On-device learning for ultra-low-power wireless sensors: evaluating the effects of data subsampling - École Centrale de Lyon Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

On-device learning for ultra-low-power wireless sensors: evaluating the effects of data subsampling

Résumé

Integrating Artificial Intelligence (AI) into embedded systems is critical for the development of viable Ambient Intelligence (AmI). However, the energy requirements of current AI computations are not compatible with the limited resources of AmI devices and global sustainability goals. To address this issue, we propose using Federated Learning across multiple intermittent embedded systems to distribute data gathering, storage, and load balancing, thus enabling the system to assess and adapt appropriately to the environment. We initially focus on relevant real-world data acquisition to check the minimum data required by a local node in a federation. Our preliminary results demonstrate a direct correlation between signal decimation, a decrease in both training time and energy usage, and a collapsing threshold limit in accuracy.
Fichier principal
Vignette du fichier
GDR_SOC2_Colloque_2023_Antoine_Bonneau.pdf (1.51 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04110297 , version 1 (30-05-2023)

Identifiants

  • HAL Id : hal-04110297 , version 1

Citer

Antoine Bonneau, Fabien Mieyeville, Frédéric Le Mouël. On-device learning for ultra-low-power wireless sensors: evaluating the effects of data subsampling. Journées Colloque National du GDR SoC2, GDR SOC2; INL Lyon, Jun 2023, Lyon, France. ⟨hal-04110297⟩
49 Consultations
42 Téléchargements

Partager

Gmail Facebook X LinkedIn More