Title: SmartCon: a context-aware service discovery and selection mechanism using Artificial Neural Networks
Authors: Eyhab Al-Masri, Qusay H. Mahmoud
Addresses: Department of Computing and Information Science, University of Guelph, Guelph, Ontario N1G 2W1, Canada. ' Department of Computing and Information Science, University of Guelph, Guelph, Ontario N1G 2W1, Canada
Abstract: In this paper, we present SmartCon, a context-aware system for the discovery and selection of mobile services using Artificial Neural Networks (ANNs). The solution we have developed is a mobile agent-enabled system that adaptively and iteratively learns to select the best available mobile service derived from the extraction of a series of features utilising contextual information such as the Composite Capabilities/Preference Profiles (CC/PP), service-specific and non-uniform user-specific features which are supplied to a Back-Propagation Neural Network. Based on the features provided, the neural network classifies the most relevant mobile service. In the present work, the system is also capable through iterative learning to generalise and gather information using cognitive feedback based on the user|s decisions and interactivity with a Mobile Device. SmartCon is evaluated using a series of preliminary empirical data and results show an 87% success rate in the discovery and selection of the best or most relevant mobile service.
Keywords: ANNs; artificial neural networks; back propagation; capabilities profile; preference profile; composite profiles; mobile services; m-services; service discovery; service selection; software agents; context-aware systems; iterative learning; cognitive feedback.
International Journal of Intelligent Systems Technologies and Applications, 2009 Vol.6 No.1/2, pp.144 - 156
Published online: 25 Jan 2009 *Full-text access for editors Access for subscribers Purchase this article Comment on this article