S
Sozo Inoue
Researcher at Kyushu Institute of Technology
Publications - 177
Citations - 1702
Sozo Inoue is an academic researcher from Kyushu Institute of Technology. The author has contributed to research in topics: Activity recognition & Computer science. The author has an hindex of 17, co-authored 167 publications receiving 1315 citations. Previous affiliations of Sozo Inoue include LSI Corporation & Kyushu University.
Papers
More filters
Journal ArticleDOI
Deep recurrent neural network for mobile human activity recognition with high throughput
TL;DR: A method of human activity recognition with high throughput from raw accelerometer data applying a deep recurrent neural network (DRNN) is proposed, and various architectures and its combination to find the best parameter values are investigated.
Proceedings ArticleDOI
HASC Challenge: gathering large scale human activity corpus for the real-world activity understandings
Nobuo Kawaguchi,Nobuhiro Ogawa,Yohei Iwasaki,Katsuhiko Kaji,Tsutomu Terada,Kazuya Murao,Sozo Inoue,Yoshihiro Kawahara,Yasuyuki Sumi,Nobuhiko Nishio +9 more
TL;DR: A project to collect a large scale human activity corpus based on small number of test subjects, and not well adapted for real world applications, and developed a tool for management, evaluation and collection of the large number of activity sensor data.
RFID Privacy Using User-Controllable Uniqueness
TL;DR: Two approaches to protect privacy in the 'Digitally Named World' are proposed, which attempt to give users the controllability of the uniqueness of IDs from local to global, thereby enabling IDs private or public ones in the required stage of the object's life cycle.
Journal ArticleDOI
Supporting Colocated Interactions Using RFID and Social Network Displays
TL;DR: DeaiExplorer uses RFID technology to dynamically derive interconnected social clusters from a publication database and reveals these social networks on a display, letting colocated conference participants discover interpersonal connections.
Posted Content
Deep Recurrent Neural Network for Mobile Human Activity Recognition with High Throughput
TL;DR: In this article, the authors proposed a method of human activity recognition with high throughput from raw accelerometer data applying a deep recurrent neural network (DRNN), and investigate various architectures and its combination to find the best parameter values.