Reduced state BCJR algorithms for one- and two-dimensional equalization

We consider BCJR-like soft-input soft-output (SISO) iterative detection algorithms for 1D and 2D binary-input ISI channels with AWGN. The complexity of BCJR algorithms grows exponentially with the size of the ISI mask and is an important concern with their implementation. We consider new techniques to reduce the complexity of BCJR algorithms by decreasing the effective number of states in the trellis. The proposed state reduction technique does particularly well for mixed phase sequence ISI masks, which have higher weights for the center taps and lower weights for the peripheral taps. Other complexity reduction techniques proposed in the literature perform poorly for such masks. Moreover, the complexity of the proposed state reduction technique is comparable to other reduced complexity techniques reported in the literature. Experimental results are provided to demonstrate the advantages of the proposed state reduction technique.