Home

ontology

Using Ontologies in Case-Based Activity Recognition

Fri, 02/19/2010 - 10:03 — lorcan

Publication Type:

Conference Paper

Authors:

Stephen Knox; Lorcan Coyle; Simon Dobson

Source:

23rd Florida Artificial Intelligence Research Society Conference (FLAIRS-23), AAAI (2010)

Keywords:

case based reasoning; ontology; pervasive computing; ubiquitous computing; situation; context awareness

Abstract:

Pervasive computing requires the ability to detect user activity in order to provide situation-specific services. Case-based reasoning can be used for activity recognition by using sensor data obtained from the environment. Pervasive computing systems can grow to be very large, containing many users, sensors, objects and situations, thus raising the issue of scalability. This paper presents a case-based reasoning approach to activity recognition in a smart home setting. An analysis is performed on scalability with respect to case storage, and an ontology-based approach is proposed for case base maintenance. We succeeded in reducing the casebase size by a factor of one thousand, while increasing the accuracy in recognising some activities.

Ontology-Based Query Recommendation as a Support to Image Retrieval

Sat, 08/30/2008 - 14:21 — lorcan

Publication Type:

Conference Paper

Authors:

Olga Murdoch; Lorcan Coyle; Simon Dobson

Source:

19th Irish Conference on Artificial Intelligence and Cognitive Science, Cork, Ireland, p.103-112 (2008)

Keywords:

ontology; recommender systems; query elaboration; image retrieval; image annotation; tagging

Abstract:

Stock photo libraries are the most common means for publishers and advertisers to find images for their media. Searching for the perfect photo can be a time-consuming and frustrating task. This is because searching is often dependent on the descriptors or tags given to each photo by the editors and contributors to the library. The tagging process is subjective, further complicating the search process. We describe an algorithm that uses domain ontologies to improve the interactions with these libraries. Ontologies are used to expand query terms based on users' initial search queries. We present results that demonstrate that the use of ontologies greatly improves users ability to retrieve photos when undertaking a number of search tasks.

Integrating Multiple Contexts and Ontologies in a Pervasive Computing Framework

Sun, 03/09/2008 - 12:18 — lorcan

Publication Type:

Conference Paper

Authors:

Adrian K. Clear; Stephen Knox; Juan Ye; Lorcan Coyle; Simon Dobson; Paddy Nixon

Source:

Contexts and Ontologies: Theory, Practice and Applications, CEUR Workshop Proceedings, Volume 210, Riva Del Garda, Italy, p.20-25 (2006)

Keywords:

context; ontology; construct; pervasive computing; ubiquitous computing

Abstract:

There is a commonly accepted need for contexts and ontologies to describe the vast amounts of data that are available to pervasive computing applications. Existing contexts and ontologies are either much generalised, very application specific, or inflexible. An integrated approach is required in which new concepts can be added and related to existing ones transparently. This paper describes a novel approach to the design of a set of contexts and ontologies for context-aware pervasive computing systems. It describes a Query Service, that lies between applications and contextual information, which complemented by the contexts and ontologies, offers a more powerful query answering service to application developers than is currently available.

Ontology-based Models in Pervasive Computing Systems

Sun, 03/09/2008 - 12:18 — lorcan

Publication Type:

Journal Article

Authors:

Juan Ye; Lorcan Coyle; Simon Dobson; Paddy Nixon

Source:

The Knowledge Engineering Review, Cambridge University Press, Volume 22, Issue 4, p.315-347 (2007)

Keywords:

ontology; pervasive computing; ontology modelling; ubiquitous computing

Abstract:

Pervasive computing is by its nature open and extensible, and must integrate information from a diverse range of sources. This leads to a problem of information exchange, so sub-systems must agree on shared representations. Ontologies potentially provide a well-founded mechanism for the representation and exchange of such structured information. A number of ontologies have been developed specifically for use in pervasive computing, none of which appears to cover adequately the space of concerns applicable to application designers. We compare and contrast the most popular ontologies, evaluating them against the system challenges generally recognised within the pervasive computing community. We identify a number of deficiencies that must be addressed in order to apply ontological techniques successfully to next-generation pervasive systems.

Syndicate content