Physics-informed neural networks for pathloss prediction

This paper introduces a physics-informed machine learning approach for pathloss prediction. This is achieved by including in the training phase simultaneously (i) physical dependencies between spatial loss field and (ii) measured pathloss values in the field. It is shown that the solution to a proposed learning problem improves generalization and prediction quality with a small number of neural network layers and parameters. The latter leads to fast inference times which are favorable for downstream tasks such as localization. Moreover, the physics-informed formulation allows training and prediction with small amount of training data which makes it appealing for a wide range of practical pathloss prediction scenarios.

Generative Adversarial Networks for Pseudo-Radio-Signal Synthesis

For many wireless communication applications, traffic pattern modeling of radio signals combined with channel effects is much needed. While analytical models are used to capture these phenomena, real world non-linear effects (e.g. device responses, interferences, distortions, noise) and especially the combination of such effects can be difficult to capture by these models. This is simply due to their complexity and degrees of freedom which can be hard to explicitize in compact expressions. In this paper, we propose a more model-free approach to jointly approximate an end-to-end black-boxed wireless communication scenario using software-defined radio platforms and optimize for an efficient synthesis of subsequently similar 'pseudo-radio-signals'. More precisely, we implement a generative adversarial network based solution that automatically learns radio properties from recorded prototypes in specific scenarios. This allows for a high degree of expressive freedom. Numerical results show that the prototypes' traffic patterns jointly with channel effects are learned without the introduction of assumptions about the scenario or the simplification to a parametric model.

Leveraging Machine Learning for Industrial Wireless Communications

Two main trends characterize today's communication landscape and are finding their way into industrial facilities: the rollout of 5G with its distinct support for vertical industries and the increasing success of machine learning (ML). The combination of those two technologies open the doors to many exciting industrial applications and its impact is expected to rapidly increase in the coming years, given the abundant data growth and the availability of powerful edge computers in production facilities. Unlike most previous work that has considered the application of 5G and ML in industrial environment separately, this paper highlights the potential and synergies that result from combining them. The overall vision presented here generates from the KICK project, a collaboration of several partners from the manufacturing and communication industry as well as research institutes. This unprecedented blend of 5G and ML expertise creates a unique perspective on ML-supported industrial communications and their role in facilitating industrial automation. The paper identifies key open industrial challenges that are grouped into four use cases: wireless connectivity and edge-cloud integration, flexibility in network reconfiguration, dynamicity of heterogeneous network services, and mobility of robots and vehicles. Moreover, the paper provides insights into the advantages of ML-based industrial communications and discusses current challenges of data acquisition in real systems.