Low-Cost Sensor Calibration for Indoor Air Quality Monitoring: A Dataset, Evaluation Scenarios, and a Lightweight Model
The study proposes a lightweight temporal model to calibrate low-cost indoor air quality sensors using a six-month dataset from five locations. The model is designed to be robust against various calibration challenges, including limited reference data and long-term sensor drift. Experimental results show the model performs well across multiple demanding scenarios while maintaining low computational cost for deployment on resource-constrained devices.