Energy efficient equalizer design for MIMO OFDM communication systems using improved split complex extreme learning machine

Dual interactive Wasserstein generative adversarial networks optimized with hybrid Archimedes optimization and chimp optimization algorithm‐based channel estimation in OFDM

“…The evaluation metrics is analyzed. The obtained results are assessed with existing MIMO‐OFDM system using DNN and improved AMO model (DNN‐IAMO‐MIMO‐OFDM), 24 MIMO OFDM systems using the DL and optimization (RBFNN‐PSO‐MIMO‐OFDM), 25 and MIMO OFDM systems using HNN (HNN‐CSI‐MIMO‐OFDM) 26 models, respectively.…”

“…Sahoo et al 25 have presented MIMO‐OFDM communication schemes utilizing improved split complex extreme learning machine (ISCELM). The quadrature amplitude modulation (QAM) constellation and IEEE 802.11 indoor channel were used to characterize the fading statistics with constrained user mobility.…”

“…• The experimental outcomes display that the proposed method has very effectiveness for the settings of higher mobility in MIMO-OFDM, 23 when analyzed with other algorithms. • Then the proposed DiWGAN-hybrid (Hyb) Archimedes optimization algorithm (AOA)-chimp optimization algorithm (COA)-MIMO-OFDM method performance is compared with existing MIMO-OFDM system using DNN and improved AMO model (DNN-IAMO-MIMO-OFDM), 24 MIMO OFDM systems using the DL and optimization (RBFNN-PSO-MIMO-OFDM), 25 and MIMO OFDM systems using hybrid neural network (HNN-CSI-MIMO-OFDM) methods. 26 Continual manuscript is designed as follows: Section 2 delimits recent studies, Section 3 explains the proposed method, Section 4 demonstrates the results, and Section 5 concludes this manuscript.…”

“…The key contributions of this manuscript are abridged below: In high mobility situations with non‐stationary channel characteristics, channel estimation for MIMO‐OFDM systems is exceedingly difficult. To deal this issue, a DiWGAN 20 optimized with hybrid Archimedes optimization 21 and chimp optimization algorithm 22 basis MIMO‐OFDM channel estimation approach is proposed. The learning network can be effectively trained offline, and the CSI produced through the training samples to modify the features of quickly changing channels in higher mobility environments. The experimental outcomes display that the proposed method has very effectiveness for the settings of higher mobility in MIMO‐OFDM, 23 when analyzed with other algorithms. Then the proposed DiWGAN‐hybrid (Hyb) Archimedes optimization algorithm (AOA)‐chimp optimization algorithm (COA)‐MIMO‐OFDM method performance is compared with existing MIMO‐OFDM system using DNN and improved AMO model (DNN‐IAMO‐MIMO‐OFDM), 24 MIMO OFDM systems using the DL and optimization (RBFNN‐PSO‐MIMO‐OFDM), 25 and MIMO OFDM systems using hybrid neural network (HNN‐CSI‐MIMO‐OFDM) methods 26 Continual manuscript is designed as follows: Section 2 delimits recent studies, Section 3 explains the proposed method, Section 4 demonstrates the results, and Section 5 concludes this manuscript.…”