| Summary: | In this study, an efficient model of the channel matrix is developed for a <inline-formula> <tex-math notation="LaTeX">$2\times $ </tex-math></inline-formula> 2 wireless body area network multiple input output (WBAN-MIMO) system based on deep learning algorithms. The model is composed of three deep-learning algorithms. Moreover, the model simultaneously predicts channel matrix <inline-formula> <tex-math notation="LaTeX">$H$ </tex-math></inline-formula> in an underground mine and identifies the position of the collected data in both line-of-sight (LoS) and non-line-of-sight (NLoS) scenarios. The model was trained and evaluated using the magnitude and phase of the collected data in an underground mine environment within a frequency range of 2.3 GHz – 2.5 GHz. These measurements, conducted with different antenna configurations in the LoS and NLoS scenarios, constitute an input to the model. The latest predicts the channel matrix <inline-formula> <tex-math notation="LaTeX">${H}$ </tex-math></inline-formula> with position and identifies whether the channel is a LoS or NLoS. Finally, the path loss and channel impulse response models were compared with measurement-based models. The modeled channel prediction exhibited a lower root mean square error (RMSE) for channel prediction and high classification accuracy for LoS-NLoS and position identification, respectively. The numerical results reveal that deep learning WBAN-MIMO modeling offers a powerful solution for future wireless systems in underground mine environments.
|
|---|