A Semantic-Oriented Federated Learning for Hybrid Ground-Aqua Computing Systems

Nowadays, an ambitious target of the next gener- ation networks is to develop intelligent overarching space-air- ground-aqua environments, in order to provide a smart ecosystem able to efficiently operate in heterogeneous domains. In partic- ular, in such a context, the underwater environment requires a special attention, since it is recognized as the most challenging domain, due to channel impairments and adverse propagation conditions. This paper proposes an example of a self-intelligent system able to efficiently perform underwater environment mon- itoring or underwater survey of critical infrastructure. The main goal, is to highlight the effectiveness of the use of the semantic communication paradigm in order to provide Machine Learning capabilities at the edge of the system. In particular, in our case, images sent by underwater devices are collected by shore small base stations (SSBSs) to form their training dataset to take part in a federated learning process with a ground base station. In reference to this, the paper considers a semantic communication scheme based on a deep-convolution neural networks encoder- decoder architecture for an efficient exploitation of the data transmission from underwater devices to SBSs. Performance analysis is provided to show the better behavior of the proposed system in comparison with the conventional alternative that does not involve the use of the semantic communications approach. Finally, a specific performance evaluation analysis is devoted to the investigation of the convergence behavior of the proposed federated learning procedure in reference to the cross ground- aqua system considered in order to validate its advantages with respect to a classical implementation