Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Powiadomienia systemowe

Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

Assessment of the middle cerebral artery spasm with learning vector quantization neural networks

Świercz M., Krejza J., Mariak Z., Bień M.

Biocybernetics and Biomedical Engineering

2004

Vol. 24, no. 1

3-16

With transcranial color-coded Doppler sonography (TCCS), blood velocity in the middle cerebral (MCA) can be measured and used for diagnosis os spasm in this artery. The interpretation of TCCS results is not straightforward however. In this study blood velocities in the MCA's, obtained in one hundred consecutive patients, were classified with the use of artificial neural networks. The results of cerebral angiography were used as the criteria for evaluation of classification accuracy. The neural networks show very good performance in the two-class separation problem. In moderate-to-severe spasm detection, classification accuracy amounted to 92 % and in the assessment of vasospasm of other grades - 87%. The accuracy was higher than that obtained by the human investigator.

Existence of global weak solutions for coupled thermoelasticity with Barber`s heat exchange condition

Bień M.

Journal of Applied Analysis

2003

Vol. 9, nr 2

163-185

The existence of global weak solutions for coupled thermoelasticity with the nonlinear contact boundary condition and Barber's heat exchange condition is proved via the Faedo-Galerkin, monotonic-ity and compactness methods. Some a priori bounds obtained with Gronwalls inequality in connection with the embedding and trace theorems lead to accomplishing a generalization of our previous study [5]. The heat-exchange coefficient associated with Barber's heat exchange condition is dependent only on the normal displacement. This dependence is described by a bounded Lipschitz function. Moreover, this study is some extension of works due to Andrews et al. [3] and Elliot et al. [12].