Resolving context conflicts using Association Rules (RCCAR) to improve quality of context-aware systems

Context-aware systems (CASs) face many challenges to keep high quality performance. One challenge faces CASs is conflicted values come from different sensors because of different reasons. These conflicts affect the quality of context (QoC) and as a result the quality of service as a whole. This paper conducts a novel approach called RCCAR resolves the context conflicts and so contributes in improving QoC for CASs. RCCAR approach resolve context conflicts by exploiting the previous context using Association Rules (AR) to predict the valid values among different conflicted ones. RCCAR introduces an equation that evaluates the strength of prediction for different conflicted context elements values. The approach RCCAR has been implemented using Weka 3.7.7 and results show the success of the solution for different experiments applied to different scenarios designed to examine the solution according to different possible conditions.