AN HMM APPROACH TO ADAPTIVE DEMODULATION OF QAM SIGNALS IN FADING CHANNELS

In this paper the techniques of extended Kalman filtering (EKF) and hidden Markov model (HMM) signal processing are combined to adaptively demodulate quadrature amplitude-modulated (QAM) signals in noisy fading channels. This HMM approach is particularly suited to signals for which the message symbols are not equally probable, as is the case with many types of coded signals. Our approach is to formulate the QAM signal by a finite-discrete state process and represent the channel model by a continuous state process. The mixed state model is then reformulated in terms of conditional information states using HMM theory. This leads to models which are amenable to standard EKF or related techniques. A sophisticated EKF scheme with an HMM subfilter is discussed, as well as more practical schemes coupling discrete state HMM filters and continuous state Kalman filters. The case of white noise is considered, as well as generalizations to cope with coloured noise. Simulation studies demonstrate the improvement gained over standard schemes.