Abstract: In this talk, the challenges of human activity recognition and its application to elderly care / hospital domains are discussed.
We firstly review the demand in elderly care and hospital domains including the productivity of care workers. Then we introduce several approaches to forecast the future and utilize
them for improving productivity. We use various sensor data, video data, and care / medical records and integrate them. We also introduce several techniques to improve machine learning
in such a domain, including enhancing the algorithm using large language models. Finally, we introduce the deployment challenges cooperating with a startup company.
Bio: Sozo INOUE is a full professor in National Kyushu Institute of Technology, Japan, and the Chief Technical Officer of AUTOCARE LLC.
His research interests include human activity recognition with smart phones, and healthcare application of web/pervasive/ubiquitous systems. Currently he is working on applications
of activity recognition and health forecasting for nursing care and medicine to hospitals and more than 50 nursing facilities using smartphones and IoT. 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 has been appointed as an associate professor in the Faculty of
Engineering at Kyushu Institute of Technology, Japan, and moved to Graduate School of Life Science and Systems Engineering at Kyushu Institute of Technology in 2018, and appointed
as a full professor from 2020 and a head of Care XDX Center in Kyushu Institute of Technology from 2022. Meanwhile, he was a guest professor in Kyushu University, a visiting professor
at Karlsruhe Institute of Technology, Germany, in 2014, a special researcher at Institute of Systems, Information Technologies and Nanotechnologies (ISIT) during 2015-2016, and a
guest professor at University of Los Andes in Colombia in 2019. He was a technical advisor of Team AIBOD Co. Ltd during 2017-2019, and a guest researcher at RIKEN Center for Advanced
Intelligence Project (AIP) during 2017-2019. He was a director during 2020-2021 and is a senior member of the Information Processing Society of Japan (IPSJ), a member of the IEEE
Computer Society, the ACM, 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).