Abstract
With a significant increase in the data and demand for large bandwidth, the wireless research community has identified the need to pay attention to transmitting the context rather than focusing on only the manner of transmission. Inspired by this, in the current article a semantic wireless system enabled by deep learning is proposed which aims to maximize the system capacity. As opposed to evaluating only the bit/symbol errors, the proposed technique is able to recover the meaning of sentences and is hence able to minimize the semantic errors. Furthermore, transfer learning is implemented to accelerate the process of re-training. Extensive simulations to validate the performance of the proposed technique demonstrate that it is able to (i) maintain enhanced robustness to channel fluctuations and (ii) achieve higher performance. Overall, the current study makes it evident that the proposed technique is a good candidate for implementation in semantic wireless systems.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call