A DNN Architecture for the Detection of Generalized Spatial Modulation Signals
share
In this paper, we consider the problem of signal detection in generalized spatial modulation (GSM) and explore the utility of the deep neural networks (DNN) for the detection task. We propose a DNN architecture which uses small sub-DNNs to detect the active antennas and the constellation symbols transmitted by the active antennas. Under the assumption of i.i.d. additive white Gaussian noise (AWGN), the proposed DNN detector achieves a performance very close to that of maximum likelihood detector. We also analyze the performance of the proposed detector under two conditions of practical interest: i) correlated noise across receive antennas (resulting from mutual coupling, matching networks) and ii) noise distribution deviating from the standard AWGN model. The proposed DNN-based detector learns the deviations from the standard model and achieves superior performance compared to that of conventional maximum likelihood detector.
READ FULL TEXT
