Distributed clique-based neural networks for data fusion at the edge - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2020

Distributed clique-based neural networks for data fusion at the edge

Résumé

Distributed smart sensors are more and more used in applications such as biomedical or domestic monitoring. However, each sensor broadcasts data wirelessly to the others or to an aggregator, which leads to energy-hungry sensors not ensuring data privacy. To tackle both challenges, this work proposes to distribute a part of a clique-based neural network in each sensor. This scheme allows standardizing data at the sensor level, ensuring privacy if the data is intercepted. Besides, a lower number of bits is transmitted, thus limiting the communication overhead. The circuit implementation is possible with the use of single-cluster iterative clique-based circuits.
Fichier non déposé

Dates et versions

hal-03582290 , version 1 (21-02-2022)

Identifiants

  • HAL Id : hal-03582290 , version 1

Citer

Benoit Larras. Distributed clique-based neural networks for data fusion at the edge. 14ème Ecole d'hiver Francophone sur les Technologies de Conception des Systèmes Embarqués Hétérogènes, FETCH 2020, Feb 2020, Montréal, QC, Canada. ⟨hal-03582290⟩
14 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More