2 results
Filters
Settings
Now showing1 - 2 of 2
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , Analysis of Differential Crosstalk and Transmission for Via Arrays in Low Temperature Cofired Ceramics(2021-05); ; ; ; Given the ubiquitous use of via arrays in multilayer substrates based on organic materials, this work explores ceramic-based solutions instead. Assuming typical design and technology constraints, the performance of via arrays on low temperature cofired ceramics is studied in terms of crosstalk as well as transmission. Both single-ended and differential signaling are considered, thus covering a broad range of use cases for microwave applications and high-speed digital links. By employing single vias optimized with respect to 50O systems as fundamental building blocks for larger via arrays, different array configurations are proposed and analyzed. The question as to what moving from organic to ceramic materials and vice versa implies in terms of electrical performance is investigated. The majority of the work is based on the computationally efficient physics-based via modeling technique due to the size and complexity of the via array models, but comparisons to conventional full-wave solvers show strong agreement between the two methods up to 50GHz.Publicationtype: Conference Paper32 - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Access status: without files , ANN Hyperparameter Optimization by Genetic Algorithms for Via Interconnect ClassificationIn an imbalanced classification problem the distribution of data across the known classes is biased or skewed. It poses a challenge for predictive modeling as most of the machine learning algorithms used for classification were designed around the assumption of an equal number of examples for each class. In this paper, we propose an approach to solve via interconnect classification problems by artificial neural networks, where the optimum hyperparameters of the networks are searched through a genetic algorithm. We solve the binary imbalanced classification problem for vias in time domain and frequency domain, including single and multilabel cases. Imbalanced learning techniques, like random oversampling and weighted binary crossentropy, are studied in combination with the genetic algorithm. We found standardization, F-measure, and imbalanced learning techniques are suitable to deal with minority label classification for this kind of signal integrity problems. The overall accuracy of our method is above 97%.Publicationtype: Conference Paper66