Guardado en:
| Autores principales: | , , , |
|---|---|
| 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 |