LSTM with time-lagged features and harmonic encodings calibrates low-cost sensors to higher R2 and regulatory-compliant uncertainties of 9.1-22.11% for three pollutants.
Band-sensitive calibration of low-cost pm2. 5 sensors by lstm model with dynamically weighted loss function,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
A temporal deep learning framework for calibration of low-cost air quality sensors
LSTM with time-lagged features and harmonic encodings calibrates low-cost sensors to higher R2 and regulatory-compliant uncertainties of 9.1-22.11% for three pollutants.