English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Tools annual

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Tools monthly

Global: Zendy Plus monthly

Presents the access of premium content as premium feature

Premium Content

Global: Zendy Plus annual

Global: Zendy Free Plan

Conductive polymer composite materials are used in many technological applications such as supercapacitors, varistors or sensors. Electronic properties of these materials such as dielectric permeability, which are very important for technological applications, show nonlinear behavior depending on basic parameters such as additive rate and temperature. Due to the abundance of possible parameter configurations, it is cumbersome and costly to experimentally determine all the appropriate sets of parameters to achieve the desired values of these properties. It is very important to propose a practical method for determining the required parameter configurations in order for these properties to provide the desired values. In this study, three different machine learning algorithms have been applied for the prediction of real (ε') and imaginary components (ε'') of nonlinear. complex dielectric functions dependent on frequency and PANI concentration (10%, 25% and 50%) of CM1 and KYZ13 basalt doped PANI polymer composites. These algorithms are Linear Regression, kNearest neighbor regression, Decision tree regression machine learning algorithms. The data set required for the training processes of these algorithms was created using experimental dielectric measurements. These experimental data were obtained using an impedance analyzer in the frequency range ranging from 100 Hz to 17.5 MHz at room temperature. In this study, * Sorumlu Yazar: oeyeci@gmail.com Avrupa Bilim ve Teknoloji Dergisi e-ISSN: 2148-2683 818 the prediction performance of linear regression, k-nearest neighbor regression and decision tree regression algorithms are compared in detail. The comparison was determined by using statistical fit, coefficient of determination (R2), mean square error (MSE) and mean absolute error (MAE). Although the Linear Regression algorithm did not show a stable prediction performance with the performance comparison of the prediction results, Decision tree regression model has been found to be a more suitable model for computing both real (ε') and virtual components (ε'').

Bazalt/PANI Kompozitlerinin Dielektrik Özelliklerinin Tahmini için Makine Öğrenmesi Modellerinin Karşılaştırılması