Cargando…

Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes

Wearable biosensors, such as those embedded in smart phones, can provide data to assess neuro-motor control in mobile settings, at homes, schools, workplaces and clinics. However, because most machine learning algorithms currently used to analyze such data require several steps that depend on human...

Descripción completa

Detalles Bibliográficos
Autores principales: Torres, Elizabeth B., Vero, Joe, Rai, Richa
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2018
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948575/
https://www.ncbi.nlm.nih.gov/pubmed/29596342
http://dx.doi.org/10.3390/s18041025
_version_ 1783322580825931776
author Torres, Elizabeth B.
Vero, Joe
Rai, Richa
author_facet Torres, Elizabeth B.
Vero, Joe
Rai, Richa
author_sort Torres, Elizabeth B.
collection PubMed
description Wearable biosensors, such as those embedded in smart phones, can provide data to assess neuro-motor control in mobile settings, at homes, schools, workplaces and clinics. However, because most machine learning algorithms currently used to analyze such data require several steps that depend on human heuristics, the analyses become computationally expensive and rather subjective. Further, there is no standardized scale or set of tasks amenable to take advantage of such technology in ways that permit broad dissemination and reproducibility of results. Indeed, there is a critical need for fully objective automated analytical methods that easily handle the deluge of data these sensors output, while providing standardized scales amenable to apply across large sections of the population, to help promote personalized-mobile medicine. Here we use an open-access data set from Kaggle.com to illustrate the use of a new statistical platform and standardized data types applied to smart phone accelerometer and gyroscope data from 30 participants, performing six different activities. We report full distinction without confusion of the activities from the Kaggle set using a single parameter (linear acceleration or angular speed). We further extend the use of our platform to characterize data from commercially available smart shoes, using gait patterns within a set of experiments that probe nervous systems functioning and levels of motor control.
format Online
Article
Text
id pubmed-5948575
institution National Center for Biotechnology Information
language English
publishDate 2018
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-59485752018-05-17 Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes Torres, Elizabeth B. Vero, Joe Rai, Richa Sensors (Basel) Article Wearable biosensors, such as those embedded in smart phones, can provide data to assess neuro-motor control in mobile settings, at homes, schools, workplaces and clinics. However, because most machine learning algorithms currently used to analyze such data require several steps that depend on human heuristics, the analyses become computationally expensive and rather subjective. Further, there is no standardized scale or set of tasks amenable to take advantage of such technology in ways that permit broad dissemination and reproducibility of results. Indeed, there is a critical need for fully objective automated analytical methods that easily handle the deluge of data these sensors output, while providing standardized scales amenable to apply across large sections of the population, to help promote personalized-mobile medicine. Here we use an open-access data set from Kaggle.com to illustrate the use of a new statistical platform and standardized data types applied to smart phone accelerometer and gyroscope data from 30 participants, performing six different activities. We report full distinction without confusion of the activities from the Kaggle set using a single parameter (linear acceleration or angular speed). We further extend the use of our platform to characterize data from commercially available smart shoes, using gait patterns within a set of experiments that probe nervous systems functioning and levels of motor control. MDPI 2018-03-29 /pmc/articles/PMC5948575/ /pubmed/29596342 http://dx.doi.org/10.3390/s18041025 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
Torres, Elizabeth B.
Vero, Joe
Rai, Richa
Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes
title Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes
title_full Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes
title_fullStr Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes
title_full_unstemmed Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes
title_short Statistical Platform for Individualized Behavioral Analyses Using Biophysical Micro-Movement Spikes
title_sort statistical platform for individualized behavioral analyses using biophysical micro-movement spikes
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC5948575/
https://www.ncbi.nlm.nih.gov/pubmed/29596342
http://dx.doi.org/10.3390/s18041025
work_keys_str_mv AT torreselizabethb statisticalplatformforindividualizedbehavioralanalysesusingbiophysicalmicromovementspikes
AT verojoe statisticalplatformforindividualizedbehavioralanalysesusingbiophysicalmicromovementspikes
AT rairicha statisticalplatformforindividualizedbehavioralanalysesusingbiophysicalmicromovementspikes