Guardado en:
Detalles Bibliográficos
Autores principales: Ahn, Seokho, Kim, Hyungjin, Shin, Sungbok, Seo, Young-Duk
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:https://arxiv.org/abs/2412.20170
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866917881457934336
author Ahn, Seokho
Kim, Hyungjin
Shin, Sungbok
Seo, Young-Duk
author_facet Ahn, Seokho
Kim, Hyungjin
Shin, Sungbok
Seo, Young-Duk
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20170
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series
Ahn, Seokho
Kim, Hyungjin
Shin, Sungbok
Seo, Young-Duk
Machine Learning
Artificial Intelligence
Signal Processing
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.
title Real-time Calibration Model for Low-cost Sensor in Fine-grained Time series
topic Machine Learning
Artificial Intelligence
Signal Processing
url https://arxiv.org/abs/2412.20170