Mining Emerging Patterns for Activity Recognition

With the rapid advances of sensors and wireless networks, recognizing human activity based on sensor readings has been recently attracting much research interest in the pervasive computing community. A typical application is monitoring activities for the elderly and cognitively impaired people, and providing them with proactive assistance. In real life, people perform activities in not only a sequential manner (i.e., performing one activity after another), but also an interleaved (i.e., switching between the steps of two or more activities) or concurrent manner (i.e., performing two or more activities simultaneously). Recognizing activities in such a complex situation is important not only for meeting real life needs but also for advancing the field of pervasive computing.