Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series
This addresses calibration challenges for low-cost sensor systems, offering improved performance in hardware-constrained environments, though it appears incremental as it builds on existing deep learning techniques.
The paper tackles the problem of inaccurate measurements from low-cost sensors by developing TESLA, a Transformer-based model with logarithmic-binned attention for real-time calibration, which outperforms existing methods in accuracy, speed, and energy efficiency.
Precise measurements from sensors are crucial, but data is usually collected from low-cost, low-tech systems, which are often inaccurate. Thus, they require further calibrations. To that end, we first identify three requirements for effective calibration under practical low-tech sensor conditions. Based on the requirements, we develop a model called TESLA, Transformer for effective sensor calibration utilizing logarithmic-binned attention. TESLA uses a high-performance deep learning model, Transformers, to calibrate and capture non-linear components. At its core, it employs logarithmic binning to minimize attention complexity. TESLA achieves consistent real-time calibration, even with longer sequences and finer-grained time series in hardware-constrained systems. Experiments show that TESLA outperforms existing novel deep learning and newly crafted linear models in accuracy, calibration speed, and energy efficiency.