Edge-AI for Power reduction: Application to accelerometer sensors - Université Clermont Auvergne Accéder directement au contenu
Communication Dans Un Congrès Année : 2022

Edge-AI for Power reduction: Application to accelerometer sensors

Résumé

Edge-AI is the use of AI algorithms directly embedded on a device contrary to a remote AI which makes use of an AI on a cloud or remote server for prediction. Recent improvements in microcontroller computing capabilities along with deep learning algorithms conversion frameworks made it easier to run small models directly on microcontroller units. In this paper, we present how an embedded deep convolutional neural network can be used for real-time human activity recognition with +98% accuracy and extending battery life. Experiments conducted on an Arm Cortex-M4 showed that average power can be reduced up to 10% when inferences are run on edge vs using a remote server.
Fichier principal
Vignette du fichier
article_coc22.pdf (327.26 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04064256 , version 1 (11-04-2023)

Identifiants

  • HAL Id : hal-04064256 , version 1

Citer

Aimé Cedric Muhoza, Emmanuel Bergeret, Corinne Brdys, Francis Gary. Edge-AI for Power reduction: Application to accelerometer sensors. Colloque sur les Objets et systèmes Connectés - COC 2022, May 2022, Dakar, Senegal. ⟨hal-04064256⟩
31 Consultations
11 Téléchargements

Partager

Gmail Facebook X LinkedIn More