14 December 2015 A new coefficient of concordance with applications to biosignal analysis
Author Affiliations +
Proceedings Volume 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications; 981525 (2015) https://doi.org/10.1117/12.2210993
Event: Ninth International Symposium on Multispectral Image Processing and Pattern Recognition (MIPPR2015), 2015, Enshi, China
Abstract
In this paper we propose a novel concordance coefficients called Order Statistics Concordance Coefficients based on order statistics and Pearson's Product Moment Correlation Coefficient. For comparison, we also construct other three similar index based on Average Pearson's Product Moment Correlation Coefficient, Kendall's Concordance Coefficients, Average Kendall's tau. We propose Multivariate Normal Model to estimate the correlation coefficient, Linear Model and Nonlinear Model to model the linear and nonlinear association between multichannel signals, And we also apply the concordance coefficients to biosignal analysis developed a new organizational index for quantifying organization of AF. Statistical evidences suggest that (a) Order Statistics Concordance Coefficients have better robust than other three index; (b) capable of distinguishing fibrillatory rhythms from nonfibrillatory rhythms, such as Atiral flutter; (c) can reflect the effectiveness of adenosine, a drug commonly used during electrophysiological procedures; and (d) perform better than other three concordance coefficients.
© (2015) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Weichao Xu, Weichao Xu, Zhaoguo Chen, Zhaoguo Chen, Wenqing Liu, Wenqing Liu, } "A new coefficient of concordance with applications to biosignal analysis", Proc. SPIE 9815, MIPPR 2015: Remote Sensing Image Processing, Geographic Information Systems, and Other Applications, 981525 (14 December 2015); doi: 10.1117/12.2210993; https://doi.org/10.1117/12.2210993
PROCEEDINGS
9 PAGES


SHARE
Back to Top