TY - JOUR T1 - Neural Network Aided Computation of Mutual Information for Adaptation of Spatial Modulation JF - IEEE Transactions on Communications Y1 - 2020 A1 - Anxo Tato A1 - Carlos Mosquera A1 - Pol Henarejos A1 - Ana Pérez Neira KW - ACM KW - Adaptive Communications KW - Capacity KW - Index Modulation KW - link adaptation KW - Machine Learning KW - MFNN KW - Mutual Information KW - neural networks KW - Polarized Modulation KW - Spatial Modulation AB -

Index Modulations, in the form of Spatial Modulation or Polarized Modulation, are gaining traction for both satellite and terrestrial next generation communication systems. Adaptive Spatial Modulation based links are needed to fully exploit the transmission capacity of time-variant channels. The adaptation of code and/or modulation requires a real-time evaluation of the channel achievable rates. Some existing results in the literature present a computational complexity which scales quadratically with the number of transmit antennas and the constellation order. Moreover, the accuracy of these approximations is low and it can lead to wrong Modulation and Coding Scheme selection. In this work we apply a Multilayer Feedforward Neural Network to compute the achievable rate of a generic Index Modulation link. The case of two antennas/polarizations is analyzed in depth, showing not only a one-hundred fold decrement of the Mean Square Error in the estimation of the capacity as compared with existing analytical approximations, but also a fifty times reduction of the computational complexity. Moreover, the extension to an arbitrary number of antennas is explained and supported with simulations. More generally, neural networks can be considered as promising candidates for the practical estimation of complex metrics in communication related settings.

SN - 1558-0857 ER - TY - CONF T1 - Deep Learning Assisted Rate Adaptation in Spatial Modulation Links T2 - 16th International Symposium on Wireless Communication Systems (ISWCS) Y1 - 2019 A1 - Anxo Tato A1 - Carlos Mosquera KW - Deep Learning KW - link adaptation KW - Machine Learning KW - Spatial Modulation AB -

The adaptation of Spatial Modulation based links to the channel conditions is challenged by the complicated dependence between performance (either error rate metrics or theoretically achievable rates) and the multiple antenna channel description. In this paper a coding rate selection mechanism is presented based on a carefully selected set of channel features and the proper training of a deep neural network, which all together can satisfy a given error rate bound.

JF - 16th International Symposium on Wireless Communication Systems (ISWCS) CY - Oulu (Finland) ER - TY - CONF T1 - Spatial Modulation for Beyond 5G Communications: Capacity Calculation and Link Adaptation T2 - 2nd XoveTIC Conference Y1 - 2019 A1 - Anxo Tato A1 - Carlos Mosquera KW - 5G KW - adaptive coding and modulation KW - Deep Learning KW - link adaptation KW - Machine Learning KW - neural networks KW - Spatial Modulation JF - 2nd XoveTIC Conference CY - A Coruña (Spain) ER -