SmartCon: a context-aware service discovery and selection mechanism using Artificial Neural Networks

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.