Context-aware inference in ubiquitous residential environments

•We develop a framework of sensor-based context-aware system in a residential environment.•The URE constitutes three layers of context node, behaviour node and service node.•The system utilizes a mixed inference method comprising of three reasoning processes.•The reasoning methods could be applied selectively according to the situation.•The unique reasoning is pattern driven inference to focus on residents’ behaviour. Residential ubiquitous computing environments have focused on interconnecting environmental controls using a home network and the management of sensor data rather than a context-aware inference. Building upon previous research, this paper proposes a novel sensor-based context-aware system with a focus on three inference processes: rule, inference and pattern driven. Using pattern data derived from five families for a working week and establishing rules and inferences, the proposed context-aware system is demonstrated using electrical lighting as an example. The processes to develop an intelligent house are described so as to ameliorate personalized services in response to inhabitants’ needs.