.png){kind=icon}
.png){kind=icon}
Return
Two-stage deep learning framework for reliable PM2.5 soft sensing in schools: Integrated fault reconstruction and prediction
.png){kind=icon}
PRE
AI
H
A
Y
DOI：10.1016/j.apr.2026.103102.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
• A two-stage DL soft-sensor developed for accurate, fault-tolerant PM2.5 monitoring. • RCAE reconstructed faulty air quality input data, reducing MSE from 36.3 to 0.29. • CNN-LSTM with attention mechanism achieved PM2.5 prediction accuracy of 99.3%. • PM2.5 prediction using calibrated data improved accuracy by 78.4% over faulty data. • The proposed framework enables smart PM2.5 sensing for healthy school environment.
Journal
IF:
3.5
Papers:
3.0K
Citations:
7.4K
Organization
Cited Papers