Sensor Calibration Model Balancing Accuracy, Real-time, and Efficiency
This addresses deployment bottlenecks in sensor calibration for resource-constrained devices like microcontrollers, though it is incremental as it builds on existing transformer and compression methods.
The paper tackles the problem of on-device sensor calibration by decomposing accuracy, real-time, and efficiency into eight microscopic requirements, and introduces Scare, an ultra-compressed transformer that outperforms existing baselines in experiments on air-quality datasets and microcontroller deployments.
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.