Skip navigation

Distributing intelligence to the edge and beyond

Intelligent applications require that the intelligence is configured and distributed to the remote subsystems that might not always be connected. Distributed Machine Intelligence (D-MI) is therefore very important for IoT to achieve the IoT systems goals and comply with their requirements.
Research paper

Current D-MI deployments are limited by the lack of interoperability. Embedding intelligence in the applications tie them to the own application life management cycle, and in consequence updates or changes in intelligence results in updates to the applications and vice versa.

This article proposes a novel approach - decoupling the intelligence from the application by revising the traditional device’s stack and introducing an intelligence layer that provides services to the overlying application layer that enables also MI interoperability. Additionally, we explore several aspects related to the intelligence distribution and its impact in the whole MI ecosystem.

Full abstract in IEEE Xplore, DOI: 10.1109/MCI.2019.2937613

Authors: 

Edgar Ramos, Roberto Morabito, Jani-Pekka Kainulainen

Published in IEEE Computational Intelligence Magazine, Volume 14, Issue 4, Nov. 2019

© 2019 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse.