| 학회 |
한국화학공학회 |
| 학술대회 |
2022년 봄 (04/20 ~ 04/23, 제주국제컨벤션센터) |
| 권호 |
28권 1호, p.1127 |
| 발표분야 |
[주제 12] 화학공학일반(부문위원회 발표) |
| 제목 |
Gated Probabilistic Transformer기반 실내공간 미세먼지 건강리스크 지표 및 예측 모델링 |
| 초록 |
Indoor environment quality (IEQ) at subway stations is a complex system comprised of several factors with extremely non-linear patterns. To achieve sustainable IEQ levels accurate identification of future fine particulate matter (PM2.5) levels is crucial. However, numerous statistical and neural network models perform poorly to generate an accurate early warning mostly because of their deterministic nature. The current study presents a genetic algorithm enhanced gated transformer model for probabilistic forecasting of PM2.5 levels at a subway platform up to five hours ahead. The proposed framework surpasses numerous combinations of traditional time series models in terms of prediction interval probability and Winkler scores. In comparison to the deterministic model, missed health risk alarms were reduced by up to 72%. Acknowledgments This research was supported by a grant from the National Research Foundation of Korea (NRF) funded by the Korean government (MSIT) (No. 2021R1A2C2007838), and from the Subway Fine Dust Reduction Technology Project of the Ministry of Land Infrastructure and Transport from the Republic of Korea (21QPPW-B152306-03). |
| 저자 |
Tariq Shahzeb1, 김상윤2, 유창규2
|
| 소속 |
1KyungHee Univ., 2경희대 |
| 키워드 |
공정시스템(Process Systems Engineering) |
| E-Mail |
|
| 원문파일 |
초록 보기 |
