Communication Dans Un Congrès Année : 2024

Real-Time Calibration Model for Low-Cost Sensor in Fine-Grained Time Series

Seokho Ahn
  • Fonction : Auteur
Hyungjin Kim
  • Fonction : Auteur
Sungbok Shin
  • Fonction : Auteur
  • PersonId : 1495069
Young-Duk Seo
  • Fonction : Auteur correspondant
  • PersonId : 1495070

Connectez-vous pour contacter l'auteur

Résumé

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 highperformance 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 hardwareconstrained systems. Experiments show that TESLA outperforms existing novel deep learning and newly crafted linear models in accuracy, calibration speed, and energy efficiency.

Fichier principal
Vignette du fichier
Tesla_AAAI25__Copy_____sharable_.pdf (1.46 Mo) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04906168 , version 1 (22-01-2025)

Identifiants

  • HAL Id : hal-04906168 , version 1

Citer

Seokho Ahn, Hyungjin Kim, Sungbok Shin, Young-Duk Seo. Real-Time Calibration Model for Low-Cost Sensor in Fine-Grained Time Series. AAAI 2025 - The 39th Annual AAAI Conference on Artificial Intelligence, AAAI - Association for the Advancement of Artificial Intelligence, Feb 2025, Philadelphia (PA), United States. ⟨hal-04906168⟩
0 Consultations
0 Téléchargements

Partager

More