An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes

Yaxin Bi, Chris Nugent, Jing Liao

Research output: Chapter in Book/Report/Conference proceedingChapter

1 Citation (Scopus)

Abstract

Activity recognition under instances of uncertainty is currently recognised as being a challenge within the application domain of Smart Homes. In such environments, uncertainty can be derived from the reliability of sensor networks, the interaction between human and physical objects and the variability of human activities. Nevertheless, it is a difficult process to quantify these sources of uncertainty within the context of an effective reasoning model in order to accurately recognize activities of daily living (ADL). In this paper we propose an evidential framework, where a sensor network is modelled as an evidence space and a collection of ADLs is subsequently modelled as an activity space. The relation between the two spaces is modelled as a multi-valued probabilistic mapping. We identify two sources of uncertainty in terms of sensor uncertainty and relation uncertainty that is reflected in the interaction between sensors and ADLs. Estimations of the respective types of uncertainty were achieved through manufacture statistics for the sensor technology and by learning statistics from sensor data. A preliminary experimental analysis has been carried out to illustrate the advantage of the proposed approach.
LanguageEnglish
Title of host publicationAdvances in Computational Intelligence Communications in Computer and Information Science
Pages564-574
Volume299
Publication statusPublished - 2012

Fingerprint

Sensors
Sensor networks
Statistics
Uncertainty

Cite this

Bi, Y., Nugent, C., & Liao, J. (2012). An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes. In Advances in Computational Intelligence Communications in Computer and Information Science (Vol. 299, pp. 564-574)
Bi, Yaxin ; Nugent, Chris ; Liao, Jing. / An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes. Advances in Computational Intelligence Communications in Computer and Information Science. Vol. 299 2012. pp. 564-574
@inbook{aa634bdae7164ff886cd32162785f024,
title = "An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes",
abstract = "Activity recognition under instances of uncertainty is currently recognised as being a challenge within the application domain of Smart Homes. In such environments, uncertainty can be derived from the reliability of sensor networks, the interaction between human and physical objects and the variability of human activities. Nevertheless, it is a difficult process to quantify these sources of uncertainty within the context of an effective reasoning model in order to accurately recognize activities of daily living (ADL). In this paper we propose an evidential framework, where a sensor network is modelled as an evidence space and a collection of ADLs is subsequently modelled as an activity space. The relation between the two spaces is modelled as a multi-valued probabilistic mapping. We identify two sources of uncertainty in terms of sensor uncertainty and relation uncertainty that is reflected in the interaction between sensors and ADLs. Estimations of the respective types of uncertainty were achieved through manufacture statistics for the sensor technology and by learning statistics from sensor data. A preliminary experimental analysis has been carried out to illustrate the advantage of the proposed approach.",
author = "Yaxin Bi and Chris Nugent and Jing Liao",
year = "2012",
language = "English",
isbn = "978-3-642-31717-0",
volume = "299",
pages = "564--574",
booktitle = "Advances in Computational Intelligence Communications in Computer and Information Science",

}

Bi, Y, Nugent, C & Liao, J 2012, An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes. in Advances in Computational Intelligence Communications in Computer and Information Science. vol. 299, pp. 564-574.

An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes. / Bi, Yaxin; Nugent, Chris; Liao, Jing.

Advances in Computational Intelligence Communications in Computer and Information Science. Vol. 299 2012. p. 564-574.

Research output: Chapter in Book/Report/Conference proceedingChapter

TY - CHAP

T1 - An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes

AU - Bi, Yaxin

AU - Nugent, Chris

AU - Liao, Jing

PY - 2012

Y1 - 2012

N2 - Activity recognition under instances of uncertainty is currently recognised as being a challenge within the application domain of Smart Homes. In such environments, uncertainty can be derived from the reliability of sensor networks, the interaction between human and physical objects and the variability of human activities. Nevertheless, it is a difficult process to quantify these sources of uncertainty within the context of an effective reasoning model in order to accurately recognize activities of daily living (ADL). In this paper we propose an evidential framework, where a sensor network is modelled as an evidence space and a collection of ADLs is subsequently modelled as an activity space. The relation between the two spaces is modelled as a multi-valued probabilistic mapping. We identify two sources of uncertainty in terms of sensor uncertainty and relation uncertainty that is reflected in the interaction between sensors and ADLs. Estimations of the respective types of uncertainty were achieved through manufacture statistics for the sensor technology and by learning statistics from sensor data. A preliminary experimental analysis has been carried out to illustrate the advantage of the proposed approach.

AB - Activity recognition under instances of uncertainty is currently recognised as being a challenge within the application domain of Smart Homes. In such environments, uncertainty can be derived from the reliability of sensor networks, the interaction between human and physical objects and the variability of human activities. Nevertheless, it is a difficult process to quantify these sources of uncertainty within the context of an effective reasoning model in order to accurately recognize activities of daily living (ADL). In this paper we propose an evidential framework, where a sensor network is modelled as an evidence space and a collection of ADLs is subsequently modelled as an activity space. The relation between the two spaces is modelled as a multi-valued probabilistic mapping. We identify two sources of uncertainty in terms of sensor uncertainty and relation uncertainty that is reflected in the interaction between sensors and ADLs. Estimations of the respective types of uncertainty were achieved through manufacture statistics for the sensor technology and by learning statistics from sensor data. A preliminary experimental analysis has been carried out to illustrate the advantage of the proposed approach.

M3 - Chapter

SN - 978-3-642-31717-0

VL - 299

SP - 564

EP - 574

BT - Advances in Computational Intelligence Communications in Computer and Information Science

ER -

Bi Y, Nugent C, Liao J. An Evidential Framework for Associating Sensors to Activities for Activity Recognition in Smart Homes. In Advances in Computational Intelligence Communications in Computer and Information Science. Vol. 299. 2012. p. 564-574