ETRI-Knowledge Sharing Plaform

ENGLISH

성과물

논문 검색
구분 SCI
연도 ~ 키워드

상세정보

학술대회 A Study on CNN-Based Berg Balance Scale Analysis for Elderly Persons
Cited 1 time in scopus Download 0 time Share share facebook twitter linkedin kakaostory
저자
이연수, 윤성재, 김원종
발행일
201906
출처
International Technical Conference on Circuits/Systems, Computers and Communications (ITC-CSCC) 2019, pp.252-253
DOI
https://dx.doi.org/10.1109/ITC-CSCC.2019.8793344
협약과제
19ZT1100, 수도권 지역산업기반 ICT융합기술 지원사업, 나중찬
초록
In this paper, we propose a method to analyze berg balance scale (BBS) for elderly persons using convolutional neural network (CNN). One of the main problem for elderly people is that their health is easily get deteriorated after a fall. The proposed CNN model predicts the BBS score of the elderly using sensors that can measure the motion pattern while performing activities of BBS. We developed two CNN models - one dimensional and two dimensional - to predict the score of BBS activities. The models predict the score between 0 to 4 with the accuracy of 90%. The proposed CNN models can be used to evaluate fall risk for elderly persons.
KSP 제안 키워드
CNN model, Convolution neural network(CNN), Elderly People, Elderly person, Motion Pattern, One-dimensional, berg balance scale, fall risk, scale analysis, two-dimensional(2D)