Improving activity recognition by segmental pattern mining

Activity recognition is a key task for the development of advanced and effective ubiquitous applications in fields like Ambient Assisted Living. Most automated approaches for the task fail to incorporate dependencies between non-close time instants. In this paper we present a simple approach for introducing longer-range interactions based on sequential pattern mining. The algorithm searches for patterns characterizing time segments during which the same activity is performed. Novel sequences are tagged according to matches of the extracted patterns. An experimental evaluation shows that enriching sensor-based representations with the mined patterns allows improving results of sequential and segmental labeling algorithms on most of the cases.