Activity Recognition in Ubiquitous Learning Environment

With the advance and the development of sensors, computing devices and wireless communication networks, ubiquitous computing has been an active and fast growing research area. The technology is applied in educational domain, resulting in ubiquitous learning, in which the system can detect the students’ behavior and provide personalized support to guide the students to learn in real world. This paper focuses on activity recognition in ubiquitous learning environment which assists the novice user to conduct a complex experiment. Here the activity is a kind of complex activity which is an independent task to achieve a certain goal and is composed of simple actions. The approach we propose is knowledge-driven technique. We first present concepts of context pattern and context evolving pattern, and based on these concepts define the activity model. Then we analyze the condition of distinguishable activity and propose the algorithm of activity recognition. Activity model in single-crystal X-ray diffraction experiment support system is designed and the method is further interpreted through this case.