Particle Swarm Optimization and regression analysis – II

Document Type

Article

Publication Date

2012

Abstract

In the first part of this article, Particle Swarm Optimization (PSO) was applied to the problem of optimizing knot placement in the regression spline method. Although promising for broadband signals having smooth, but otherwise unknown, waveforms, this simple approach fails in the case of narrowband signals when the carrier frequency as well as the amplitude and phase modulations are unknown. A method is presented that addresses this challenge by using PSO based regression splines for the in-phase and quadrature amplitudes separately. It is thereby seen that PSO is an effective tool for regression analysis of a broad class of signals.

Comments

© 2012 Taylor & Francis. Original published version available at https://doi.org/10.1080/21672857.2012.11519708

Publication Title

Astronomical Review

DOI

10.1080/21672857.2012.11519708

Link to Full Text

Share

COinS