• 作者： Kuang-Jen WANG, Shiunn-Jang CHERN
• 中文摘要： The optimal equalization solution under the classical symbol-by-symbol decision-making architecture is an inherently nonlinear problem; therefore, some degree of nonlinear decision making ability is desirable in the equalizer structure, even for a linear channel. The Bayesian equalizer has been shown to be an optimum solution for a symbol-by-symbol equalizer in terms of signal detection. In this paper, the performance of the adaptive Bayesian decision feedback equalizer (DFE) with the complex radial basis function/stochastic gradient (CRBF/SG) algorithm used as a non-linear channel (e.g., a radio channel with a high-power amplifier) estimator for channel equalization is investigated. Also, the Bayesian decision making (or classification) of the adaptive Bayesian DFE, for the M-level complex signaling scheme, is implemented using the CRBF network. To evaluate the performance of this adaptive Bayesian DFE, the error rate in symbol detection is evaluated and is shown to be better than that of the conventional least mean square (LMS) DFE and other existing methods.
• 英文摘要： --
• 中文關鍵字： adaptive Bayesian equalizer, high power amplifier, non-linear distortion, complex radial basis function, channel estimator
• 英文關鍵字： --