Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Correlation between structural and electrical properties in highly porous (Y,Sr)(Ti,Nb)O3−δ SOFC anodes

Miruszewski T, Trawiński B., Gałka M., Morzy J, Bochentyn B, Karczewski J., Gdaniec P, Gazda M., Kusz B.

Materials Science Poland

2014

Vol. 32, No. 3

331--340

In order to find a relationship between structural and electrical properties, niobium and yttrium doped SrTiO3 ceramics were prepared via solid-state reaction. The samples were sintered in hydrogen and air conditions. The samples were also fabricated with a pore-former to obtain highly porous specimens. The electrical properties of Nb-doped SrTiO3 samples and yttrium and niobium co-doped SrTiO3 were compared. The comparable electrical properties were observed and discussed according to previous literature reports. It was noticed that the synthesis in a reducing hydrogen atmosphere can increase the solubility of dopants. Moreover, the samples sintered in air presented lower conductivity level and worse structural properties than the samples sintered in hydrogen. The explanation of obtained results was also suggested and discussed.

Nonparametric statistical analysis for multiple comparison of machine learning regression algorithms

Trawiński B., Smętek M., Telec Z., Lasota T.

International Journal of Applied Mathematics and Computer Science

2012

Vol. 22, no. 4

867-881

In the paper we present some guidelines for the application of nonparametric statistical tests and post-hoc procedures devised to perform multiple comparisons of machine learning algorithms. We emphasize that it is necessary to distinguish between pairwise and multiple comparison tests. We show that the pairwise Wilcoxon test, when employed to multiple comparisons, will lead to overoptimistic conclusions. We carry out intensive normality examination employing ten different tests showing that the output of machine learning algorithms for regression problems does not satisfy normality requirements. We conduct experiments on nonparametric statistical tests and post-hoc procedures designed for multiple 1 x N and N x N comparisons with six different neural regression algorithms over 29 benchmark regression data sets. Our investigation proves the usefulness and strength of multiple comparison statistical procedures to analyse and select machine learning algorithms.