Efficient Channel Coding and Error Correction in MIMO-OFDM by Using Spatio Temporal Joint Graph Convolutional Networks

Due to the dependability, spatial multiplexing and increased spatial diversity gain, Orthogonal frequency division multiplexing (OFDM) and multiple input, multiple output (MIMO) have received lot of attention. However, MIMO-OFDM suffers from communication problems like inter symbol as well as inter carrier interference. In this study, Efficient Channel Coding and Error Correction in MIMO-OFDM Using Spatio Temporal Joint Graph Convolutional Networks (MIMO-OFDM-EC-STJGCN) developed to solve data transmission mistakes. To enable improved data broadcasting over MIMO-OFDM, the Spatio Temporal Joint Graph Convolutional Networks (STJGCN) techniques are applied. Therefore, inter carrier, inter symbol interference arose in MIMO-OFDM decreased by MIMO-OFDM-EC-STJGCN attain less Bit Error Rate (BER). The performance of MIMO-OFDM-EC-STJGCN method implemented in MATLAB using Test accuracy, Sum communication cost, BER, peak signal to noise ratio (PSNR).PSNR in MIMO-OFDM-EC-STJGCN is 28.47%, 29.27%, and 28.54% which is high when compared with existing researches such as Wireless Image Transfer utilizing Deep Source Channel Coding with Attention Modules (MIMO-OFDM-EC-ADJSCC), OFDM-guided Deep Joint Source Channel Coding for Wireless Multiple path Fading networks (MIMO-OFDM-EC-CNN) and Nonlinear Transform Source-Channel Coding for Semantic Communications (MIMO-OFDM-EC-NTSCC) respectively.