LAUSR

In view of the propagation environment directly determining the channel properties, the applications can also be solved with the aid of environmental information. Inspired by task-oriented semantic communication and machine learning (ML) powered environment-channel mapping methods, we aim to provide a new view of the environment from the semantic level. This letter defines propagation environment semantics (PES) as a limited set of propagation environment semantic symbols (PESS). The PESS is extracted, which is oriented to the application tasks with concerned channel properties as a foundation. For method validation, the PES-aided beam prediction (PESaBP) is investigated and implemented for non-line-of-sight (NLOS) scenarios. Environment features and graph representations are constructed for actions of channel quality evaluation and target scatterer detection with maximum power. It can obtain 0.92 and 0.9 precision, respectively, and save over 87% of the time cost.