A comparison of quantizers optimized for corrupted and uncorrupted input signals |
| |
| Affiliation: | 1. Department of Meteorology and Oceanography, Andhra University, Visakhapatnam, India;2. India Meteorological Department, Hyderabad, Telangana, India;3. Department of Atmospheric Science, KL University, Vaddeswaram, Guntur District, Andhra Pradesh, India;1. Department of Geography, Environment and Population, University of Adelaide, Adelaide, South Australia 5005, Australia;2. Sprigg Geobiology Centre, University of Adelaide, Adelaide, South Australia 5005, Australia;3. School of Physical Sciences, University of Adelaide, Adelaide, South Australia 5005, Australia;4. School of Civil, Environmental and Mining Engineering, University of Adelaide, Adelaide, South Australia 5005, Australia;5. School of Earth, Atmospheric & Life Sciences, Faculty of Science, Medicine and Health, University of Wollongong, Wollongong, NSW 2522, Australia;6. College of Science and Engineering, Flinders University, Bedford Park, South Australia 5042, Australia;7. College of Humanities Arts and Social Sciences, Flinders University, Beford Park, South Australia 5042, Australia;8. School of Biological Sciences, University of Adelaide, Adelaide, South Australia 5005, Australia;9. School of Agriculture, Food and Wine, University of Adelaide, Adelaide, South Australia 5005, Australia;1. Fisheries and Oceans Canada, 867 Lakeshore Road Burlington, Ontario, L7S 1A1, Canada;2. University of Toronto Scarborough Department of Biological Sciences, 1265 Military Trail Toronto, Ontario, M1C 1A4, Canada |
| |
| Abstract: | It is known from literature how to design optimal quantizers for input signals with a given probability density function. In this paper, optimal quantizers for input signals corrupted by noise are designed. In addition to that it is shown by a separation theorem that the optimal quantizer can be replaced by an estimator for the corrupted input signal followed by an optimal quantizer for the estimate. Furthermore, some numerical results for processes with a Gaussian probability density function are given. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
