메뉴 건너뛰기
소속 기관 / 학교 인증
인증하면 논문, 학술자료 등을  무료로 열람할 수 있어요.
한국대학교, 누리자동차, 시립도서관 등 나의 기관을 확인해보세요
(국내 대학 90% 이상 구독 중)
고객센터 ENG
주제분류

논문 기본 정보

저자정보
(Seoul National University of Science and Technology) (Seoul National University of Science and Technology) (Seoul National University of Science and Technology) (Seoul National University of Science and Technology)
저널정보
한국HCI학회 한국HCI학회 학술대회 PROCEEDINGS OF HCI KOREA 2025 학술대회 발표 논문집
오류 신고하기

피인용 0

검색

    초록·키워드

    In modern society, psychological stress negatively impacts health and productivity in workplaces. In terms of organization management, effective stress management for employees is becoming crucial. However, workplace characteristics, such as fear of being perceived as incompetent and lack of trust in management often lead employees to conceal their stress. One of the promising methods for recognizing stress levels involving involuntary stress response is tracking changes in remote photoplethysmography (rPPG) of blood volume pulse signals. In this study, we propose a deep learning model that utilizes rPPG signals both neutral and stress state to identify stress levels. We demonstrate that incorporating neutral state signals reduces sensitivity to individual physiological differences and accurately captures relative stress-induced changes, enhancing generalization performance. To the end, the findings of this study aim to suggest a deep learning model for remote stress level recognition considering both neutral and stress state could support stress management systems in future study.

    최근 본 자료 전체보기