Title :
A normalized correlation estimator for complex data based on a quadruplex transformation
Author :
Sullivan, Mark C. ; Wegman, Edward J.
Author_Institution :
Information Syst. Lab. Inc., Vienna, VA, USA
Abstract :
The computational cost of estimating normalized correlations can be reduced by employing sums of simple nonlinear functions of the data. A quadruplex transformation is presented, and the performance of the associated estimator is analyzed for complex Gaussian processes. With independent observations, the variance of the estimator is approximately 14% higher than that of the conventional estimator.
Keywords :
Gaussian processes; computational complexity; correlation methods; signal processing; statistical analysis; complex Gaussian processes; complex data; computational cost; independent observations; nonlinear functions; normalized correlation estimator; quadruplex transformation; signal processing; variance; Computational efficiency; Digital signal processors; Gaussian processes; Heart; Performance analysis; Process design; Signal design; Signal processing; Taylor series; Throughput;
Journal_Title :
Signal Processing Letters, IEEE
