Activity Recognition for Smart Homes Using Dempster-Shafer Theory of Evidence Based on a Revised Lattice Structure. Intelligent Environments 2010: 46-51

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

This paper explores an improvement to activity recognition within a Smart Home environment using the Dempster-Shafer theory of evidence. This approach has the ability to be used to monitor human activities in addition to managing uncertainty in sensor based readings. A three layer lattice structure has been proposed, which can be used to combine the mass functions derived from sensors along with sensor context and subsequently can be used to infer activities. From the total 209 recorded activities throughout a two week period, 85 toileting activities were considered. The results from this work demonstrated that this method was capable of detecting 75 of the toileting activities correctly within a Smart Home environment equating to a classification accuracy of 88.2%.
LanguageEnglish
Title of host publicationUnknown Host Publication
Number of pages5
Publication statusPublished - 2010
EventIntelligent Environments (IE), 2010 Sixth International Conference on -
Duration: 1 Jan 2010 → …

Conference

ConferenceIntelligent Environments (IE), 2010 Sixth International Conference on
Period1/01/10 → …

Fingerprint

Sensors
Uncertainty

Cite this

@inproceedings{9953d4321c634ded806810c85fcae22b,
title = "Activity Recognition for Smart Homes Using Dempster-Shafer Theory of Evidence Based on a Revised Lattice Structure. Intelligent Environments 2010: 46-51",
abstract = "This paper explores an improvement to activity recognition within a Smart Home environment using the Dempster-Shafer theory of evidence. This approach has the ability to be used to monitor human activities in addition to managing uncertainty in sensor based readings. A three layer lattice structure has been proposed, which can be used to combine the mass functions derived from sensors along with sensor context and subsequently can be used to infer activities. From the total 209 recorded activities throughout a two week period, 85 toileting activities were considered. The results from this work demonstrated that this method was capable of detecting 75 of the toileting activities correctly within a Smart Home environment equating to a classification accuracy of 88.2{\%}.",
author = "Jing Liao and Yaxin Bi and Nugent, {Chris D.}",
year = "2010",
language = "English",
booktitle = "Unknown Host Publication",

}

Liao, J, Bi, Y & Nugent, CD 2010, Activity Recognition for Smart Homes Using Dempster-Shafer Theory of Evidence Based on a Revised Lattice Structure. Intelligent Environments 2010: 46-51. in Unknown Host Publication. Intelligent Environments (IE), 2010 Sixth International Conference on, 1/01/10.

Activity Recognition for Smart Homes Using Dempster-Shafer Theory of Evidence Based on a Revised Lattice Structure. Intelligent Environments 2010: 46-51. / Liao, Jing; Bi, Yaxin; Nugent, Chris D.

Unknown Host Publication. 2010.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Activity Recognition for Smart Homes Using Dempster-Shafer Theory of Evidence Based on a Revised Lattice Structure. Intelligent Environments 2010: 46-51

AU - Liao, Jing

AU - Bi, Yaxin

AU - Nugent, Chris D.

PY - 2010

Y1 - 2010

N2 - This paper explores an improvement to activity recognition within a Smart Home environment using the Dempster-Shafer theory of evidence. This approach has the ability to be used to monitor human activities in addition to managing uncertainty in sensor based readings. A three layer lattice structure has been proposed, which can be used to combine the mass functions derived from sensors along with sensor context and subsequently can be used to infer activities. From the total 209 recorded activities throughout a two week period, 85 toileting activities were considered. The results from this work demonstrated that this method was capable of detecting 75 of the toileting activities correctly within a Smart Home environment equating to a classification accuracy of 88.2%.

AB - This paper explores an improvement to activity recognition within a Smart Home environment using the Dempster-Shafer theory of evidence. This approach has the ability to be used to monitor human activities in addition to managing uncertainty in sensor based readings. A three layer lattice structure has been proposed, which can be used to combine the mass functions derived from sensors along with sensor context and subsequently can be used to infer activities. From the total 209 recorded activities throughout a two week period, 85 toileting activities were considered. The results from this work demonstrated that this method was capable of detecting 75 of the toileting activities correctly within a Smart Home environment equating to a classification accuracy of 88.2%.

M3 - Conference contribution

BT - Unknown Host Publication

ER -