Performance evaluation of hybrid ANN based time series prediction on embedded processor

Rafael Trapani Possignolo, Omar Hammami

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Complex embedded systems application exhibit time-varying workload which requires continuous resource adaptivity. Workload prediction has been successfully achieved through a hybrid model of NARX Recurrent Neural Networks combined with Self Organizing Map (SOM). This paper presents the performance evaluation of this hybrid time series prediction on embedded processors as an alternative to dedicated hardware. Achieved results demonstrate the potential of this approach for heavy workloads such as parallel applications. This solution is prone to extension to MPSOC.

Original languageEnglish
Title of host publicationProceedings - 2010 1st IEEE Latin American Symposium on Circuits and Systems, LASCAS 2010
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages204-207
Number of pages4
ISBN (Electronic)9781509020768
DOIs
Publication statusPublished - 17 Feb 2016
Event1st IEEE Latin American Symposium on Circuits and Systems, LASCAS 2010 - Foz do Iguacu, Brazil
Duration: 24 Feb 201026 Feb 2010

Publication series

NameProceedings - 2010 1st IEEE Latin American Symposium on Circuits and Systems, LASCAS 2010

Conference

Conference1st IEEE Latin American Symposium on Circuits and Systems, LASCAS 2010
Country/TerritoryBrazil
CityFoz do Iguacu
Period24/02/1026/02/10

Keywords

  • ANN
  • MPSOC
  • SOC
  • embedded
  • processor
  • time series

Fingerprint

Dive into the research topics of 'Performance evaluation of hybrid ANN based time series prediction on embedded processor'. Together they form a unique fingerprint.

Cite this