On the disambiguation of passively measured in-home gait velocities from multi-person smart homes

Daniel Austin, Tamara L. Hayes, Jeffrey Kaye, Nora Mattek, Misha Pavela

Research output: Contribution to journalArticle

17 Citations (Scopus)

Abstract

In-home monitoring of gait velocity with passive PIR sensors in a smart home has been shown to be an effective method of continuously and unobtrusively measuring this important predictor of cognitive function and mobility. However, passive measurements of velocity are nonspecific with regard to who generated each measurement or walking event. As a result, this method is not suitable for multi-person homes without additional information to aid in the disambiguation of gait velocities. In this paper we propose a method based on Gaussian mixture models (GMMs) combined with infrequent clinical assessments of gait velocity to model in-home walking speeds of two or more residents. Modeling the gait parameters directly allows us to avoid the more difficult problem of assigning each measured velocity individually to the correct resident. We show that if the clinically measured gait velocities of residents are separated by at least 15 cm/s a GMM can be accurately fit to the in-home gait velocity data. We demonstrate the accuracy of this method by showing that the correlation between the means of the GMMs and the clinically measured gait velocities is 0.877 (p value <0.0001) with bootstrapped 95% confidence intervals of (0.79, 0.94) for 54 measurements of 20 subjects living in multi-person homes. Example applications of using this method to track in-home mean velocities over time are also given.

Original languageEnglish (US)
Pages (from-to)165-174
Number of pages10
JournalJournal of Ambient Intelligence and Smart Environments
Volume3
Issue number2
DOIs
StatePublished - 2011

Fingerprint

Monitoring
Sensors

Keywords

  • Gait
  • passive infrared (PIR) motion detectors
  • smart homes
  • unobtrusive monitoring
  • walking speed

ASJC Scopus subject areas

  • Software

Cite this

On the disambiguation of passively measured in-home gait velocities from multi-person smart homes. / Austin, Daniel; Hayes, Tamara L.; Kaye, Jeffrey; Mattek, Nora; Pavela, Misha.

In: Journal of Ambient Intelligence and Smart Environments, Vol. 3, No. 2, 2011, p. 165-174.

Research output: Contribution to journalArticle

@article{8d052aad5fd24e1da4ef5495a8d555c6,
title = "On the disambiguation of passively measured in-home gait velocities from multi-person smart homes",
abstract = "In-home monitoring of gait velocity with passive PIR sensors in a smart home has been shown to be an effective method of continuously and unobtrusively measuring this important predictor of cognitive function and mobility. However, passive measurements of velocity are nonspecific with regard to who generated each measurement or walking event. As a result, this method is not suitable for multi-person homes without additional information to aid in the disambiguation of gait velocities. In this paper we propose a method based on Gaussian mixture models (GMMs) combined with infrequent clinical assessments of gait velocity to model in-home walking speeds of two or more residents. Modeling the gait parameters directly allows us to avoid the more difficult problem of assigning each measured velocity individually to the correct resident. We show that if the clinically measured gait velocities of residents are separated by at least 15 cm/s a GMM can be accurately fit to the in-home gait velocity data. We demonstrate the accuracy of this method by showing that the correlation between the means of the GMMs and the clinically measured gait velocities is 0.877 (p value <0.0001) with bootstrapped 95{\%} confidence intervals of (0.79, 0.94) for 54 measurements of 20 subjects living in multi-person homes. Example applications of using this method to track in-home mean velocities over time are also given.",
keywords = "Gait, passive infrared (PIR) motion detectors, smart homes, unobtrusive monitoring, walking speed",
author = "Daniel Austin and Hayes, {Tamara L.} and Jeffrey Kaye and Nora Mattek and Misha Pavela",
year = "2011",
doi = "10.3233/AIS-2011-0107",
language = "English (US)",
volume = "3",
pages = "165--174",
journal = "Journal of Ambient Intelligence and Smart Environments",
issn = "1876-1364",
publisher = "IOS Press",
number = "2",

}

TY - JOUR

T1 - On the disambiguation of passively measured in-home gait velocities from multi-person smart homes

AU - Austin, Daniel

AU - Hayes, Tamara L.

AU - Kaye, Jeffrey

AU - Mattek, Nora

AU - Pavela, Misha

PY - 2011

Y1 - 2011

N2 - In-home monitoring of gait velocity with passive PIR sensors in a smart home has been shown to be an effective method of continuously and unobtrusively measuring this important predictor of cognitive function and mobility. However, passive measurements of velocity are nonspecific with regard to who generated each measurement or walking event. As a result, this method is not suitable for multi-person homes without additional information to aid in the disambiguation of gait velocities. In this paper we propose a method based on Gaussian mixture models (GMMs) combined with infrequent clinical assessments of gait velocity to model in-home walking speeds of two or more residents. Modeling the gait parameters directly allows us to avoid the more difficult problem of assigning each measured velocity individually to the correct resident. We show that if the clinically measured gait velocities of residents are separated by at least 15 cm/s a GMM can be accurately fit to the in-home gait velocity data. We demonstrate the accuracy of this method by showing that the correlation between the means of the GMMs and the clinically measured gait velocities is 0.877 (p value <0.0001) with bootstrapped 95% confidence intervals of (0.79, 0.94) for 54 measurements of 20 subjects living in multi-person homes. Example applications of using this method to track in-home mean velocities over time are also given.

AB - In-home monitoring of gait velocity with passive PIR sensors in a smart home has been shown to be an effective method of continuously and unobtrusively measuring this important predictor of cognitive function and mobility. However, passive measurements of velocity are nonspecific with regard to who generated each measurement or walking event. As a result, this method is not suitable for multi-person homes without additional information to aid in the disambiguation of gait velocities. In this paper we propose a method based on Gaussian mixture models (GMMs) combined with infrequent clinical assessments of gait velocity to model in-home walking speeds of two or more residents. Modeling the gait parameters directly allows us to avoid the more difficult problem of assigning each measured velocity individually to the correct resident. We show that if the clinically measured gait velocities of residents are separated by at least 15 cm/s a GMM can be accurately fit to the in-home gait velocity data. We demonstrate the accuracy of this method by showing that the correlation between the means of the GMMs and the clinically measured gait velocities is 0.877 (p value <0.0001) with bootstrapped 95% confidence intervals of (0.79, 0.94) for 54 measurements of 20 subjects living in multi-person homes. Example applications of using this method to track in-home mean velocities over time are also given.

KW - Gait

KW - passive infrared (PIR) motion detectors

KW - smart homes

KW - unobtrusive monitoring

KW - walking speed

UR - http://www.scopus.com/inward/record.url?scp=79956091064&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=79956091064&partnerID=8YFLogxK

U2 - 10.3233/AIS-2011-0107

DO - 10.3233/AIS-2011-0107

M3 - Article

AN - SCOPUS:79956091064

VL - 3

SP - 165

EP - 174

JO - Journal of Ambient Intelligence and Smart Environments

JF - Journal of Ambient Intelligence and Smart Environments

SN - 1876-1364

IS - 2

ER -