Measurements - Misure
Description: a quantile based estimation tool for IMEKO 2014 Software Session,developed in Matlab by Paolo Carbone and Antonio Moschitta (see the "Download attachment" link below)
Abstract - Signal parametric estimation based on quantized data is often carried out by means of least mean square (LMS) or averaging techniques. Such an approach often leads to optimal performance, resulting in almost unbiased estimators when quantization error can approximately be modeled as an additive white noise, or when other additive white noise sources dominate quantization error. When such hypotheses are not satisfied, however, averaging techniques may produce suboptimal biased estimators. In such a case, maximum likelihood or quantile based identification techniques can be shown to lead to more performing estimators, mostly unbiased and with a lower mean square error than that of a LMS estimator. A software tool is presented, capable of estimating a DC level, a DC level corrupted by AWGN, and sinewave parameters when the frequency is known frequency, using data quantized by a non uniform ADC.