메뉴 건너뛰기
.. 내서재 .. 알림
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)
로그인 회원가입 고객센터 ENG
주제분류

추천
검색
질문

논문 기본 정보

자료유형
학술대회자료
저자정보
Xiguan Liang (Sungkyunkwan University) Owen Anderton (Sungkyunkwan University) Doosam Song (Sungkyunkwan University)
저널정보
대한설비공학회 대한설비공학회 학술발표대회논문집 대한설비공학회 2023년도 하계학술발표대회 논문집
발행연도
2023.6
수록면
410 - 416 (7page)

이용수

표지
📌
연구주제
📖
연구배경
🔬
연구방법
🏆
연구결과
AI에게 요청하기
추천
검색
질문

초록· 키워드

오류제보하기
The accurate estimation of indoor occupancy is of utmost importance for maintaining energy efficiency and protecting occupants from infectious diseases. Traditional methods of occupancy detection, such as image recognition from webcams, are associated with expensive initial installation costs and raise concerns about personal privacy invasion. In this study, a low-cost, data-driven approach for predicting indoor occupancy based on CO₂ concentration is proposed as a means to accurately estimate realtime occupancy rates while avoiding human rights violations. The proposed method was tested in a university, where field measurements were taken, occupancy image data were recorded with the consent of subjects, and indoor and outdoor CO₂ concentration, temperature, and humidity data were collected in 3 months. An occupancy rate estimation model based on CO₂ concentration was created through deep learning. The deep learning models were built using a multivariate multi-step input approach using CO₂ concentration data and real-time occupancy data for this classroom. The results show that the LSTM model for occupancy prediction based on CO₂ concentration can accurately derive the relationship between indoor CO₂ concentration and the number of people and can effectively predict occupancy rate. In addition, the model was validated and analyzed in 16 different scenarios measured in the field.

목차

Abstract
1. Introduction
2. Methodology
3. Results and discussion
4. Conclusion
References

참고문헌 (0)

참고문헌 신청

함께 읽어보면 좋을 논문

논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!

최근 본 자료

전체보기

댓글(0)

0