Problem
Research questions and friction points this paper is trying to address.
Low-cost sensor calibration
Indoor air quality monitoring
Spatial generalization
Temporal drift
Distribution shift
Low-Cost Sensor Calibration for Indoor Air Quality Monitoring: A Dataset, Evaluation Scenarios, and a Lightweight Model
🤖 AI Summary
This study addresses the inaccuracy of low-cost sensors in indoor air quality monitoring caused by nonlinear distortion, noise, and temporal drift, which render conventional calibration methods inadequate for spatiotemporal heterogeneity. We construct a multi-site dataset and introduce a novel four-dimensional evaluation framework encompassing spatial generalization and temporal robustness. Furthermore, this work proposes a lightweight temporal calibration model integrating input compression with residual mechanisms, combined with data augmentation and distribution shift mitigation techniques to achieve efficient feature fusion. Experimental results demonstrate that the proposed method attains high-precision calibration across complex scenarios while significantly reducing edge inference overhead and enhancing long-term stability.
📝 Abstract
Low-cost sensors enable scalable indoor air quality monitoring but require calibration because of nonlinear distortions, noise, and temporal drift. The conventional strict pairwise calibration setting requires a co-located reference sensor at each deployment location and does not account for spatial and temporal heterogeneity. To address these limitations, we introduce a six-month dataset comprising multivariate indoor air-quality measurements from low-cost and reference sensors with contextual metadata collected at five locations. Using this dataset, we define four evaluation scenarios. The reference-efficient and location-transfer scenarios evaluate spatial generalization, whereas the long-term drift and event-conditioned scenarios assess robustness to gradual and abrupt distribution shifts. Based on these scenarios, we derive design requirements and propose a lightweight temporal model that combines input-window compression with residual temporal and feature fusion. Experiments show strong calibration performance across all four scenarios with low edge-inference cost.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Low-cost sensor calibration
Lightweight temporal model
Input-window compression
Spatial generalization
Distribution shift robustness
🔎 Similar Papers
No similar papers found.
