Reasoning on data streams: An approach to adaptation in pervasive systems

Urban environments are increasingly invaded by devices that acquire sensor information and pave the way for innovative forms of context awareness. Collecting knowledge from loosely-structured data streams and reasoning about changes are two key elements of the process. This paper illustrates a possible way to combine these two elements in a coordinated way. We make use of a recently-developed framework for classifying data streams with service-oriented, reconfigurable components. Furthermore, we embed the KnowLang Reasoner, allowing logical and statistical reasoning on the acquired knowledge aiming to achieve self-adaptation.