A framework to assist to the modeling, classification, and identification of PCB designs involving different topological approaches is proposed based on the analysis of scattering parameters. The underlying idea is to break down the relevant information hidden in the network topology to a flattened latent space via an encoder-decoder structure. Various machine learning and optimization methods are proposed using the trained encoder or decoder as upstream or downstream component.

The implementation of an anomaly detection with a decision tree was investigated with respect to the evaluation of selected SI effects in PCB design. The tree based approach allows the designer to understand the proposals more easily (explainable AI). High prediction accuracies for two simple networks were achieved with the proposed method. The use of anomaly detection with a decision tree will be further developed in future work for various more complex SI applications in circuit design.

The effects of parameters (decaps, power plane and stackup) affecting the input impedance of a power delivery network are investigated. An artificial neural network is trained using the generated data utilizing a process to generate suitable input for training a machine learning module, which is able to predict the impedance profile of the PDN. In order to obtain a more accurate prediction, Bayesian optimization is implemented and the results are compared to commercial power integrity software.

Autonomous driving is handled as one of the key technologies of the current era. Safety proofs for this form of transportation are partly carried out using simulations. In this paper the response of roads made of rough asphalts and concrete to radar signals is investigated, to create a database improving the accuracy of such simulations. The measurements are performed in a laboratory using specific samples of roads. The setup is validated as well, and the results are described mathematically.

Based on new archive sources, it is shown that Egbert von Lepel is one of the pioneers of early radio technology, which has not been adequately dealt with in the history of radio science. In particular, the significance of his 1907 patent of the spark-gap transmitter ("Löschfunkensender") is unknown, although it was granted as a key patent by the Imperial Patent Office in 1911. Therefore, Telefunken paid licenses to von Lepel, but this was the subject of a secret treaty of 1919.

In this paper, a two-stage artificial intelligence framework for supporting the signal integrity compliant printed circuit board design process has been developed. This framework was applied to compare linear and non-linear data, which showed that the non-linear data source gains advantages over the linear data in terms of attainable regression accuracy. For the investigated application however, the linear model can be utilized directly or by utilizing transfer learning for adequate results.