%0 Journal Article
%A Gorospe, Joseba
%A Mulero, Rubén
%A Arbelaitz, Olatz
%A Muguerza, Javier
%A Antón, Miguel Ángel
%T A Generalization Performance Study Using Deep Learning Networks in Embedded Systems
%D 2021
%U http://hdl.handle.net/11556/1078
%X Deep learning techniques are being increasingly used in the scientific community as aconsequence of the high computational capacity of current systems and the increase in the amountof data available as a result of the digitalisation of society in general and the industrial world inparticular. In addition, the immersion of the field of edge computing, which focuses on integratingartificial intelligence as close as possible to the client, makes it possible to implement systems that actin real time without the need to transfer all of the data to centralised servers. The combination of thesetwo concepts can lead to systems with the capacity to make correct decisions and act based on themimmediately and in situ. Despite this, the low capacity of embedded systems greatly hinders thisintegration, so the possibility of being able to integrate them into a wide range of micro-controllerscan be a great advantage. This paper contributes with the generation of an environment based onMbed OS and TensorFlow Lite to be embedded in any general purpose embedded system, allowingthe introduction of deep learning architectures. The experiments herein prove that the proposedsystem is competitive if compared to other commercial systems.
%~