EXPERIMENTAL COMPARISON OF MAXIMUM LIKELIHOOD AND LS FITTING FOR ADC TESTING

Ján Šaliga, Linus Michaeli, Ján Buša, Jozef Lipták, István Kollár, Tamás Virosztek
Abstract:
ADC test methods require the best possible reconstruction of the input signal to the ADC under test from the acquired, therefore erroneous ADC output data. The commonly used LS fit and the recently introduced maximum likelihood estimation are competing methods. This paper presents an experimental comparative study of these estimation methods with the goal to investigate the behaviour of both methods and to determine their limits. An alternative algorithm for the calculation of the maximum likelihood fit is also examined. Some practical recommendations for the choice of optimal method for various conditions of ADC testing are also given as a conclusion of the comparative study.
Keywords:
ADC test, maximum likelihood estimation, least squares method, LS method, four-parameter fit, signal recovery, estimation of signal parameters, differential evolution
Download:
IMEKO-WC-2012-TC4-O1.pdf
DOI:
-
Event details
Event name:
XX IMEKO World Congress
Title:

Metrology for Green Growth

Place:
Busan, REPUBLIC of KOREA
Time:
09 September 2012 - 12 September 2012