Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series

TL;DR

This paper introduces TESLA, a Transformer-based model with logarithmic-binned attention, enabling real-time calibration of low-cost sensors for fine-grained time series, improving accuracy and efficiency in resource-constrained environments.

Contribution

The paper presents TESLA, a novel deep learning model that effectively calibrates low-cost sensors in real-time using logarithmic-binned attention within Transformer architecture.

Findings

TESLA outperforms existing models in accuracy.

TESLA achieves faster calibration speeds.

TESLA is more energy-efficient in hardware-constrained systems.

Abstract

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.