In this paper, a customized Auto-Encoder Complex Valued Convolutional Neural Network (AE-CV-CNN) that has been developed in a prior work is applied to Single Symbol Generalized Spatial Modulation (SS-GSM) scheme with new extracted features. The achieved reductions in the computational complexity at the receiver is at least 63.64% for M-PSK schemes compared to the complexity of Maximum Likelihood (ML) detection algorithm. This Fast detection algorithm is based on a proposed Low Complexity ML (LC-ML) detector that affords a complexity reduction of at least 40.91%. With these proposed algorithms, the complexity is reduced as the spatial constellation size increases. Furthermore, in comparison to other sub optimal detection algorithms, the computational complexity in terms of real valued multiplications of the AE-CV-CNN applied to LC-ML is independent of the spatial spectrum efficiency which means that the total spectrum efficiency increases with larger spatial constellation size at no additional complexity.
Akram A. Marseet , Taissir Y. Elganimi(10-2019)

A multi-relay cooperative diversity protocol based on the concept of Generalized Spatial Modulation (GSM) scheme is proposed in this paper, assuming that decode-and-forward relaying protocol is adopted at relays. This scheme is referred to as Distributed Generalized Spatial Modulation (DGSM) with activating more than one relay. The system performance of the proposed diversity protocol in terms of the Symbol Error Rate (SER) is evaluated and compared to the performance of GSM and Distributed Spatial Modulation (DSM) schemes. Simulation results show that DGSM systems with activating more than one relay perform almost the same as DSM systems for the same spectral efficiency. It is also demonstrated that a performance enhancement of about 3 dB is achieved over GSM schemes for the same modulation order, which increases the energy efficiency and the reachability using the proposed model. Therefore, the proposed scheme can be effectively used in various 5G wireless networks.
Taissir Y. Elganimi, Fatima I. Alwerfly, Akram A. Marseet(10-2020)

Multiple Input Multiple Output (MIMO) systems with limited Radio Frequency (RF) chains play a pivotal role in the Fifth Generation (5G) of wireless networks. However, the transmitter of Generalized Spatial Modulation MIMO (GSM-MIMO) systems that characterized by a single RF chain and multiple active antennas is capable of reducing both the energy consumption and the transmitter cost. In this paper, combining GSM-MIMO systems with the fully digital Geometric Mean Decomposition (GMD)-based precoding scheme and Analog Beamforming (ABF) into Hybrid Beamforming (HBF) regime is presented for Millimeter-wave (mmWave) massive MIMO systems which is a key enabler for 5G networks. In addition, applying the norm-based user selection algorithm in GSM-MIMO scheme with GMD-based hybrid precoding is proposed, and referred to as Multiuser Steered GSM-MIMO (MUS-GSM-MIMO) scheme. Simulation results demonstrate that the proposed schemes are capable of achieving considerable performance gains over the conventional GSM-MIMO schemes, while avoiding the overwhelming costs of multiple RF chains. Therefore, the proposed schemes are very efficient and highly suitable for large-scale and 5G wireless networks.
Taissir Y. Elganimi, Amani A. Aturki(9-2020)