A Practical Approach To Higher-Order Statistics. An Application to Electrical Transients Characterization

Author

De la Rosa, Juan José González ; Moreno, Antonio ; Puntonet, Carlos G.

Author_Institution

Univ. of Cadiz-Cordoba, Algeciras

fYear

2007

fDate

3-5 Oct. 2007

Firstpage

1

Lastpage

6

Abstract

In this paper we perform a practical review on higher- order statistics interpretation. Concretely we focus on an unbiased estimate of the 4th-order time-domain cumulants. Some synthetics involving classical noise processes are characterized using this unbiased estimate, with the goal of checking its performance and to provide the scientific community with another result, dealing with the interpretation of this signal processing tool. A real practical example is presented in the field of electrical power quality event analysis. The work also aims to present a set of general advice in order to save memory and gain speed in a real signal processing frame, dealing with non-stationary processes.

Keywords

filtering theory; higher order statistics; power supply quality; power system analysis computing; power system transients; 4th-order time-domain cumulant; classical noise process; electrical power quality event analysis; electrical transient characterization; filtering theory; higher-order statistics; neural network; signal processing; Autocorrelation; Fourier transforms; Higher order statistics; Phase noise; Power quality; Random processes; Signal analysis; Signal processing; Time domain analysis; Transient analysis; Electrical transients; Higher-Order statistics; Neural networks; Power quality;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Signal Processing, 2007. WISP 2007. IEEE International Symposium on

Conference_Location

Alcala de Henares

Print_ISBN

978-1-4244-0829-0

Electronic_ISBN

978-1-4244-0830-6

Type

conf

DOI

10.1109/WISP.2007.4447547

Filename

4447547