Human Activity Sensing and Applications to Medical and Caregiving Domains

Abstract

In this talk, we introduce activity recognition technology using mobile type sensors including smartphones and applications to medical and nursing fields. Although a lot of activity recognition technology has already been introduced, there are many challenges in collecting realistic datasets and developing algorithms for complicated and long­term activities. To this problem, from our research, we proposed a method [UbiComp2015] that uses prior knowledge of the activity segment of the day, and a method that automatically corrects when the timing of the labels are inaccurate [MobiQuitou2016]. We also proposed a method [MobiQuitous2016] that corrects differences among individuals by transfer learning. Along with these works, we talk about the future prediction of nursing work volume and patient prognosis in combination with medical data in the hospital[UBI16], and talk about the trial of recognizing whole staffs' activities in nursing homes for 4 months [UBI17].














































Avatar

Sozo Inoue

Sozo INOUE is an associate professor in Kyushu Institute of Technology, Japan. His research interests include human activity recognition with smart phones, and healthcare application of web/pervasive/ubiquitous systems. Currently he is working on verification studies in real field applications, and collecting and providing a large­scale open dataset for activity recognition, such as a mobile accelerator dataset with about 35,000 activity data from more than 200 subjects, nurses' sensor data combined with 100 patients' sensor data and medical records, and 34 households' light sensor data set for 4 months combined with smart meter data.

Inoue has a Ph.D of Engineering from Kyushu University in 2003. After completion of his degree, he was appointed as an assistant professor in the Faculty of Information Science and Electrical Engineering at the Kyushu University, Japan. He then moved to the Research Department at the Kyushu University Library in 2006. Since 2009, he is appointed as an associate professor in the Faculty of Engineering at Kyushu Institute of Technology, Japan. Meanwhile, he was a guest professor in Kyushu University, a visiting professor at Karlsruhe Institute of Technology, Germany, in 2014, and a special researcher at Institute of Systems, Information Technologies and Nanotechnologies (ISIT) during 2015­2016. He is a technical advisor of TeamAIBOD Co. Ltd since 2017, and a guest researcher at RIKEN Center for Advanced Intelligence Project (AIP).

He is a member of the IEEE Computer Society, the ACM, the Information Processing Society of Japan (IPSJ), the Institute of Electronics, Information and Communication Engineers (IEICE), the Japan Society for Fuzzy Theory and Intelligent Informatics, the Japan Association for Medical Informatics (JAMI), and the Database Society of Japan (DBSJ). Contact him at sozo@acm.org; 1­1 Sensui­cho, Tobata­ku, Kitakyushu, 804­8550, Japan.