Uma comparação entre técnicas adaptativas baseadas em grafos

Daniel Gilio Tiglea, Renato Candido, Magno T. M. Silva. Uma comparação entre técnicas adaptativas baseadas em grafos. In: Simpósio Brasileiro de Telecomunicações – SBrT’2018, 2018, Campina Grande. Anais do SBrT 2018, 2018, pp.1–5 (available only in portuguese).


Graph signal processing has been gaining widespread attention within the scientific community, due to the fact that it is an effective tool to deal with great quantities of interrelated data. Applications include communication networks, image analysis, temperature estimation, etc. Recently, two adaptive solutions based on the LMS (least-mean-squares) algorithm have been proposed. In this article, they are revisited and compared through computer simulations. It is shown that one of them has more difficulty keeping track of variations in the signal, which makes the selection of its adaptive step more difficult.


Graphs, Signal Processing, Adaptive Filtering, LMS Algorithm.