Ontology-Enabled Activity Learning and Model Evolution in Smart Homes

George Okeyo; Liming Chen; Hui Wang; Roy Sterritt

doi:10.1007/978-3-642-16355-5_8

Ontology-Enabled Activity Learning and Model Evolution in Smart Homes

George Okeyo, Liming Chen, Hui Wang, Roy Sterritt

School of Electronics, Electrical Engineering and Computer Science

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

5 Citations (Scopus)

Abstract

Activity modelling plays a critical role in activity recognition and assistance in smart home based assisted living. Ontology-based activity modelling is able to leverage domain knowledge and heuristics to create Activities of Daily Living (ADL) models with rich semantics. However, they suffer from incompleteness, inflexibility, and lack of adaptation. In this paper, we propose a novel approach for learning and evolving activity models. The approach uses predefined ”seed” ADL ontologies to identify activities from sensor activation streams. We develop algorithms that analyze logs of activity data to discover new activities as well as the conditions for evolving the seed ADL ontologies. We illustrate our approach through a scenario that shows how ADL models can be evolved to accommodate new ADL activities and preferences of individual smart home’s inhabitants.

Original language	English
Title of host publication	Unknown Host Publication
Place of Publication	Switzerland
Publisher	Springer
Pages	67-82
Number of pages	16
Volume	6406
DOIs	https://doi.org/10.1007/978-3-642-16355-5_8
Publication status	Published - 01 Oct 2010

Bibliographical note

The 7th International Conference on Ubiquitous Intelligence and Computing (UIC 2010) ; Conference date: 01-10-2010

Access to Document

10.1007/978-3-642-16355-5_8

Cite this

@inproceedings{e859b3fe70564b0fa38afaca827ee297,

title = "Ontology-Enabled Activity Learning and Model Evolution in Smart Homes",

abstract = "Activity modelling plays a critical role in activity recognition and assistance in smart home based assisted living. Ontology-based activity modelling is able to leverage domain knowledge and heuristics to create Activities of Daily Living (ADL) models with rich semantics. However, they suffer from incompleteness, inflexibility, and lack of adaptation. In this paper, we propose a novel approach for learning and evolving activity models. The approach uses predefined ”seed” ADL ontologies to identify activities from sensor activation streams. We develop algorithms that analyze logs of activity data to discover new activities as well as the conditions for evolving the seed ADL ontologies. We illustrate our approach through a scenario that shows how ADL models can be evolved to accommodate new ADL activities and preferences of individual smart home{\textquoteright}s inhabitants.",

author = "George Okeyo and Liming Chen and Hui Wang and Roy Sterritt",

note = "The 7th International Conference on Ubiquitous Intelligence and Computing (UIC 2010) ; Conference date: 01-10-2010",

year = "2010",

month = oct,

day = "1",

doi = "10.1007/978-3-642-16355-5_8",

language = "English",

volume = "6406",

pages = "67--82",

booktitle = "Unknown Host Publication",

publisher = "Springer",

}

TY - GEN

T1 - Ontology-Enabled Activity Learning and Model Evolution in Smart Homes

AU - Okeyo, George

AU - Chen, Liming

AU - Wang, Hui

AU - Sterritt, Roy

N1 - The 7th International Conference on Ubiquitous Intelligence and Computing (UIC 2010) ; Conference date: 01-10-2010

PY - 2010/10/1

Y1 - 2010/10/1

N2 - Activity modelling plays a critical role in activity recognition and assistance in smart home based assisted living. Ontology-based activity modelling is able to leverage domain knowledge and heuristics to create Activities of Daily Living (ADL) models with rich semantics. However, they suffer from incompleteness, inflexibility, and lack of adaptation. In this paper, we propose a novel approach for learning and evolving activity models. The approach uses predefined ”seed” ADL ontologies to identify activities from sensor activation streams. We develop algorithms that analyze logs of activity data to discover new activities as well as the conditions for evolving the seed ADL ontologies. We illustrate our approach through a scenario that shows how ADL models can be evolved to accommodate new ADL activities and preferences of individual smart home’s inhabitants.

AB - Activity modelling plays a critical role in activity recognition and assistance in smart home based assisted living. Ontology-based activity modelling is able to leverage domain knowledge and heuristics to create Activities of Daily Living (ADL) models with rich semantics. However, they suffer from incompleteness, inflexibility, and lack of adaptation. In this paper, we propose a novel approach for learning and evolving activity models. The approach uses predefined ”seed” ADL ontologies to identify activities from sensor activation streams. We develop algorithms that analyze logs of activity data to discover new activities as well as the conditions for evolving the seed ADL ontologies. We illustrate our approach through a scenario that shows how ADL models can be evolved to accommodate new ADL activities and preferences of individual smart home’s inhabitants.

U2 - 10.1007/978-3-642-16355-5_8

DO - 10.1007/978-3-642-16355-5_8

M3 - Conference contribution

VL - 6406

SP - 67

EP - 82

BT - Unknown Host Publication

PB - Springer

CY - Switzerland

ER -

Ontology-Enabled Activity Learning and Model Evolution in Smart Homes

Abstract

Bibliographical note

Access to Document

Fingerprint

Cite this