Validating Context Information in Context Aware Systems

Abstract

Context-aware computing refers to a general class of computing systems that can sense their physical environment and adapt their behavior accordingly. In order to behave properly, such systems rely on valid and reliable context information. Therefore concepts for validating the correctness of context data are required. In our previous research we have introduced the Context Pattern Method (CPM) that calculates the probability of correctness measure, which quantifies the belief that the context information is correct and reliable. In this paper we use the CPM method and two well known statistical classification methods, Linear Discriminant Analysis (LDA) and the Support Vector Machines (SVM), to validate the context information and compare their performances under different conditions.