A context-aware mobile service discovery and selection mechanism using artificial neural networks

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 utilizing contextual information such as the Composite Capabilities/Preferences Profile (CC/PP), service-specific, and non-uniform user-specific features which are supplied to a backpropagation 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 generalize and gather information using cognitive feedback based on 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.

[1]  John Wroclawski,et al.  Learning user preferences for wireless services provisioning , 2004, Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..

[2]  Danny B. Lange,et al.  Seven good reasons for mobile agents , 1999, CACM.

[3]  Renato Roque,et al.  VESPER Project - Validation of VHE Concept , 2001 .

[4]  Jukka Riekki,et al.  Context-aware middleware for mobile multimedia applications , 2004, MUM '04.

[5]  James P. Black,et al.  Discovering Services Is Not Enough , 2004, IEEE Distributed Systems Online.

[6]  Eija Kaasinen,et al.  User needs for location-aware mobile services , 2003, Personal and Ubiquitous Computing.

[7]  Daniel P. Siewiorek,et al.  Determining User Location For Context Aware Computing Through the Use of a Wireless LAN Infrastructure , 2000 .

[8]  Zhixin Wang,et al.  Customizing and delivering mobile services using software agents and CC/PP , 2006, CCNC 2006. 2006 3rd IEEE Consumer Communications and Networking Conference, 2006..

[9]  Qusay H. Mahmoud,et al.  An Architecture and Business Model for Making Software Agents Commercially Viable , 2005, Proceedings of the 38th Annual Hawaii International Conference on System Sciences.

[10]  Marc M. Lankhorst,et al.  Enabling technology for personalizing mobile services , 2002, Proceedings of the 35th Annual Hawaii International Conference on System Sciences.