Andrius Katkevičius

TL;DR: The procedure of synthesis of the meander delay system is presented using the Pareto-optimal multilayer perceptron network and multiple linear regression model with the M5 descriptor and the prediction of parameters allowed to speed up the process of synthesis multiple times from hours to only 2.3 s.

TL;DR: In this paper, the authors presented a procedure for analyzing a hybrid meander system (HMS) using the feed-forward backpropagation network (FFBN), and compared the prediction results of the transmission factor S 21 ( f ) and the reflection factor S 11 ( f ), obtained using the FFBN, with results obtained using traditional analytical and numerical methods, as well as with experimental results.

TL;DR: An artificial neural network is proposed to be used as the universal approximator for solving mathematical problems of delay system investigation instead of usual analytical and numerical techniques.

TL;DR: In this article, the model of the system based on the multi-conductor line method is used, and properties of the non-homogeneous helical systems are revealed, showing that the stop-band appears when the phase angle between the voltages on the neighbor conductors of the helix approach π.

TL;DR: According to results of simulation, using formed meander electrodes, the system can considerably increase characteristic impedance and ensure the wide-pass-band of the signal path.