sensor fusion

Sensor Aggregation and Integration in Healthcare Location Based Services

Publication Type:

Conference Paper

Source:

1st Workshop on Location Based Services for Health Care, p.1-4 (2006)

ISBN:

1-4244-1086-X

Accession Number:

9463769

Keywords:

sensor fusion; location-based systems; ubiquitous computing; pervasive computing

Abstract:

Complex and dynamic working environments such as healthcare facilities consist of staff, patients and equipment constantly moving in response to changing medical requirements. Knowing the current location of people and equipment is essential for the smooth running of a facility, yet creating a global view through tracking is a challenging task. It is clear that many common hospital situations can be improved with real-time access to the various actors' location information. One of the main problems with implementing such services is that current location based applications tend to be proprietary and the data generated closed. The realisation of ubiquitous location based services demands the exploration of hybrid models and methods that can utilise existing and subsequent infrastructures in novel and complimentary ways. We describe a number of hospital scenarios that use location-based services and make available all the location data gathered. We propose that by aggregating location data by a range of acquisition methods it is possible to improve the performance of location applications and readily adapt to the introduction of new location detection technologies.

Sensor Fusion-Based Middleware for Assisted Living

Publication Type:

Conference Paper

Source:

4th International Conference On Smart homes & heath Telematics, IOS Press, Belfast, UK, p.281-288 (2006)

Keywords:

smart homes; pervasive computing; construct; sensor fusion; middleware; ubiquitous computing

Abstract:

Systems for home automation can make a vital contribution to the well-being of individuals requiring moderate amounts of support for day-to-day living. Existing systems suffer both from competing and often closed standards bases and from a message-based architecture that can complicate the development of flexible applications requiring information from disparate sources. We describe a knowledge-based pervasive computing middleware and show how it can be used to provide semantically rich unification over a range of home- and web-based automation systems.

Sensor Fusion-Based Middleware for Smart Homes

Publication Type:

Journal Article

Source:

International Journal of Assistive Robotics and Mechatronics (IJARM), Volume 8, Number 2, p.53-60 (2007)

URL:

http://www.csi.ucd.ie/UserFiles/publications/1178110026850.pdf

Keywords:

smart homes; pervasive computing; construct; sensor fusion; middleware; ubiquitous computing

Abstract:

Smart homes are sensor-rich environments that contain dynamic sets of interacting components. These components often use competing and closed standards and form a message-based architecture. This complicates the development of applications that require information from disparate sources. It becomes difficult to add new components or to allow components from different applications to interact with each another. In this paper we describe Construct, a pervasive computing middleware that is ideally suited for deployment in the smart home. Construct acts as a sensor fusion layer that takes output from each smart home component and makes it available to all applications. This makes it easy to develop applications that require access to heterogeneous sources of sensor data, and to add sensors to existing systems to improve their performance. This paper demonstrates two Construct-enabled smart home applications and shows how access to new sensors leads to improvements in their performance.

Hybridising Events and Knowledge as a Basis for Building Autonomic Systems

Publication Type:

Journal Article

Source:

Journal of Trusted and Autonomic Computing (2006)

Keywords:

sensor fusion; uncertainty; ubiquitous computing; pervasive computing

Abstract:

Event-based systems are a popular substrate for distributing information derived from sensors to be used in driving adaptive behaviour. This paper argues that using events directly provides a poor model of context, and that a hybrid approach that uses events to populate and maintain a distributed knowledge base offers a more stable solution. The inherent uncertainties in both sensor data and reasoning imply that traditional knowledge-based system techniques applied to context be extended to deal with more uncertain reasoning

Syndicate content