Multi-Task Deep Learning Based Hybrid Precoding for mmWave Massive MIMO System

Due to the different signal-to-noise ratio(SNR)of each subchannel,the bit error rate(BER)of hybrid precoding based on singular value decomposition(SVD)decreases.In this paper,we propose a multi-task learning based precoding network(PN)model to solve the BER loss problem caused by SVD based hybrid precoding under imperfect channel state information(CSI).Specifically,we firstly generate a dataset including imcomplete CSI input channel matrix and corresponding output labels to train the PN model.The output labels are designed based on uniform channel decomposition(UCD)which decomposes the channel into multiple subchannels with same gain,while the vertical-bell layered space-time structure(V-BLAST)signal processing technology is combined to eliminate the inner interference of the subchannels.Then,the PN model is trained to design the analog and digital precoding/combining matrix simultaneous.Simulation results show that the proposed scheme has only negligible gap in spectrum efficiency compared with the fully digital precoding,while achieves better BER performance than SVD based hybrid precoding.

Decomposition of the equation of state of asymmetric nuclear matter into different spin-isospin channels

We investigate the equation of state of asymmetric nuclear matter and its isospin dependence in various spin-isospin ST channels within the framework of the Brueckner-Hartree-Fock approach extended to include a microscopic three-body force（TBF） . It is shown that the potential energy per nucleon in the isospinsinglet T = 0 channel is mainly determined by the contribution from the tensor SD coupled channel. At high densities,the TBF effect on the isospin-triplet T = 1 channel contribution turns out to be much larger than that on the T =0 channel contribution. At low densities around and below the normal nuclear matter density,the isospin dependence is found to come essentially from the isospin-singlet SD channel and the isospin-triplet T = 1 component is almost independent of isospin asymmetry. As the density increases,the T = 1 channel contribution becomes sensitive to the isospin asymmetry and at high enough densities its isospin dependence may even become more pronounced than that of the T = 0 contribution. The present results may provide some microscopic constraints for improving effective nucleon-nucleon interactions in a nuclear medium and for constructing new functionals of effective nucleon-nucleon interaction based on microscopic many-body theories.