Quantized Identification and Asymptotic Efficiency
Up to this point, we have been treating binary-valued observations. The fundamental principles and basic algorithms for binary-valued observations can be modified to handle quantized observations as well. One way to understand the connection is to view a quantized observation as a vector-valued binary observation in which each vector component represents the output of one threshold, which is a binary-valued sensor. The dimension of the vector is the number of the thresholds in the quantized sensor.
KeywordsUnbiased Estimator Quantization Error Uniform Quantization Minimum Variance Unbiased Estimator Rational Transfer Function
Unable to display preview. Download preview PDF.
- H. Abut, Ed., Vector Quantization, IEEE Press Selected Reprint Series, IEEE, Piscataway, 1990.Google Scholar
- J.C. Aguero, G.C. Goodwin, J.I. Yuz, System identification using quantized data, in Proc. 46th IEEE Conf. Decision Control, 4263–4268, 2007.Google Scholar
- K. Sayood, Introduction to Data Compression, 2nd ed., Morgan Kaufmann, San Francisco, 2000.Google Scholar