Optimal knot selection for least-squares fitting of noisy data with spline functions

Author

Blair, Jerome

Author_Institution

Nat. Security Technol., LLC, Las Vegas, NV

fYear

2008

fDate

12-15 May 2008

Firstpage

27

Lastpage

32

Abstract

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.

Keywords

least mean squares methods; smoothing methods; splines (mathematics); statistical analysis; automatic data-smoothing algorithm; cubic spline functions; digital oscilloscopes; filtering bandwidth; least-squares fitting; minimum mean squared error; noisy data; optimal knot selection; root-mean-square error; spline functions; statistical assumptions; Bandwidth; Filtering algorithms; Measurement errors; Noise measurement; Oscilloscopes; Sampling methods; Smoothing methods; Spline; White noise; Yield estimation; data smoothing; estimation; multiresolution analysis; spline functions;

fLanguage

English

Publisher

ieee

Conference_Titel

Instrumentation and Measurement Technology Conference Proceedings, 2008. IMTC 2008. IEEE

Conference_Location

Victoria, BC

ISSN

1091-5281

Print_ISBN

978-1-4244-1540-3

Electronic_ISBN

1091-5281

Type

conf

DOI

10.1109/IMTC.2008.4546998

Filename

4546998