Intelligent Resource Selection for Sensor-Task Assignment: A Knowledge Based Approach

DOI: 10.5176/978-981-08-7656-2ATAI2010-55

Authors: Geeth de Mel, Wamberto Vasconcelos, Timothy J. Norman

Abstract:

Sensing resources play a crucial role in the successof critical tasks such as surveillance. Therefore, it is importantto assigning appropriate sensing resources to tasks such that theselected resources fully cater the needs of the tasks. However,selecting the right resources to tasks is a computationally hardproblem to solve. Most of the existing approaches address theefficiency aspect of the resource selection by considering thephysical aspects of the sensor network (e.g., range, power, etc.)but have ignored important domain related properties such ascapabilities of assets, environmental conditions, policies and soon which makes the selection effective. In this paper we presenta knowledge rich mechanism to intelligently select resourcesfor tasks such that the selected resources sufficiently coverthe needs of the tasks. Ontologies are used to capture thecrucial domain knowledge and semantic matchmaking is usedto perform sensor-task matching. A combination of ontologicaland first-order-logic reasoning is considered for the solutionarchitecture.

Keywords: Sensors; Platforms; Knowledge Representation;Reasoning; Semantic Matchmaking; Resource Assignment