AR time-series identification using quantized observations

In the paper an approach to AR time-series identification based on observations obtained using data acquisition system equipped with a quantizer having saturation is presented. In the presented approach AR time-series model identification is replaced by an ARMA time-series model identification that returns parameters of AR time-series. A focus on model identification for ultra low- and ultra high-power AR time-series is given. The presented discussion is illustrated by a simulation case study showing properties of the presented approach.