Semantic segmentation of real-time sensor data stream for complex activity recognition

Data segmentation plays a critical role in performing human activity recognition in the ambient assistant living systems. It is particularly important for complex activity recognition when the events occur in short bursts with attributes of multiple sub-tasks. Although substantial efforts have been made in segmenting the real-time sensor data stream such as static/dynamic window sizing approaches, little has been explored to exploit object semantic for discerning sensor data into multiple threads of activity of daily living. This paper proposes a semantic-based approach for segmenting sensor data series using ontologies to perform terminology box and assertion box reasoning, along with logical rules to infer whether the incoming sensor event is related to a given sequences of the activity. The proposed approach is illustrated using a use-case scenario which conducts semantic segmentation of a real-time sensor data stream to recognise an elderly persons complex activities.