org/10.3390/s18103363 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
Mauldin, Taylor R.
Canby, Marc E.
Metsis, Vangelis
Ngu, Anne H. H.
Rivera, Coralys Cubero
SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning
title SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning
title_full SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning
title_fullStr SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning
title_full_unstemmed SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning
title_short SmartFall: A Smartwatch-Based Fall Detection System Using Deep Learning
title_sort smartfall: a smartwatch-based fall detection system using deep learning
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6210545/
https://www.ncbi.nlm.nih.gov/pubmed/30304768
http://dx.doi.org/10.3390/s18103363
work_keys_str_mv AT mauldintaylorr smartfallasmartwatchbasedfalldetectionsystemusingdeeplearning
AT canbymarce smartfallasmartwatchbasedfalldetectionsystemusingdeeplearning
AT metsisvangelis smartfallasmartwatchbasedfalldetectionsystemusingdeeplearning
AT nguannehh smartfallasmartwatchbasedfalldetectionsystemusingdeeplearning
AT riveracoralyscubero smartfallasmartwatchbasedfalldetectionsystemusingdeeplearning