Use this URL to cite or link to this record in EThOS: http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.629409
Title: Intelligent resource selection for sensor-task assignment : a knowledge-based approach
Author: De Mel, Geeth R.
ISNI:       0000 0004 5348 8046
Awarding Body: University of Aberdeen
Current Institution: University of Aberdeen
Date of Award: 2014
Availability of Full Text:
Access from EThOS:
Full text unavailable from EThOS. Please try the link below.
Access from Institution:
Abstract:
Today, sensing resources play a crucial role in the success of critical tasks such as border monitoring and surveillance. Although there are various types of resources available, each with different capabilities, only a subset of these resources are useful for a specific task. This is due to the dynamism in tasks' environment and the heterogeneity of the resources. Thus, an effective mechanism to select resources for tasks is needed so that the selected resources cater for the needs of the tasks. Though a considerable amount of research has already been done in different communities to efficiently allocate resources to tasks, we argue that there is little work done to guarantee the effectiveness of the section with respect to the context of operation. In this thesis, we propose a knowledge-based approach in which the context of operation is introduced to the resource selection process. First, we present a formalism to represent a sensor domain. We then introduce sound and complete mechanisms through which effective resource solutions for tasks are discovered. An extension to the representation is then proposed so that the agility in resource selection is increased. Finally, we present an architecture whereby a multitude of such knowledge bases are exposed as services so that a coalition can fully benefit from its networked resources; a query language – and its semantics – to discover appropriate service collections for user requirements are also presented. We have evaluated our work through controlled experiments and critical arguments. Through these evaluations, we have shown that our approach can indeed improve the resource selection process and can augment resource allocation mechanisms. Our approach is general in that, it can be applied in many other domains.
Supervisor: Not available Sponsor: International Technology Alliance
Qualification Name: Thesis (Ph.D.) Qualification Level: Doctoral
EThOS ID: uk.bl.ethos.629409  DOI: Not available
Keywords: Intelligent sensors
Share: