AFFLUENT CONTEXT AWARE SYSTEMS BASED ON THE USER BEHAVIOR IN MOBILE-PERVASIVE COMPUTING ENVIRONMENT

H Shaheen, Dr Karthik
2014 Journal of Theoretical and Applied Information Technology   unpublished
A huge number of embedded devices offer their services to the end users in pervasive environments. Context-aware discovery is a rich and very dynamic system extensively applied for combining the different mobile devices, sensors, actuators and software functions. Existing knowledge-based system using the Common KADS (CKADS) system represent contextual information but algorithm are not effective in predicting the user behavior. Current Location-aware Private Service Discovery (LPSD) considers
more » ... discovery path for reducing the distributed topology and flooding operations. LPSD in pervasive environment is not effective in accurately locating the required service by searching method. To present an architecture principle for accurately predicting the user behavior in mobile-pervasive computing environment, Affluent Context Aware Systems based on the User Behavior (ACAS-UB) is proposed in this paper. ACAS-UB mechanism contains the class of mobile devices that can sense (i.e.,) search the physical pervasive environment. Affluent means effectively engaged mobile devices in ACAS-UB mechanism which uses the context information. The ACAS-UB context information contains the judgment of the similar users and also the response from the other users for improving the effectiveness in pervasive environment user behavior prediction. Master-slave concept is used in the ACAS-UB mechanism for the easy collection of response information from the different users. ACAS-UB mechanism construct the user profile initially from the context information, then performs the similarity measure and finally work is to predict the user behavior. ACAS-UB mechanism provides the hints which are necessary to explore different options, rather than just limiting the options in mobile-pervasive computing environment. ACAS-UB mechanism is experimented on the factors such as message overhead in pervasive environment, scalability and approximately 10 % lesser processing time.
fatcat:o67ol34edrgg7d2im2vjyvs2xm