Circular Correntropy: Definition and Application in Impulsive Noise Environments

被引:2
作者
Aquino, Manoel B. L. [1 ,2 ]
Guimaraes, Joao P. F. [1 ,2 ]
Fontes, Aluisio I. R. [1 ,2 ]
Linhares, Leandro L. S. [3 ]
Rego, Joilson B. A. [2 ,4 ]
Martins, Allan De M. [2 ,4 ]
机构
[1] Fed Inst Rio Grande do Norte IFRN, Dept Informat, BR-59015000 Pau Dos Ferros, RN, Brazil
[2] Fed Univ Rio Grande do Norte UFRN, BR-59078970 Natal, RN, Brazil
[3] Fed Inst Educ Sci & Technol Paraiba, BR-58900000 Joao Pessoa, Cajazeiras, Brazil
[4] Univ Fed Rio Grande do Norte, Dept Comp Engn & Automat, BR-59078900 Natal, RN, Brazil
关键词
Kernel; Random variables; Correlation; Pollution measurement; Noise measurement; Particle measurements; Mathematical models; Circular correntropy; circular statistics; correntropy; directional statistics; MAXIMUM CORRENTROPY; STATISTICS; SIGNALS; DOA;
D O I
10.1109/ACCESS.2022.3178423
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Circular statistics has been applied to several areas of knowledge in which the input data is circular or directional. Noisy measurements are still a problem in circular data applications and, like non-circular data, second-order statistics have some limitations to deal with non-Gaussian noise. Recently, a similarity function called correntropy has been successfully employed in applications involving impulsive noise for being capable of extracting more information than second-order methods. However, correntropy has not been studied from the perspective of circular data so far. This paper defines a novel statistical measure called circular correntropy (CC). It uses the von Mises density function in order to redefine correntropy in this domain. In particular, it is proved analytically that the CC contains information regarding second-order and higher-order moments, being a generalization of the circular correlation measure. The performance of this novel similarity measure is evaluated as a cost function in a nonlinear regression problem, where the signals are contaminated with additive impulsive noise. The simulations demonstrate that the CC is more robust than circular correlation in impulsive noise environments.
引用
收藏
页码:58777 / 58786
页数:10
相关论文
共 46 条
[1]   Robust estimation for circular data [J].
Agostinelli, Claudio .
COMPUTATIONAL STATISTICS & DATA ANALYSIS, 2007, 51 (12) :5867-5875
[2]   Some New Robust Estimators for Circular Logistic Regression Model with Applications on Meteorological and Ecological Data [J].
Alshqaq, Shokrya S. ;
Ahmadini, Abdullah A. ;
Abuzaid, Ali H. .
MATHEMATICAL PROBLEMS IN ENGINEERING, 2021, 2021
[3]  
[Anonymous], 2020, INMET WEATHER STATIO
[4]  
Araujo I. B., 2019, J CONTROL AUTOM ELEC, V30, P1
[5]   EEG signal classification of imagined speech based on Riemannian distance of correntropy spectral density [J].
Bakhshali, Mohamad Amin ;
Khademi, Morteza ;
Ebrahimi-Moghadam, Abbas ;
Moghimi, Sahar .
BIOMEDICAL SIGNAL PROCESSING AND CONTROL, 2020, 59
[6]   Using circular statistics to analyse time patterns in crime incidence [J].
Brunsdon, Chris ;
Corcoran, Jon .
COMPUTERS ENVIRONMENT AND URBAN SYSTEMS, 2006, 30 (03) :300-319
[7]   Statistical modelling of directional wind speeds using mixtures of von Mises distributions:: Case study [J].
Carta, Jose A. ;
Bueno, Celia ;
Ramirez, Penelope .
ENERGY CONVERSION AND MANAGEMENT, 2008, 49 (05) :897-907
[8]   APPLICATION OF CIRCULAR STATISTICS TO THE STUDY OF NEURONAL DISCHARGE DURING LOCOMOTION [J].
DREW, T ;
DOUCET, S .
JOURNAL OF NEUROSCIENCE METHODS, 1991, 38 (2-3) :171-181
[9]  
Fisher N. I., 1983, OXFORD U PRESS BEHAL, V70, P27
[10]  
Fisher N. I., 1993, Statistical Analysis of Spherical Data