Sensor Calibration Model Balancing Accuracy, Real-time, and Efficiency

TL;DR

This paper introduces Scare, an ultra-compressed transformer model for sensor calibration that balances accuracy, real-time performance, and efficiency by decomposing the traditional requirements into eight microscopic criteria, and demonstrates its effectiveness on large-scale datasets and microcontroller deployments.

Contribution

The paper presents a novel transformer-based sensor calibration model that meets all eight microscopic deployment requirements, unlike previous models that only consider macroscopic criteria.

Findings

Scare outperforms existing baselines on large-scale air-quality datasets.

It maintains high accuracy while minimizing computational overhead.

Successfully deploys on microcontroller units (MCUs).

Abstract

Most on-device sensor calibration studies benchmark models only against three macroscopic requirements (i.e., accuracy, real-time, and resource efficiency), thereby hiding deployment bottlenecks such as instantaneous error and worst-case latency. We therefore decompose this triad into eight microscopic requirements and introduce Scare (Sensor Calibration model balancing Accuracy, Real-time, and Efficiency), an ultra-compressed transformer that fulfills them all. SCARE comprises three core components: (1) Sequence Lens Projector (SLP) that logarithmically compresses time-series data while preserving boundary information across bins, (2) Efficient Bitwise Attention (EBA) module that replaces costly multiplications with bitwise operations via binary hash codes, and (3) Hash optimization strategy that ensures stable training without auxiliary loss terms. Together, these components minimize computational overhead while maintaining high accuracy and compatibility with microcontroller units (MCUs). Extensive experiments on large-scale air-quality datasets and real microcontroller deployments demonstrate that Scare outperforms existing linear, hybrid, and deep-learning baselines, making Scare, to the best of our knowledge, the first model to meet all eight microscopic requirements simultaneously.