In this paper, we propose a normalized least mean squares algorithm with variable step size with low computational cost, and only three parameters that are simple to choose.
Research
New paper: An Adaptive Algorithm for Sampling over Diffusion Networks with Dynamic Parameter Tuning and Change Detection Mechanisms
Recently, we proposed a sampling algorithm for diffusion networks that locally adapts the number of nodes sampled according to the estimation error. In this paper, we extend the results, proposing some improvements to the algorithm.
Papers published in SBrT 2021
Simpósio Brasileiro de Telecomunicações (SBrT) is the most important brazilian symposium on telecommunications and signal processing. In the 2021 edition, that happened from September 26th to 29th, we had 4 papers published:
New paper: A Sampling Algorithm for Diffusion Networks
Conference paper presented on the 28th European Signal Processing Conference (EUSIPCO) in which we propose an adaptive sampling method for the diffusion networks.
New paper: A Low-Cost Algorithm for Adaptive Sampling and Censoring in Diffusion Networks
This paper summarizes the results obtained by Daniel G. Tiglea during the period he was working to obtain the M.S. Degree.
New paper: An Adaptive Sampling Technique for Graph Diffusion LMS Algorithm
Conference paper presented on the 27th European Signal Processing Conference (EUSIPCO) in which we propose an adaptive sampling method for the diffusion algorithm for adaptively learning from streaming graphs signals.
New paper: Equalization in chaos-based communication systems using kernel adaptive filtering
As an extension to the paper presented at SPS 2017 (in portuguese), we present a study on the use of kernel adaptive filters for channel equalization in a chaos-based communication system.