z-logo
open-access-imgOpen Access
Method for Behavior Normalization to Enable Comparative Understanding of Interactions of Elderly Persons with Consumer Products using a Behavior Video Database
Author(s) -
Kei Hirano,
Kohei Shoda,
Koji Kitamura,
Yusuke MIYAZAKI,
Yoshifumi Nishida
Publication year - 2019
Publication title -
procedia computer science
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.334
H-Index - 76
ISSN - 1877-0509
DOI - 10.1016/j.procs.2019.11.073
Subject(s) - computer science , normalization (sociology) , product (mathematics) , dementia , cluster analysis , cognition , rgb color model , database , artificial intelligence , human–computer interaction , psychology , medicine , mathematics , sociology , anthropology , geometry , disease , pathology , neuroscience
Consumer product safety for dementia sufferers is a global problem. To develop products that can be safely used by elderly people with degradation of physical and cognitive functions (e.g., people with dementia), it is necessary to measure the product use behavior of elderly people using them in various environments and quantitatively analyze behavioral changes during product use due to changes in the functions. Recent developments in smart home technology are opening a new path for quantifying the behavior of elderly people in daily environments. This proposes a new method for comparative understanding of the elderly’s interactions with consumer products. The method employs three functions: robust pose estimation, behavior normalization method, and clustering. This paper also describes the evaluation of the developed functions and report their application to analyzing an elderly behavior library, which is an RGB-D database for elderly product use in daily environments.

The content you want is available to Zendy users.

Already have an account? Click here to sign in.
Having issues? You can contact us here
Accelerating Research

Address

John Eccles House
Robert Robinson Avenue,
Oxford Science Park, Oxford
OX4 4GP, United Kingdom