Optimal Knot Selection for Least-squares Fitting of Noisy Data with Spline Functions.

Blair, J.

Technical Information Center Oak Ridge Tennessee

关键词: Least squares fitting;    Noisy data;    Spline functions;    Algorithms;    Digital oscilloscopes;   

RP-ID  :  DE2008935721

学科分类：工程和技术（综合）

美国|英语

来源: National Technical Reports Library

【 摘 要 】

An automatic data-smoothing algorithm for data from digital oscilloscopes is described. The algorithm adjusts the bandwidth of the filtering as a function of time to provide minimum mean squared error at each time. It produces an estimate of the root-mean-square error as a function of time and does so without any statistical assumptions about the unknown signal. The algorithm is based on least-squares fitting to the data of cubic spline functions.