Marcus Vinicius Lopes

Marcus Vinicius Lopes

Research scientist obtained her Master’s degree in Electrical Engineering from the Universidade Federal do Maranhão in 2013. Doctor of Electrical Engineering in the same School. Her research interests include Signal Processing, Fuzzy Logic, Machine Learning, Big Data, Electronics, Instrumentation and Aerospace

A Non-Quadratic Algorithm Based on the Extended Recursive Least Squares Algorithm

Published in IEEE Signal Processing Letters, 2018

Recommended citation: AMARAL, Luis Fernando Coelho; LOPES, Marcus Vinicius ; BARROS, Allan Kardec. A Non-Quadratic Algorithm Based on the Extended Recursive Least Squares Algorithm. IEEE Signal Processing Letters, v. 3, p. 1-1, 2018. http://dx.doi.org/10.1109/lsp.2018.2864609

Abstract

In adaptiveg filters, several recursive algorithms have been used to track state-space model vectors in nonstationary environments. So far, kernel recursive algorithms showed the best results in this regard. With this letter, we aim to propose an algorithm based on a nonlinear function of the error, motivated by the extended recursive least-squares algorithm. Simulations were performed on the problem of tracking a nonlinear Rayleigh fading multipath channel and on a system identification. The results showed that the proposed algorithm can overcome the extended kernel version ones.