A Bayesian network (BN) decoder for direct‐conversion microwave and millimeter‐wave six‐port receivers (SPRs)

In this paper, learning algorithms are used to decode QPSK data in a direct‐conversion hardware (QPSK‐unimode) microwave/millimeter‐wave receiver using an application‐specific six‐port module. Two different algorithms, the K ‐means and Bayesian network, are considered for operation of the decoder to recover IQ data from QPSK modulated signals. Bit‐error‐rate (BER) results versus noise level ( E b / N 0 ) are presented after a brief data‐collecting period involving fewer than 500 data points. Results of the Bayesian network for E b / N 0 =−3 dB and E b / N 0 =−9 dB are presented, using the same data‐gathering period. © 2001 John Wiley & Sons, Inc. Microwave Opt Technol Lett 30: 33–38, 2001.