Complex correntropy function: properties, and application to a channel equalization problem

The use of correntropy as a similarity measure has been increasing in dif ferent scenarios due to the well-known ability to extract high-order statistic information from data. Recently, a new similarity measure between complex random variables was defined and called complex correntropy. Based on a G...

Full description

Bibliographic Details
Authors: Guimarães, João P. F., Fontes, Aluisio I. R., Rego, Joilson Batista de Almeida, Martins, Allan de Medeiros, Principe, J.C.
Format: article
Status:Published version
Publication Date:2018
Country:Brasil
Institution:Universidade Federal do Rio Grande do Norte (UFRN)
Repository:Repositório Institucional da UFRN
Language:English
OAI Identifier:oai:repositorio.ufrn.br:123456789/30942
Online Access:https://repositorio.ufrn.br/handle/123456789/30942
Access Level:Open access
Keyword:Channel equalization
Complex-valued data
Correntropy
Fixed-point algorithm
Maximum complex correntropy criterion
Properties
Description
Summary:The use of correntropy as a similarity measure has been increasing in dif ferent scenarios due to the well-known ability to extract high-order statistic information from data. Recently, a new similarity measure between complex random variables was defined and called complex correntropy. Based on a Gaussian kernel, it extends the benefits of correntropy to complex-valued data. However, its properties have not yet been formalized. This paper studies the properties of this new similarity measure and extends this defini tion to positive-definite kernels. Complex correntropy is applied to a channel equalization problem as good results are achieved when compared with other algorithms such as the complex least mean square (CLMS), complex recursive least squares (CRLS), and least absolute deviation (LAD)