(Invited) Mobile Activity Recognition and Large-scale Healthcare Sensing

Sozo Inoue,
International Symposium on Advanced Intelligent Systems
(Not Available)
(Not Available)
2013-11-13
Daejeon, Korea
www.isis2013.org
Recent deployment of smart phones equipped with accelerometers will make it possible to recognize activities of the users. If human activity can be objectively measured, we can expect various applications. For example, lifestyle aspects can be quantified and used for prevention of lifestyle-related diseases. In that of agriculture, farmers can improve efficiency by automatically obtaining their own activity record. Moreover, in more domain specific application such as nursing management, nursing activity will be quantified and optimized for various type of process in hospitals.
In this new horizon of technology, we are facing challenges to realize mobile activity recognition. To realize mobile activity recognition, we need a wide variety of activity data with realistic settings. However, collecting such data from varieties of people is not easy, since it requires costs for managing data, time synchronization, and annotations of what kind of activities are done, to be utilized for (semi-) supervised machine learning.
In this talk, we talk the state of the art of mobile activity recognition, including collecting large-scale activity data using smart phone, challenges for realistic mobile activity recognition, and how to deal with the annotation problem. Moreover, we also introduce the research for large-scale nursing activity recognition with one-year nursing data, in which we tried to segment and annotate nursing activities from audio data and low-level activity recognition. We also address the healthcare application of mobile sensing to massive people in Bangladesh.

Data Files

No records to display